# ZeroLLM - Free LLM Providers & Models

## Providers
- [AIHubMix](https://aihubmix.com/) (aihubmix) - Nền tảng API AI Router & Model Hub hỗ trợ giao thức tương thích OpenAI với Base URL https://api.aihubmix.com/v1 và cung 
- [BAI](https://b.ai/) (bai) - Next-generation AI inference and developer routing platform offering free API access to leading models including DeepSee
- [Cerebras AI](https://cerebras.ai) (cerebras) - Wafer-Scale Engine wafer-chip hardware delivering unmatched generation speeds up to 2,000 tokens per second for Llama 3 
- [Cloudflare Workers AI](https://workers.cloudflare.com) (cloudflare-workers-ai) - Serverless GPU edge computing platform delivering 10,000 free daily Neurons for Llama 3.3, DeepSeek R1 Distill, and Whis
- [Cloudflare Workers AI](https://workers.cloudflare.com) (cloudflare-workers) - Serverless GPU edge computing platform delivering 10,000 free daily Neurons for Llama 3.3, DeepSeek R1 Distill, and Whis
- [Cohere](https://cohere.com) (cohere) - Enterprise NLP powerhouse offering free developer trial keys with generous rate limits for Command R, Command R+, and mu
- [DeepInfra](https://deepinfra.com) (deepinfra) - Serverless GPU inference. $5 free credit on signup.
- [Fal AI](https://fal.ai) (fal-ai) - 
- [Featherless AI](https://featherless.ai) (featherless-ai) - 
- [Fireworks AI](https://fireworks.ai) (fireworks-ai) - 
- [FreeLLMAPI](https://freellmapi.co/) (freellmapi) - Open-source unified API gateway and smart router aggregating free LLM tiers across 30+ providers with 0$ token cost, int
- [GitHub Models](https://github.com/marketplace/models) (github-models) - GitHub official free AI inference playground giving developers direct OpenAI, Llama 3.3, and Azure AI model access with 
- [Google AI Studio](https://aistudio.google.com) (google-aistudio) - Official developer interface for Gemini models featuring 1 million+ token context window, audio/video input, and high sp
- [Groq](https://groq.com) (groq) - Ultra-fast LPU inference engine powering open-weights models like Llama 3.3, DeepSeek R1, Gemma 2, and Whisper at multi-
- [Hugging Face Inference API](https://huggingface.co) (huggingface) - Serverless inference endpoint hosting thousands of open-source fine-tuned models and community releases for free.
- [Infini-AI (Infinigence)](https://cloud.infini-ai.com) (infini-ai) - Infini-AI GenStudio high-performance platform granting developer free inference tiers and complimentary tokens.
- [Kira AI](https://kiraai.vn/) (kira-ai) - High-performance AI model routing and developer platform offering free API access to leading models including Qwen 3.8 F
- [Mistral AI (La Plateforme)](https://mistral.ai) (mistral) - European AI champion offering free developer tier access to open-weights models like Mistral Small, Codestral, and Pixtr
- [ModelScope](https://modelscope.cn/my/myaccesstoken) (modelscope) - From open-free-llm-api/awesome-freellm-apis table 'Provider Directory': ModelScope
- [Novita](https://novita.ai) (novita) - 
- [NVIDIA Build NIMs](https://build.nvidia.com) (nvidia-nim) - NVIDIA official cloud microservices platform hosting optimized inference containers for DeepSeek R1, Llama 3.3 70B, and 
- [OpenCode](https://opencode.ai) (opencode) - AI code engine and multi-model router platform offering OpenAI-compatible endpoints with Base URL https://opencode.ai/ze
- [OpenRouter](https://openrouter.ai) (openrouter) - Unified AI gateway hosting over 20+ completely free LLM models alongside paid endpoints with zero minimum commitment.
- [OrcaRouter](https://www.orcarouter.ai) (orcarouter) - High-speed unified AI model routing & aggregation gateway providing ultra-low latency inference, high-availability failo
- [Replicate](https://replicate.com) (replicate) - 
- [SambaNova Systems](https://sambanova.ai) (sambanova) - SN40L Reconfigurable Dataflow Unit architecture serving full-size 671B parameter DeepSeek R1 and Llama 3.3 70B at ultra 
- [SiliconFlow (SiliconCloud)](https://siliconflow.cn) (siliconflow) - High-performance Asian AI infrastructure providing free endpoints for DeepSeek V3/R1, Qwen 2.5 72B, and GLM open-source 
- [xKiro](https://xkiro.com) (xkiro) - High-performance distributed AI inference cloud offering free access to DeepSeek V4, Mistral, Qwen3, MiniMax, and MiMO m
- [ZenMux](https://zenmux.ai) (zenmux) - Unified AI routing platform & model proxy offering OpenAI-compatible endpoints with Base URL https://zenmux.ai/api/v1 an
- [Zhipu AI (BigModel)](https://bigmodel.cn) (zhipu-ai) - Zhipu AI official developer platform offering GLM-4-Flash permanently 100% free with unmetered standard token usage.

## Models
- qwen3-32b-abliterated (ctx: N/A, free: yes) - https://featherless.ai/models/huihui-ai/Qwen3-32B-abliterated
- opencodereasoning-nemotron-7b (ctx: N/A, free: yes) - https://featherless.ai/models/nvidia/OpenCodeReasoning-Nemotron-7B
- meta-llama-3-70b (ctx: N/A, free: yes) - https://featherless.ai/models/meta-llama/Meta-Llama-3-70B
- medgemma-27b-text-it (ctx: N/A, free: yes) - https://featherless.ai/models/google/medgemma-27b-text-it
- nvidia-nemotron-3-super-120b-a12b-bf16 (ctx: N/A, free: yes) - https://featherless.ai/models/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- phi-3-mini-4k-instruct (ctx: N/A, free: yes) - https://featherless.ai/models/microsoft/Phi-3-mini-4k-instruct
- fietje-2-chat (ctx: N/A, free: yes) - https://featherless.ai/models/BramVanroy/fietje-2-chat
- smaug-llama-3-70b-instruct-abliterated-v3 (ctx: N/A, free: yes) - https://featherless.ai/models/failspy/Smaug-Llama-3-70B-Instruct-abliterated-v3
- nuextract (ctx: N/A, free: yes) - https://featherless.ai/models/numind/NuExtract
- nvidia-nemotron-3.5-lightning-30b-a3b-bf16 (ctx: N/A, free: yes) - https://app.fireworks.ai/models/fireworks/nvidia-nemotron-3.5-lightning-30b-a3b-bf16
- psycopref-llama3-8b (ctx: N/A, free: yes) - https://featherless.ai/models/Psychotherapy-LLM/PsyCoPref-Llama3-8B
- cantonesellmchat-v1.0-7b (ctx: N/A, free: yes) - https://featherless.ai/models/hon9kon9ize/CantoneseLLMChat-v1.0-7B
- llama-3.1-70b-instruct (ctx: N/A, free: yes) - https://featherless.ai/models/meta-llama/Llama-3.1-70B-Instruct
- llama-3.1-alternatetokenizer (ctx: N/A, free: yes) - https://featherless.ai/models/teknium/Llama-3.1-AlternateTokenizer
- nemotron-orchestrator-8b (ctx: N/A, free: yes) - https://featherless.ai/models/nvidia/Nemotron-Orchestrator-8B
- llama-3.2-3b (ctx: N/A, free: yes) - https://featherless.ai/models/meta-llama/Llama-3.2-3B
- llama-3-70b-instruct-abliterated (ctx: N/A, free: yes) - https://featherless.ai/models/failspy/llama-3-70B-Instruct-abliterated
- dolphin-2.9.1-llama-3-70b (ctx: N/A, free: yes) - https://featherless.ai/models/dphn/dolphin-2.9.1-llama-3-70b
- mg-finalmix-72b (ctx: N/A, free: yes) - https://featherless.ai/models/Undi95/MG-FinalMix-72B
- darkidol-llama-3.1-8b-instruct-1.2-uncensored (ctx: N/A, free: yes) - https://featherless.ai/models/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
- glm-4-9b-0414 (ctx: N/A, free: yes) - https://featherless.ai/models/zai-org/GLM-4-9B-0414
- qwen2.5-coder-1.5b (ctx: N/A, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-Coder-1.5B
- fastapply-1.5b-v1.0 (ctx: N/A, free: yes) - https://featherless.ai/models/Kortix/FastApply-1.5B-v1.0
- qwen2.5-coder-14b (ctx: N/A, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-Coder-14B
- deepseek-r1-distill-llama-8b (ctx: N/A, free: yes) - https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- oolel-v0.1 (ctx: N/A, free: yes) - https://featherless.ai/models/soynade-research/Oolel-v0.1
- jailbreak-r1 (ctx: N/A, free: yes) - https://featherless.ai/models/yukiyounai/Jailbreak-R1
- gemma-4-31b-styletune (ctx: N/A, free: yes) - https://featherless.ai/models/Gryphe/Gemma-4-31B-StyleTune
- apollo-0.5b (ctx: N/A, free: yes) - https://featherless.ai/models/FreedomIntelligence/Apollo-0.5B
- qwen2.5-1.5b-instruct-abliterated (ctx: N/A, free: yes) - https://featherless.ai/models/huihui-ai/Qwen2.5-1.5B-Instruct-abliterated
- llama-3.2-1b (ctx: N/A, free: yes) - https://featherless.ai/models/meta-llama/Llama-3.2-1B
- llama-3.3-70b-vulpecula-r1 (ctx: N/A, free: yes) - https://featherless.ai/models/Sao10K/Llama-3.3-70B-Vulpecula-r1
- mythos-nano (ctx: N/A, free: yes) - https://featherless.ai/models/squ11z1/Mythos-nano
- swe-agent-lm-32b (ctx: N/A, free: yes) - https://featherless.ai/models/SWE-bench/SWE-agent-LM-32B
- arch-router-1.5b (ctx: N/A, free: yes) - https://featherless.ai/models/katanemo/Arch-Router-1.5B
- qwen3-14b-abliterated (ctx: N/A, free: yes) - https://featherless.ai/models/mlabonne/Qwen3-14B-abliterated
- llama-3.1-nemotron-nano-8b-v1 (ctx: N/A, free: yes) - https://featherless.ai/models/nvidia/Llama-3.1-Nemotron-Nano-8B-v1
- qwen3-4b-heretic (ctx: N/A, free: yes) - https://featherless.ai/models/DreamFast/qwen3-4b-heretic
- strand-rust-coder-14b-v1 (ctx: N/A, free: yes) - https://featherless.ai/models/Fortytwo-Network/Strand-Rust-Coder-14B-v1
- phi-4-mini-reasoning (ctx: N/A, free: yes) - https://featherless.ai/models/microsoft/Phi-4-mini-reasoning
- llama-3-smaug-8b (ctx: N/A, free: yes) - https://featherless.ai/models/abacusai/Llama-3-Smaug-8B
- qwen3-8b-base (ctx: N/A, free: yes) - https://featherless.ai/models/Qwen/Qwen3-8B-Base
- foundation-sec-8b (ctx: N/A, free: yes) - https://featherless.ai/models/fdtn-ai/Foundation-Sec-8B
- qwen3.8-2.4t-a95b (ctx: N/A, free: yes) - https://app.fireworks.ai/models/fireworks/qwen3.8-2.4t-a95b
- dm-llama3.2-1bi-luciefr-al4-owt-tv-ablation-h2d4 (ctx: N/A, free: yes) - https://featherless.ai/models/Grogros/dm-llama3.2-1BI-LucieFr-Al4-OWT-TV-ablation-h2d4
- dobby-mini-unhinged-plus-llama-3.1-8b (ctx: N/A, free: yes) - https://featherless.ai/models/SentientAGI/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B
- qwen3-coder-480b-a35b-instruct (ctx: N/A, free: yes) - https://featherless.ai/models/Qwen/Qwen3-Coder-480B-A35B-Instruct
- deepcoder-14b-preview (ctx: N/A, free: yes) - https://featherless.ai/models/agentica-org/DeepCoder-14B-Preview
- qwen3-8b-heretic (ctx: N/A, free: yes) - https://featherless.ai/models/DreamFast/qwen3-8b-heretic
- deepseek-v4-pro-0813 (ctx: N/A, free: yes) - https://app.fireworks.ai/models/fireworks/deepseek-v4-pro-0813
- acemath-rl-nemotron-7b (ctx: N/A, free: yes) - https://featherless.ai/models/nvidia/AceMath-RL-Nemotron-7B
- grok-oss-apollyon-24b (ctx: N/A, free: yes) - https://featherless.ai/models/c4tdr0ut/grok-oss-Apollyon-24B
- mamaylm-gemma-2-9b-it-v0.1 (ctx: N/A, free: yes) - https://featherless.ai/models/INSAIT-Institute/MamayLM-Gemma-2-9B-IT-v0.1
- mistral-nemo-instruct-heretic (ctx: N/A, free: yes) - https://featherless.ai/models/saidutta69/Mistral-Nemo-Instruct-heretic
- lucid-v1-nemo (ctx: N/A, free: yes) - https://featherless.ai/models/dreamgen/lucid-v1-nemo
- glm-4-32b-0414 (ctx: N/A, free: yes) - https://featherless.ai/models/zai-org/GLM-4-32B-0414
- qwen3-32b (ctx: N/A, free: yes) - https://featherless.ai/models/Qwen/Qwen3-32B
- qwq-32b-abliterated (ctx: N/A, free: yes) - https://featherless.ai/models/huihui-ai/QwQ-32B-abliterated
- vulnllm-r-7b (ctx: N/A, free: yes) - https://featherless.ai/models/Virtue-AI-HUB/VulnLLM-R-7B
- readerlm-v2 (ctx: N/A, free: yes) - https://featherless.ai/models/jinaai/ReaderLM-v2
- llama-2-7b-chat-hf (ctx: N/A, free: yes) - https://featherless.ai/models/NousResearch/Llama-2-7b-chat-hf
- astrosage-8b (ctx: N/A, free: yes) - https://featherless.ai/models/AstroMLab/AstroSage-8B
- mistral-trismegistus-7b (ctx: N/A, free: yes) - https://featherless.ai/models/teknium/Mistral-Trismegistus-7B
- csg-wukong-1b (ctx: N/A, free: yes) - https://featherless.ai/models/opencsg/csg-wukong-1B
- qwen2.5-0.5b-instruct-abliterated (ctx: N/A, free: yes) - https://featherless.ai/models/huihui-ai/Qwen2.5-0.5B-Instruct-abliterated
- solar-10.7b-v1.0 (ctx: N/A, free: yes) - https://featherless.ai/models/upstage/SOLAR-10.7B-v1.0
- harmbench-llama-2-13b-cls (ctx: N/A, free: yes) - https://featherless.ai/models/cais/HarmBench-Llama-2-13b-cls
- tinyllama-1.1b-chat-v1.0-pruned2.4 (ctx: N/A, free: yes) - https://featherless.ai/models/RedHatAI/TinyLlama-1.1B-Chat-v1.0-pruned2.4
- Gemini-1.5-Pro (ctx: 2097152, free: yes) - https://freellmapi.co/model/gemini-1.5-pro
- Gemini 2.0 Pro Experimental (ctx: 2097152, free: yes) - https://aistudio.google.com
- Gemini-1.5-Pro (ctx: 2097152, free: yes) - https://aistudio.google.com
- Gemini-Exp-1121 (ctx: 2097152, free: yes) - https://freellmapi.co/model/gemini-exp-1121
- Gemini-Exp-1206 (ctx: 2097152, free: yes) - https://freellmapi.co/model/gemini-exp-1206
- Gemini-2.0-Pro-Exp (ctx: 2097152, free: yes) - https://freellmapi.co/model/gemini-2.0-pro-exp
- Kimi-K1.5-Long (ctx: 2000000, free: yes) - https://freellmapi.co/model/kimi-k1.5-long
- Gemini-2.5-Pro (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-2-5-pro
- MiniMax-M3 (ctx: 1048576, free: yes) - https://freellmapi.co/model/minimax-m3
- SiliconFlow-/-InternLM2.5-20B-Chat (ctx: 1048576, free: yes) - https://freellmapi.co/model/siliconflow_internlm_internlm2_5-20b-chat
- Gemini-Flash-Lite-Latest (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-3.1-Flash-Lite-Preview (ctx: 1048576, free: yes) - https://aistudio.google.com
- OpenRouter-/-Gemini-2.0-Flash-Lite:free (ctx: 1048576, free: yes) - https://freellmapi.co/model/google_gemini-2.0-flash-lite-preview:free
- OpenRouter-/-Gemini-2.0-Flash-Thinking:free (ctx: 1048576, free: yes) - https://freellmapi.co/model/google_gemini-2.0-flash-thinking-exp:free
- Gemini-1.5-Flash-8B (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-1.5-flash-8b
- MiniMax-Text-01 (ctx: 1048576, free: yes) - https://freellmapi.co/model/minimax-text-01
- [Confidential] Gemini 3.7 Flash Video Understanding EAP (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-2.0-Flash (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-2.0-flash
- Gemini-2.0-Flash-Thinking-Exp (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-2.0-flash-thinking-exp
- Google Gemini 2.0 Flash Lite Free (ctx: 1048576, free: yes) - https://openrouter.ai
- Gemini-1.5-Flash (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-2.5-Flash-Lite (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-3.5-Flash (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-3-5-flash
- gemini-2.5-pro (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-2.5-pro
- Gemini-3.7-Flash (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-2.5-Pro (ctx: 1048576, free: yes) - https://aistudio.google.com
- SiliconFlow-/-InternLM2.5-7B-Chat (ctx: 1048576, free: yes) - https://freellmapi.co/model/siliconflow_internlm_internlm2_5-7b-chat
- Gemini 2.0 Flash Thinking Experimental (ctx: 1048576, free: yes) - https://aistudio.google.com
- gemini-2.5-flash (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-2.5-flash
- Gemini-3.1-Flash-Lite (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-Flash-Latest (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-2.0-Flash-Lite (ctx: 1048576, free: yes) - https://aistudio.google.com
- gemini-3-flash-preview (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-3-flash-preview
- Gemini-3.1-Pro-Preview (ctx: 1048576, free: yes) - https://aistudio.google.com
- gemini-3.1-pro-preview (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-3.1-pro-preview
- Gemini-3.7-Flash-Thinking (ctx: 1048576, free: yes) - https://aistudio.google.com
- Ox-Alpha (ctx: 1048576, free: yes) - https://openrouter.ai/stealth/ox-alpha
- gemini-3.1-flash-lite (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-3.1-flash-lite
- gemini-3.5-flash (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-3.5-flash
- Gemini-3.6-Flash (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-3-6-flash
- gemini-3.5-flash-lite (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-3.5-flash-lite
- gemini-3.6-flash (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-3.6-flash
- GLM-4-Long (ctx: 1048576, free: yes) - https://freellmapi.co/model/glm-4-long
- Gemini-3.1-Flash-Lite-Thinking (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-3-1-flash-lite-thinking
- Gemini-3.5-Flash-Lite (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-2.5-Flash (ctx: 1048576, free: yes) - https://aistudio.google.com
- InternLM2.5-7B-1M-Context (ctx: 1048576, free: yes) - https://freellmapi.co/model/internlm_internlm2_5-7b-chat-1m
- Gemini-2.0-Flash-Lite (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-2.0-flash-lite
- lyria-3-clip-preview (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/lyria-3-clip-preview
- Gemini-3.5-Flash (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-3-Flash-Preview-Thinking (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-3-flash-preview-thinking
- Gemini-3.1-Pro-Preview-Custom-Tools (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini 2.5 Flash (Free) (ctx: 1048576, free: yes) - https://openrouter.ai
- Gemini-2.0-Flash (ctx: 1048576, free: yes) - https://aistudio.google.com
- lyria-3-pro-preview (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/lyria-3-pro-preview
- Google Gemini 2.0 Flash Lite (Free) (ctx: 1048576, free: yes) - https://openrouter.ai
- LearnLM-1.5-Pro-Experimental (ctx: 1048576, free: yes) - https://freellmapi.co/model/learnlm-1.5-pro-experimental
- InternLM-2.5-20B-Chat (ctx: 1048576, free: yes) - https://freellmapi.co/model/internlm-2.5-20b-chat
- Gemini-3.1-Flash-Image (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-3-1-flash-image
- Gemini 2.0 Flash-Lite (Preview) (ctx: 1048576, free: yes) - https://aistudio.google.com
- Google:-Lyria-3-Clip-Preview (ctx: 1048576, free: yes) - https://openrouter.ai/google/lyria-3-clip-preview
- MiniMax:-MiniMax-M3 (ctx: 1048576, free: yes) - https://openrouter.ai/minimax/minimax-m3:free
- Google:-Lyria-3-Pro-Preview (ctx: 1048576, free: yes) - https://openrouter.ai/google/lyria-3-pro-preview
- gemini-2.5-flash-lite (ctx: 1048576, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-2.5-flash-lite
- InternLM-2.5-7B-Chat (ctx: 1048576, free: yes) - https://freellmapi.co/model/internlm-2.5-7b-chat
- Gemini-2.0-Flash-Experimental (ctx: 1048576, free: yes) - https://openrouter.ai/google/gemini-2.0-flash-exp:free
- Gemini-Pro-Latest (ctx: 1048576, free: yes) - https://aistudio.google.com
- OpenRouter-/-Gemini-2.0-Flash-Exp:free (ctx: 1048576, free: yes) - https://freellmapi.co/model/google_gemini-2.0-flash-exp:free
- Gemini-1.5-Flash (ctx: 1048576, free: yes) - https://freellmapi.co/model/gemini-1.5-flash
- Gemini-3.6-Flash (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini 3 Flash Preview (ctx: 1048576, free: yes) - https://aistudio.google.com
- Gemini-2.5-Flash-Free (ctx: 1048576, free: yes) - https://www.orcarouter.ai/
- InternLM2.5-20B-1M-Context (ctx: 1048576, free: yes) - https://freellmapi.co/model/internlm_internlm2_5-20b-chat-1m
- captain-eris_violet-v0.420-12b (ctx: 1024000, free: yes) - https://featherless.ai/models/Nitral-AI/Captain-Eris_Violet-V0.420-12B
- nekomix-12b (ctx: 1024000, free: yes) - https://featherless.ai/models/Moraliane/NekoMix-12B
- NVIDIA:-Nemotron-3-Ultra (ctx: 1000000, free: yes) - https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b:free
- Nemotron-3.5-Lightning-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/nemotron-3.5-lightning-free
- NVIDIA:-Nemotron-3.5-Lightning (ctx: 1000000, free: yes) - https://openrouter.ai/nvidia/nemotron-3.5-lightning:free
- Gemini-3.6-Flash-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/gemini-3.6-flash-free
- nemotron-3-ultra-550b-a55b (ctx: 1000000, free: yes) - https://build.nvidia.com/nvidia/nemotron-3-ultra-550b-a55b
- Coding-MiniMax-M2.5-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/coding-minimax-m2.5-free
- Gemini-3.5-Flash-Lite-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/gemini-3.5-flash-lite-free
- Coding-MiniMax-M3-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/coding-minimax-m3-free
- Coding-MiniMax-M2.1-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/coding-minimax-m2.1-free
- Nemotron-3.5-Lightning-Free (ctx: 1000000, free: yes) - https://opencode.ai/
- Coding-MiniMax-M2.7-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/coding-minimax-m2.7-free
- Gemini-3.7-Flash-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/gemini-3.7-flash-free
- Gemini-3.1-Flash-Image-Preview-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/gemini-3.1-flash-image-preview-free
- Coding-MiniMax-M2-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/coding-minimax-m2-free
- Gemini-3-Flash-Preview-Free (ctx: 1000000, free: yes) - https://aihubmix.com/model/gemini-3-flash-preview-free
- Dots-Studio:-Dots3-Note-Preview (ctx: 512000, free: yes) - https://openrouter.ai/dots-studio/dots-3-note-preview:free
- kimi-k2-thinking (ctx: 262144, free: yes) - https://novita.ai/models/moonshotai/Kimi-K2-Thinking
- qwen3-coder-30b-a3b-instruct (ctx: 262144, free: yes) - https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct
- glm-4.7-flash (ctx: 262144, free: yes) - https://novita.ai/models/zai-org/GLM-4.7-Flash
- qwen3.5-35b-a3b (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3.5-35B-A3B
- qwen3.5-397b-a17b (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3.5-397B-A17B
- laguna-s-2.1 (ctx: 262144, free: yes) - https://featherless.ai/models/poolside/Laguna-S-2.1
- glm-4.7-flash (ctx: 262144, free: yes) - https://featherless.ai/models/zai-org/GLM-4.7-Flash
- glm-4.5-air (ctx: 262144, free: yes) - https://huggingface.co/zai-org/GLM-4.5-Air
- kimi-k2-instruct (ctx: 262144, free: yes) - https://novita.ai/models/moonshotai/Kimi-K2-Instruct
- glm-4.5-air (ctx: 262144, free: yes) - https://novita.ai/models/zai-org/GLM-4.5-Air
- gemma-4-26b-a4b-it (ctx: 262144, free: yes) - https://novita.ai/models/google/gemma-4-26B-A4B-it
- qwen3-vl-235b-a22b-thinking (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3-VL-235B-A22B-Thinking
- qwen3-vl-235b-a22b-instruct (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3-VL-235B-A22B-Instruct
- nemotron-3-super-120b-a12b (ctx: 262144, free: yes) - https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b
- Kimi-For-Coding-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/kimi-for-coding-free
- Step-1-256k (ctx: 262144, free: yes) - https://freellmapi.co/model/step-1-256k
- gemma-4-26b-a4b-it (ctx: 262144, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemma-4-26b-a4b-it
- glm-4.7-flash (ctx: 262144, free: yes) - https://huggingface.co/zai-org/GLM-4.7-Flash
- qwen3-vl-8b-instruct (ctx: 262144, free: yes) - https://featherless.ai/models/Qwen/Qwen3-VL-8B-Instruct
- qwen3-coder-30b-a3b-instruct (ctx: 262144, free: yes) - https://featherless.ai/models/Qwen/Qwen3-Coder-30B-A3B-Instruct
- qwen3-coder-next (ctx: 262144, free: yes) - https://featherless.ai/models/Qwen/Qwen3-Coder-Next
- qwen3-30b-a3b-instruct-2507 (ctx: 262144, free: yes) - https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507
- gemma-3-1b-it (ctx: 262144, free: yes) - https://huggingface.co/google/gemma-3-1b-it
- qwen3-30b-a3b-instruct-2507 (ctx: 262144, free: yes) - https://featherless.ai/models/Qwen/Qwen3-30B-A3B-Instruct-2507
- qwen3.5-9b (ctx: 262144, free: yes) - https://featherless.ai/models/Qwen/Qwen3.5-9B
- gemma-4-26b-a4b-it (ctx: 262144, free: yes) - https://featherless.ai/models/google/gemma-4-26B-A4B-it
- qwen3.6-35b-a3b (ctx: 262144, free: yes) - https://featherless.ai/models/Qwen/Qwen3.6-35B-A3B
- gemma-4-31b-it (ctx: 262144, free: yes) - https://featherless.ai/models/google/gemma-4-31B-it
- Coding-GLM-4.7-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/coding-glm-4.7-free
- nex-n2-mini (ctx: 262144, free: yes) - https://featherless.ai/models/nex-agi/Nex-N2-mini
- qwen3.6-27b (ctx: 262144, free: yes) - https://featherless.ai/models/Qwen/Qwen3.6-27B
- qwen3-vl-30b-a3b-instruct (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3-VL-30B-A3B-Instruct
- Xiaomi-MiMo-V2-Pro-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/xiaomi-mimo-v2-pro-free
- Ling-3.0-Flash-Fin (ctx: 262144, free: yes) - https://openrouter.ai/inclusionai/ling-3.0-flash-fin:free
- qwen3.5-27b (ctx: 262144, free: yes) - https://featherless.ai/models/Qwen/Qwen3.5-27B
- ling-3.0-tiny (ctx: 262144, free: yes) - https://openrouter.ai/inclusionai/ling-3.0-tiny:free
- qwen3-next-80b-a3b-instruct (ctx: 262144, free: yes) - https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct
- qwen3-coder-next (ctx: 262144, free: yes) - https://huggingface.co/Qwen/Qwen3-Coder-Next
- Nemotron-3-Ultra-Free (ctx: 262144, free: yes) - https://opencode.ai/
- shadow-siren-26b-a4b (ctx: 262144, free: yes) - https://featherless.ai/models/Vortex5/Shadow-Siren-26B-A4B
- Coding-Kimi-K3-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/coding-kimi-k3-free
- Coding-GLM-5.1-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/coding-glm-5.1-free
- gemma-3-1b-it (ctx: 262144, free: yes) - https://featherless.ai/models/google/gemma-3-1b-it
- K2.6-Code-Preview-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/k2.6-code-preview-free
- Nemotron-3-Super-120B-A12B-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/nemotron-3-super-120b-a12b-free
- Thinking-Machines:-Inkling (ctx: 262144, free: yes) - https://openrouter.ai/thinkingmachines/inkling:free
- Thinking-Machines:-Inkling-Small (ctx: 262144, free: yes) - https://openrouter.ai/thinkingmachines/inkling-small:free
- Poolside:-Laguna-XS-2.1 (ctx: 262144, free: yes) - https://openrouter.ai/poolside/laguna-xs-2.1:free
- Xiaomi-MiMo-V2.5-Pro-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/xiaomi-mimo-v2.5-pro-free
- Coding-GLM-5-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/coding-glm-5-free
- Xiaomi-MiMo-V2-Omni-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/xiaomi-mimo-v2-omni-free
- Codestral-2508 (ctx: 262144, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Gemma-4-31B-IT (ctx: 262144, free: yes) - https://aistudio.google.com
- Google:-Gemma-4-31B (ctx: 262144, free: yes) - https://openrouter.ai/google/gemma-4-31b-it:free
- Nemotron-3-Ultra-550B-A55B-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/nemotron-3-ultra-550b-a55b-free
- Gemma-4-26B-A4B-IT (ctx: 262144, free: yes) - https://aistudio.google.com
- Google:-Gemma-4-26B-A4B (ctx: 262144, free: yes) - https://openrouter.ai/google/gemma-4-26b-a4b-it:free
- Coding-GLM-5-Turbo-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/coding-glm-5-turbo-free
- Poolside:-Laguna-S-2.1 (ctx: 262144, free: yes) - https://openrouter.ai/poolside/laguna-s-2.1:free
- Coding-GLM-4.6-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/coding-glm-4.6-free
- GPT-5.5-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/gpt-5.5-free
- ling-2.6-1t (ctx: 262144, free: yes) - https://novita.ai/models/inclusionAI/Ling-2.6-1T
- qwen3-next-80b-a3b-instruct (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3-Next-80B-A3B-Instruct
- qwen3-235b-a22b-thinking-2507 (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3-235B-A22B-Thinking-2507
- Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Free (ctx: 262144, free: yes) - https://aihubmix.com/model/nemotron-3-nano-omni-30b-a3b-reasoning-free
- qwen3-coder-next (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3-Coder-Next
- Kimi-K3 (ctx: 262144, free: yes) - https://freellmapi.co/model/kimi-k3
- Kimi-K2.7-Code (ctx: 262144, free: yes) - https://freellmapi.co/model/kimi-k2-7-code
- qwen3.5-122b-a10b (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3.5-122B-A10B
- NVIDIA:-Nemotron-3-Super (ctx: 262144, free: yes) - https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b:free
- gemma-4-31b-it (ctx: 262144, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemma-4-31b-it
- qwen3.5-397b-a17b (ctx: 262144, free: yes) - https://featherless.ai/models/Qwen/Qwen3.5-397B-A17B
- Kimi-K2.6 (ctx: 262144, free: yes) - https://freellmapi.co/model/kimi-k2-6
- gemma-4-31b-it (ctx: 262144, free: yes) - https://novita.ai/models/google/gemma-4-31B-it
- qwen3.5-27b (ctx: 262144, free: yes) - https://novita.ai/models/Qwen/Qwen3.5-27B
- AI21-/-Jamba-1.5-Large-256k (ctx: 256000, free: yes) - https://freellmapi.co/model/ai21labs_Jamba-1.5-Large
- north-mini-code (ctx: 256000, free: yes) - https://docs.cohere.com/docs/command-a
- AI21-/-Jamba-1.5-Mini-256k (ctx: 256000, free: yes) - https://freellmapi.co/model/ai21labs_Jamba-1.5-Mini
- NVIDIA:-Nemotron-3-Nano-30B-A3B (ctx: 256000, free: yes) - https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b:free
- Jamba-1.5-Mini (ctx: 256000, free: yes) - https://freellmapi.co/model/jamba-1.5-mini
- Mistral-/-Codestral-Mamba-7B (ctx: 256000, free: yes) - https://freellmapi.co/model/mistralai_Codestral-Mamba-7B-v0.1
- Jamba-1.5-Large (ctx: 256000, free: yes) - https://freellmapi.co/model/jamba-1.5-large
- Cohere:-North-Mini-Code (ctx: 256000, free: yes) - https://openrouter.ai/cohere/north-mini-code:free
- GitHub-Models-/-AI21-Jamba-1.5-Large (ctx: 256000, free: yes) - https://freellmapi.co/model/gh_AI21-Jamba-1.5-Large
- NVIDIA:-Nemotron-3-Nano-Omni (ctx: 256000, free: yes) - https://openrouter.ai/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
- GitHub-Models-/-AI21-Jamba-1.5-Mini (ctx: 256000, free: yes) - https://freellmapi.co/model/gh_AI21-Jamba-1.5-Mini
- Codestral-Mamba (ctx: 256000, free: yes) - https://freellmapi.co/model/codestral-mamba
- GitHub-Models-/-Codestral-2501 (ctx: 256000, free: yes) - https://freellmapi.co/model/gh_Codestral-2501
- AI21-/-Jamba-v0.1-Hybrid (ctx: 256000, free: yes) - https://freellmapi.co/model/ai21labs_Jamba-v0.1
- Codestral-2501 (ctx: 256000, free: yes) - https://freellmapi.co/model/codestral-2501
- nemotron-3-nano-omni-30b-a3b-reasoning (ctx: 256000, free: yes) - https://build.nvidia.com/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
- nemotron-3-nano-30b-a3b (ctx: 256000, free: yes) - https://build.nvidia.com/nvidia/nemotron-3-nano-30b-a3b
- MiniMax-ABAB6.5t-Chat (ctx: 245760, free: yes) - https://freellmapi.co/model/minimax-abab6.5t-chat
- MiniMax-ABAB6.5g-Chat (ctx: 245760, free: yes) - https://freellmapi.co/model/minimax-abab6.5g-chat
- MiniMax-ABAB6.5s-Chat (ctx: 245760, free: yes) - https://freellmapi.co/model/minimax-abab6.5s-chat
- MiniMax-M2.7 (ctx: 200000, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- o1 (ctx: 200000, free: yes) - https://freellmapi.co/model/o1
- Claude-3.5-Sonnet-20241022 (ctx: 200000, free: yes) - https://freellmapi.co/model/claude-3-5-sonnet-20241022
- Claude-3.5-Haiku-20241022 (ctx: 200000, free: yes) - https://freellmapi.co/model/claude-3-5-haiku-20241022
- MiniMax-M2 (ctx: 200000, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Free-Models-Router (ctx: 200000, free: yes) - https://openrouter.ai/openrouter/free
- o3 (ctx: 200000, free: yes) - https://freellmapi.co/model/o3
- MiniMax-M2.5-HighSpeed (ctx: 200000, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Claude-3-Haiku-20240307 (ctx: 200000, free: yes) - https://freellmapi.co/model/claude-3-haiku-20240307
- o3-Mini (ctx: 200000, free: yes) - https://freellmapi.co/model/o3-mini
- MiniMax-M2.7-HighSpeed (ctx: 200000, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- MiniMax-M2.1 (ctx: 200000, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- o3-Mini (ctx: 200000, free: yes) - https://github.com/marketplace/models
- MiniMax-M2.5 (ctx: 200000, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- GitHub-Models-/-OpenAI-o1 (ctx: 200000, free: yes) - https://freellmapi.co/model/gh_o1
- MiniMax-M2.1-HighSpeed (ctx: 200000, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- 01.AI-/-Yi-Medium-200k (ctx: 200000, free: yes) - https://freellmapi.co/model/01-ai_yi-medium
- Claude-3-Opus-20240229 (ctx: 200000, free: yes) - https://freellmapi.co/model/claude-3-opus-20240229
- Claude-3-Sonnet-20240229 (ctx: 200000, free: yes) - https://freellmapi.co/model/claude-3-sonnet-20240229
- MiniMax:-MiniMax-M2.7 (ctx: 196608, free: yes) - https://openrouter.ai/minimax/minimax-m2.7:free
- deepseek-v3.2 (ctx: 163840, free: yes) - https://featherless.ai/models/deepseek-ai/DeepSeek-V3.2
- Llama-4-Vision-Preview (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-4-vision-preview
- DeepSeek-R1-Zero (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-r1-zero
- DeepSeek-V3-0324 (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-v3-0324
- qwen2.5-1.5b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-1.5B-Instruct
- phi-4 (ctx: 131072, free: yes) - https://featherless.ai/models/microsoft/phi-4
- llama-3.3-70b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/meta-llama/Llama-3.3-70B-Instruct
- ornith-1.0-9b (ctx: 131072, free: yes) - https://featherless.ai/models/ornith-ai/Ornith-1.0-9B
- meta-llama-3-8b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/meta-llama/Meta-Llama-3-8B-Instruct
- qwen2.5-0.5b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-0.5B-Instruct
- qwen3-4b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen3-4B
- qwen2.5-7b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-7B-Instruct
- minimax-m2.7 (ctx: 131072, free: yes) - https://featherless.ai/models/MiniMaxAI/MiniMax-M2.7
- gpt-oss-20b (ctx: 131072, free: yes) - https://huggingface.co/openai/gpt-oss-20b
- gpt-oss-safeguard-20b (ctx: 131072, free: yes) - https://console.groq.com/playground?model=openai/gpt-oss-safeguard-20b
- c4ai-command-r7b-12-2024 (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- c4ai-command-r7b-arabic-02-2025 (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- c4ai-command-a-03-2025 (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- tiny-aya-global (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- gpt-oss-120b (ctx: 131072, free: yes) - https://huggingface.co/openai/gpt-oss-120b
- tiny-aya-water (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- tiny-aya-earth (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- deepseek-v4-pro (ctx: 131072, free: yes) - https://app.fireworks.ai/models/fireworks/deepseek-v4-pro
- deepseek-r1-distill-qwen-32b (ctx: 131072, free: yes) - https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
- nvidia-nemotron-3-nano-30b-a3b-bf16 (ctx: 131072, free: yes) - https://featherless.ai/models/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- llama-3.1-8b (ctx: 131072, free: yes) - https://huggingface.co/meta-llama/Llama-3.1-8B
- qwen3-1.7b-base (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen3-1.7B-Base
- minimax-m2.7 (ctx: 131072, free: yes) - https://huggingface.co/MiniMaxAI/MiniMax-M2.7
- qwen2.5-coder-7b (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-Coder-7B
- qwen3-vl-32b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen3-VL-32B-Instruct
- nvidia-nemotron-3-nano-30b-a3b-bf16 (ctx: 131072, free: yes) - https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- deepseek-r1-distill-llama-70b-abliterated (ctx: 131072, free: yes) - https://featherless.ai/models/nguyenthilaitrieulong/DeepSeek-R1-Distill-Llama-70B-abliterated
- huatuogpt-o1-8b (ctx: 131072, free: yes) - https://featherless.ai/models/FreedomIntelligence/HuatuoGPT-o1-8B
- llama3.1-typhoon2-deepseek-r1-70b-preview (ctx: 131072, free: yes) - https://featherless.ai/models/typhoon-ai/llama3.1-typhoon2-deepseek-r1-70b-preview
- GLM-4-Plus (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-4-plus
- GLM-4-FlashX (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-4-flashx
- llama-3.1-70b (ctx: 131072, free: yes) - https://featherless.ai/models/meta-llama/Llama-3.1-70B
- qwen2.5-72b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-72B-Instruct
- gpt-oss-120b (ctx: 131072, free: yes) - https://app.fireworks.ai/models/fireworks/gpt-oss-120b
- DeepSeek R1 Distill Llama 70B (Free) (ctx: 131072, free: yes) - https://openrouter.ai
- gpt-oss-20b (ctx: 131072, free: yes) - https://app.fireworks.ai/models/fireworks/gpt-oss-20b
- qwen3-14b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen3-14B
- nvidia-nemotron-3-super-120b-a12b-bf16 (ctx: 131072, free: yes) - https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
- llama-nemotron-embed-vl-1b-v2 (ctx: 131072, free: yes) - https://openrouter.ai/nvidia/llama-nemotron-embed-vl-1b-v2:free
- deepseek-r1-0528-qwen3-8b (ctx: 131072, free: yes) - https://featherless.ai/models/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
- ternary-bonsai-27b-gguf (ctx: 131072, free: yes) - https://huggingface.co/prism-ml/Ternary-Bonsai-27B-gguf
- deepseek-r1-distill-qwen-7b-abliterated-v2 (ctx: 131072, free: yes) - https://featherless.ai/models/huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2
- GLM-4.7 (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-4-7
- llama-3.3-70b-instruct (ctx: 131072, free: yes) - https://novita.ai/models/meta-llama/Llama-3.3-70B-Instruct
- otel-llm-27b-it (ctx: 131072, free: yes) - https://huggingface.co/farbodtavakkoli/OTel-LLM-27B-IT
- qwen3-4b-instruct-2507 (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen3-4B-Instruct-2507
- mistral-7b-instruct-v0.2 (ctx: 131072, free: yes) - https://featherless.ai/models/mistralai/Mistral-7B-Instruct-v0.2
- fanar-1-9b-instruct (ctx: 131072, free: yes) - https://huggingface.co/QCRI/Fanar-1-9B-Instruct
- GPT 5.6 Luna (Experimental/Synthetic) (ctx: 131072, free: yes) - https://xkiro.com
- deepseek-r1-distill-qwen-1.5b (ctx: 131072, free: yes) - https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
- Llama-3.3-70B-Instruct (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended
- gemma-3-1b-it-glm-4.7-flash-heretic-uncensored-thinking (ctx: 131072, free: yes) - https://featherless.ai/models/DavidAU/Gemma-3-1B-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking
- command-a-translate-08-2025 (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- Qwen-2.5-Coder-32B (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended
- qwen2.5-coder-7b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-Coder-7B-Instruct
- qwen2.5-coder-32b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-Coder-32B-Instruct
- gliese-qwen3.5-9b-abliterated-caption (ctx: 131072, free: yes) - https://featherless.ai/models/prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption
- qwen3-1.7b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen3-1.7B
- meta-llama-3-8b (ctx: 131072, free: yes) - https://featherless.ai/models/meta-llama/Meta-Llama-3-8B
- llama-3.1-8b (ctx: 131072, free: yes) - https://featherless.ai/models/meta-llama/Llama-3.1-8B
- CF-Meta-Llama-3.3-70B-Instruct (ctx: 131072, free: yes) - https://developers.cloudflare.com/workers-ai/models
- Llama-3.3-70B-Instruct-Free (ctx: 131072, free: yes) - https://www.orcarouter.ai/
- glm-5.2 (ctx: 131072, free: yes) - https://featherless.ai/models/zai-org/GLM-5.2
- qwen2.5-14b-instruct (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-14B-Instruct
- llama-3.3-70b-instruct (ctx: 131072, free: yes) - https://console.groq.com/playground?model=meta-llama/Llama-3.3-70B-Instruct
- c4ai-command-r-08-2024 (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- deepseek-r1-distill-llama-70b (ctx: 131072, free: yes) - https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- qwen3-30b-a3b (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen3-30B-A3B
- deepseek-v4-flash-0731 (ctx: 131072, free: yes) - https://app.fireworks.ai/models/fireworks/deepseek-v4-flash-0731
- minimax-m2.7 (ctx: 131072, free: yes) - https://app.fireworks.ai/models/fireworks/minimax-m2.7
- qwen2.5-coder-14b-instruct (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct
- privacy-filter-nemotron-v2 (ctx: 131072, free: yes) - https://huggingface.co/OpenMed/privacy-filter-nemotron-v2
- glm-5.2 (ctx: 131072, free: yes) - https://huggingface.co/zai-org/GLM-5.2
- phi-4-mini-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/microsoft/Phi-4-mini-instruct
- qwen3-14b (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen3-14B
- deepseek-v4-flash (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
- qwen2.5-7b (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-7B
- gpt-oss-20b (ctx: 131072, free: yes) - https://featherless.ai/models/openai/gpt-oss-20b
- gpt-oss-120b (ctx: 131072, free: yes) - https://featherless.ai/models/openai/gpt-oss-120b
- gemma-4-31b-it-nvfp4 (ctx: 131072, free: yes) - https://huggingface.co/nvidia/Gemma-4-31B-IT-NVFP4
- ornith-1.0-9b (ctx: 131072, free: yes) - https://huggingface.co/ornith-ai/Ornith-1.0-9B
- qwen3-0.6b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen3-0.6B
- qwen3-8b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen3-8B
- glm-5.2-fp8 (ctx: 131072, free: yes) - https://huggingface.co/zai-org/GLM-5.2-FP8
- meta-llama-3-8b (ctx: 131072, free: yes) - https://huggingface.co/meta-llama/Meta-Llama-3-8B
- gemma-4-31b-it-nvfp4 (ctx: 131072, free: yes) - https://featherless.ai/models/nvidia/Gemma-4-31B-IT-NVFP4
- gpt-oss-safeguard-20b (ctx: 131072, free: yes) - https://featherless.ai/models/openai/gpt-oss-safeguard-20b
- qwen2.5-7b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-7B
- qwen3-235b-a22b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen3-235B-A22B
- qwen2.5-coder-7b-instruct (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct
- meta-llama-3-8b-instruct (ctx: 131072, free: yes) - https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
- qwen2.5-32b-instruct (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-32B-Instruct
- tiny-aya-fire (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- glm-5.2 (ctx: 131072, free: yes) - https://app.fireworks.ai/models/fireworks/glm-5.2
- deepseek-v4-flash (ctx: 131072, free: yes) - https://app.fireworks.ai/models/fireworks/deepseek-v4-flash
- hermes-3-llama-3.1-8b (ctx: 131072, free: yes) - https://featherless.ai/models/NousResearch/Hermes-3-Llama-3.1-8B
- qwen3-0.6b-base (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen3-0.6B-Base
- Kimi-K2 (ctx: 131072, free: yes) - https://freellmapi.co/model/kimi-k2
- hermes-3-llama-3.1-70b (ctx: 131072, free: yes) - https://featherless.ai/models/NousResearch/Hermes-3-Llama-3.1-70B
- qwen2.5-32b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-32B
- Kimi-K1.5 (ctx: 131072, free: yes) - https://freellmapi.co/model/kimi-k1.5
- qwen2.5-1.5b-vibethinker-heretic-uncensored-abliterated (ctx: 131072, free: yes) - https://featherless.ai/models/DavidAU/Qwen2.5-1.5B-VibeThinker-heretic-uncensored-abliterated
- Devstral-2412 (ctx: 131072, free: yes) - https://freellmapi.co/model/devstral-2412
- selene-1-mini-llama-3.1-8b (ctx: 131072, free: yes) - https://featherless.ai/models/AtlaAI/Selene-1-Mini-Llama-3.1-8B
- qwen2.5-math-1.5b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-Math-1.5B
- deepseek-r1-distill-qwen-14b (ctx: 131072, free: yes) - https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- deepseek-v4-pro (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-V4-Pro
- deepseek-r1 (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-R1
- DeepSeek-R1-Distill-Llama-70B (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended
- DeepSeek-V4-Pro-0813 (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&q=deepseek%2Fdeepseek-v4-pro-0813
- Grok-4.20-Reasoning (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-4-20-reasoning
- GLM-5.2 (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-5-2
- deephermes-3-llama-3-8b-preview (ctx: 131072, free: yes) - https://featherless.ai/models/NousResearch/DeepHermes-3-Llama-3-8B-Preview
- wayfarer-large-70b-llama-3.3 (ctx: 131072, free: yes) - https://featherless.ai/models/LatitudeGames/Wayfarer-Large-70B-Llama-3.3
- l3.3-prikol-70b-extra (ctx: 131072, free: yes) - https://featherless.ai/models/Nohobby/L3.3-Prikol-70B-EXTRA
- deepseek-r1-distill-llama-70b (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- deepseek-v3.2 (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-V3.2
- minimax-m2.7 (ctx: 131072, free: yes) - https://novita.ai/models/MiniMaxAI/MiniMax-M2.7
- qwen2.5-72b-instruct (ctx: 131072, free: yes) - https://novita.ai/models/Qwen/Qwen2.5-72B-Instruct
- qwen3-235b-a22b (ctx: 131072, free: yes) - https://novita.ai/models/Qwen/Qwen3-235B-A22B
- DeepSeek-V4-Flash (ctx: 131072, free: yes) - https://docs.b.ai/llmservice/models/deepseek-v4-flash/
- qwen2.5-3b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-3B-Instruct
- deepseek-r1-0528 (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-R1-0528
- HY3 (ctx: 131072, free: yes) - https://docs.b.ai/llmservice/models/hy3/
- Qwen3-Coder-480B (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-coder-480b
- DeepSeek-V4-Pro (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-v4-pro
- deepseek-v4-flash-0731 (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-V4-Flash-0731
- glm-5.2 (ctx: 131072, free: yes) - https://novita.ai/models/zai-org/GLM-5.2
- gpt-oss-20b (ctx: 131072, free: yes) - https://novita.ai/models/openai/gpt-oss-20b
- gpt-oss-120b (ctx: 131072, free: yes) - https://novita.ai/models/openai/gpt-oss-120b
- minimax-m2.5 (ctx: 131072, free: yes) - https://novita.ai/models/MiniMaxAI/MiniMax-M2.5
- deepseek-v3 (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-V3
- deepseek-v3-0324 (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-V3-0324
- Grok-4.5 (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-4-5
- GLM-5.3-Flash (ctx: 131072, free: yes) - https://docs.b.ai/llmservice/models/glm-5-3-flash/
- Grok-4.3 (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-4-3
- Qwen3-Coder-Next (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-coder-next
- Nemotron-3-Ultra-550B (ctx: 131072, free: yes) - https://freellmapi.co/model/nemotron-3-ultra-550b
- Functionary-Medium-v3.2 (ctx: 131072, free: yes) - https://freellmapi.co/model/meetkai_functionary-medium-v3.2
- Qwen3.5-397B-A17B (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-5-397b-a17b
- Qwen3.5-397B (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-5-397b
- Gemini-2.5-Computer-Use-Preview-10-2025 (ctx: 131072, free: yes) - https://aistudio.google.com
- deepseek-v3.1 (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-V3.1
- Llama 3.2 3B Instruct (ctx: 131072, free: yes) - https://huggingface.co
- Laguna-S-2.1-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/laguna-s-2.1-free
- Gemma-4-26B-A4B-IT-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/gemma-4-26b-a4b-it-free
- Qwen-3.6-Plus-Preview-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/qwen3.6-plus-preview-free
- Gemini-Robotics-ER-2-Preview (ctx: 131072, free: yes) - https://aistudio.google.com
- DeepSeek-V3 (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-v3
- DeepSeek-V4-Flash-Free (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-v4-flash-free
- Grok-4.20-Non-Reasoning (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-4-20-non-reasoning
- GLM-5.2-Venice (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-5-2-venice
- DeepSeek-V3.2 (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-v3-2
- deepseek-v4-pro (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
- Llama-3.3-70B-Instruct (ctx: 131072, free: yes) - https://openrouter.ai/meta-llama/llama-3.3-70b-instruct:free
- Qwen-2.5-72B-Instruct (ctx: 131072, free: yes) - https://openrouter.ai/qwen/qwen-2.5-72b-instruct:free
- GPT-OSS-120B (ctx: 131072, free: yes) - https://freellmapi.co/model/gpt-oss-120b
- Grok-4.1-Fast-Non-Reasoning (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-4-1-fast-non-reasoning
- Gemini-Omni-Flash-Preview (ctx: 131072, free: yes) - https://aistudio.google.com
- Gemini-3.1-Flash-Live-Preview (ctx: 131072, free: yes) - https://aistudio.google.com
- Qwen-2.5-Coder-32B-Instruct (ctx: 131072, free: yes) - https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct:free
- Nemotron-3-Nano-30B-A3B-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/nemotron-3-nano-30b-a3b-free
- DeepSeek-R1 (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-r1
- Hermes-3-Llama-3.1-405B (ctx: 131072, free: yes) - https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b:free
- Compound (ctx: 131072, free: yes) - https://freellmapi.co/model/compound
- qwen2.5-1.5b (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-1.5B
- Gemini-Robotics-ER-2-Streaming-Preview (ctx: 131072, free: yes) - https://aistudio.google.com
- Grok-4 (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-4
- NVIDIA-Llama-3.1-Nemotron-70B (ctx: 131072, free: yes) - https://openrouter.ai/nvidia/llama-3.1-nemotron-70b-instruct:free
- DeepSeek-V4-Pro-Free (ctx: 131072, free: yes) - https://www.orcarouter.ai/models/deepseek/deepseek-v4-pro-free
- LFM-2.5-2.6B-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/lfm-2.5-2.6b-free
- GLM-4-FlashX (ctx: 131072, free: yes) - https://bigmodel.cn/dev/api#glm-4-flash
- deepseek-r1-0528-qwen3-8b (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
- Gemini-Robotics-ER-1.6-Preview (ctx: 131072, free: yes) - https://aistudio.google.com
- Gemini-3.5-Transcribe-Live (ctx: 131072, free: yes) - https://aistudio.google.com
- Qwen3-235B-A22B-Thinking-2507 (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-235b-a22b-thinking-2507
- Grok-4.1-Fast-Reasoning (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-4-1-fast-reasoning
- Grok-4-Fast-Reasoning (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-4-fast-reasoning
- GLM-5.1 (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-5-1
- Llama-3.2-11B-Vision-Instruct (ctx: 131072, free: yes) - https://openrouter.ai/meta-llama/llama-3.2-11b-vision-instruct:free
- GLM-5-Venice (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-5-venice
- Llama-3.1-8B-Instant (ctx: 131072, free: yes) - https://console.groq.com/docs/models
- Nano-Banana-Pro (ctx: 131072, free: yes) - https://aistudio.google.com
- Mistral-Large-2512 (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Ministral-8B (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- MiMO-v2.5-Pro (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- DeepSeek-V4-Flash (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.8-Max (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.6-Max-Preview (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.6-35B-A3B (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.5-Omni-Plus (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3-Coder-Plus (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3-Omni-Flash (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Grok-4-Fast-Non-Reasoning (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-4-fast-non-reasoning
- Gemini-2.5-Flash-Native-Audio-Preview-12-2025 (ctx: 131072, free: yes) - https://aistudio.google.com
- GPT-Image-2-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/gpt-image-2-free
- Qwen3-VL-235B (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-vl-235b
- GLM-5.1-Venice (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-5-1-venice
- Qwen3-30B-A3B-FP8 (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-30b-a3b-fp8
- GLM-4.5 (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-4-5
- DeepSeek-V2.5 (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-v2.5
- Mistral-Large-2512 (ctx: 131072, free: yes) - https://freellmapi.co/model/mistral-large-2512
- DeepSeek-V4-Flash-Venice (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-v4-flash-venice
- Mistral-Medium-3.5 (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Devstral-Medium (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Ministral-3B (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- MiMO-v2.5 (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- DeepSeek-V3.2 (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.7-Max (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.6-Plus (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.5-Plus (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.5-Flash (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3-Max (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen-Plus-2025-07-28 (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3-235B-A22B-Instruct-2507 (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-235b-a22b-instruct-2507
- Nemotron-3-Ultra-Free (ctx: 131072, free: yes) - https://freellmapi.co/model/nemotron-3-ultra-free
- Nemotron-3-Ultra (ctx: 131072, free: yes) - https://freellmapi.co/model/nemotron-3-ultra
- DeepSeek-V2-Chat (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-v2-chat
- DeepSeek-R1-Distill-Llama-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-r1-distill-llama-70b
- GPT-OSS-20B-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/gpt-oss-20b-free
- Qwen3.8-27B-Free (ctx: 131072, free: yes) - https://www.orcarouter.ai/models/qwen/qwen3.8-27b-free
- Ling-3.0-Tiny (ctx: 131072, free: yes) - https://zenmux.ai/inclusionai/ling-3.0-tiny
- DeepSeek-R1-Distill-Qwen-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-r1-distill-qwen-32b
- DeepSeek-R1-Distill-Qwen-14B (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-r1-distill-qwen-14b
- deepseek-v3.2 (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-V3.2
- Qwen3-VL-235B-A22B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-vl-235b-a22b-instruct
- Qwen3-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen3-32b
- Mistral-Small-2603 (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Ministral-14B (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- DeepSeek-V4-Pro (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- DeepSeek-Chat-V3.1 (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.7-Plus (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.6-27B (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.5-397B-A17B (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3.5-Omni-Flash (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Qwen3-VL-Plus (ctx: 131072, free: yes) - https://xkiro.com/dashboard/models?sort=recommended&price=free
- Nano-Banana-Pro (ctx: 131072, free: yes) - https://aistudio.google.com
- Functionary-Small-v3.2 (ctx: 131072, free: yes) - https://freellmapi.co/model/meetkai_functionary-small-v3.2
- AllenAI-/-Tulu-3-8B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/allenai_tulu-3-8b
- DeepSeek-R1-Distill-Llama-8B (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-r1-distill-llama-8b
- GLM-5.3-Free (ctx: 131072, free: yes) - https://zenmux.ai/z-ai/glm-5.3-free
- GLM-4.7-Flash-Free (ctx: 131072, free: yes) - https://zenmux.ai/z-ai/glm-4.7-flash-free
- RWKV-6-World-7B-RNN (ctx: 131072, free: yes) - https://freellmapi.co/model/BlinkDL_rwkv-6-world-7b
- Llama-3.1-8B-Instruct (ctx: 131072, free: yes) - https://openrouter.ai/meta-llama/llama-3.1-8b-instruct:free
- DeepSeek-R1-Distill-Qwen-7B (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-r1-distill-qwen-7b
- Agnes-2.5-Flash (ctx: 131072, free: yes) - https://zenmux.ai/sapiens-ai/agnes-2.5-flash
- GLM-4.6v-Flash-Free (ctx: 131072, free: yes) - https://zenmux.ai/z-ai/glm-4.6v-flash-free
- DeepSeek-R1-Distill-Qwen-1.5B (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-r1-distill-qwen-1.5b
- Xiaomi-MiMo-V2.5-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/xiaomi-mimo-v2.5-free
- GPT-5.4 (ctx: 131072, free: yes) - https://freellmapi.co/model/gpt-5-4
- Ox-Alpha-Free (ctx: 131072, free: yes) - https://opencode.ai/
- Muse-Spark-1.2-Free (ctx: 131072, free: yes) - https://opencode.ai/
- Hy3-Free (ctx: 131072, free: yes) - https://opencode.ai/
- Dots3-Note-Prev (ctx: 131072, free: yes) - https://zenmux.ai/dots-studio/dots3-note-prev
- Agnes-2.0-Flash (ctx: 131072, free: yes) - https://zenmux.ai/sapiens-ai/agnes-2.0-flash
- Ox-Alpha (ctx: 131072, free: yes) - https://aihubmix.com/model/ox-alpha
- North-Mini-Code-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/north-mini-code-free
- deepseek-v3 (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-V3
- deepseek-v3-0324 (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-V3-0324
- AllenAI-/-Tulu-3-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/allenai_tulu-3-70b
- deepseek-r1-distill-qwen-14b (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
- Dots-3-Note-Preview-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/dots-3-note-preview-free
- Nemotron-3.5-Content-Safety-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/nemotron-3.5-content-safety-free
- Gemma-4-31B-IT-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/gemma-4-31b-it-free
- qwen3-4b-base (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen3-4B-Base
- GLM-4-Flash (ctx: 131072, free: yes) - https://bigmodel.cn/dev/api#glm-4-flash
- minimax-m2.5 (ctx: 131072, free: yes) - https://huggingface.co/MiniMaxAI/MiniMax-M2.5
- qwen3-0.6b-base (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen3-0.6B-Base
- qwen2.5-coder-1.5b-instruct (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct
- Meta-Llama-3.3-70B-Instruct (ctx: 131072, free: yes) - https://build.nvidia.com/meta/llama-3_3-70b-instruct
- llama-3.2-3b-instruct (ctx: 131072, free: yes) - https://developers.cloudflare.com/workers-ai/models/llama-3.2-3b-instruct/
- llama-3.2-1b-instruct (ctx: 131072, free: yes) - https://developers.cloudflare.com/workers-ai/models/llama-3.2-1b-instruct/
- mistral-small-3.1-24b-instruct (ctx: 131072, free: yes) - https://developers.cloudflare.com/workers-ai/models/mistral-small-3.1-24b-instruct/
- OpenAI: gpt-oss-20b (free) (ctx: 131072, free: yes) - https://openrouter.ai/openai/gpt-oss-20b:free
- Laguna-S-2.1-Free (ctx: 131072, free: yes) - https://opencode.ai/
- gemma-3-12b-it (ctx: 131072, free: yes) - https://developers.cloudflare.com/workers-ai/models/gemma-3-12b-it/
- qwen2.5-72b-instruct (ctx: 131072, free: yes) - https://deepinfra.com/Qwen/Qwen2.5-72B-Instruct/api
- mistral-small-24b-instruct-2501 (ctx: 131072, free: yes) - https://deepinfra.com/mistralai/Mistral-Small-24B-Instruct-2501/api
- deepseek-v3 (ctx: 131072, free: yes) - https://deepinfra.com/deepseek-ai/DeepSeek-V3/api
- mistral-nemo (ctx: 131072, free: yes) - https://docs.mistral.ai/models/
- qwen3-235b-a22b (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen3-235B-A22B
- MiMo-V2.5-Free (ctx: 131072, free: yes) - https://opencode.ai/
- mistral-7b-instruct-v0.1 (ctx: 131072, free: yes) - https://featherless.ai/models/mistralai/Mistral-7B-Instruct-v0.1
- DeepSeek-V4-Flash-Free (ctx: 131072, free: yes) - https://opencode.ai/
- Nemotron-Nano-12B-V2-VL-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/nemotron-nano-12b-v2-vl-free
- Laguna-XS-2.1-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/laguna-xs-2.1-free
- llama-3.2-3b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/meta-llama/Llama-3.2-3B-Instruct
- huihui-qwen3-vl-4b-instruct-abliterated (ctx: 131072, free: yes) - https://featherless.ai/models/huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated
- hermes-3-llama-3.1-8b (ctx: 131072, free: yes) - https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B
- nvidia-nemotron-3-ultra-550b-a55b-bf16 (ctx: 131072, free: yes) - https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
- RWKV-6-World-14B-RNN (ctx: 131072, free: yes) - https://freellmapi.co/model/BlinkDL_rwkv-6-world-14b
- NVIDIA-Llama-3.1-Nemotron-70B-NIM (ctx: 131072, free: yes) - https://build.nvidia.com/nvidia/llama-3_1-nemotron-70b-instruct
- qwen3guard-gen-4b (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen3Guard-Gen-4B
- glm-5.1-fp8 (ctx: 131072, free: yes) - https://huggingface.co/zai-org/GLM-5.1-FP8
- typhoon2.5-qwen3-4b (ctx: 131072, free: yes) - https://huggingface.co/typhoon-ai/typhoon2.5-qwen3-4b
- olmo-3-7b-instruct (ctx: 131072, free: yes) - https://huggingface.co/allenai/Olmo-3-7B-Instruct
- mimo-v2.5 (ctx: 131072, free: yes) - https://huggingface.co/XiaomiMiMo/MiMo-V2.5
- qwen2.5-14b-instruct (ctx: 131072, free: yes) - https://huggingface.co/unsloth/Qwen2.5-14B-Instruct
- qwen3-8b-base (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen3-8B-Base
- qwen2.5-math-1.5b (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-Math-1.5B
- apertus-8b-instruct-2509 (ctx: 131072, free: yes) - https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509
- deepseek-v4-flash (ctx: 131072, free: yes) - https://novita.ai/models/deepseek-ai/DeepSeek-V4-Flash
- meta-llama-3.1-8b-instruct (ctx: 131072, free: yes) - https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct
- llama-3.1-8b-instruct (ctx: 131072, free: yes) - https://novita.ai/models/meta-llama/Llama-3.1-8B-Instruct
- saiga_llama3_8b (ctx: 131072, free: yes) - https://huggingface.co/IlyaGusev/saiga_llama3_8b
- t-lite-it-2.1 (ctx: 131072, free: yes) - https://huggingface.co/t-tech/T-lite-it-2.1
- Ling-3.0-Tiny-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/ling-3.0-tiny-free
- Gemini-2.5-Flash-Native-Audio-Latest (ctx: 131072, free: yes) - https://aistudio.google.com
- qwen3-4b-thinking-2507 (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507
- deepseek-r1-distill-llama-70b (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- deepseek-r1-distill-llama-8b (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B
- deepseek-r1-distill-qwen-7b (ctx: 131072, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
- meta-llama-3-8b (ctx: 131072, free: yes) - https://huggingface.co/NousResearch/Meta-Llama-3-8B
- qwen2.5-3b (ctx: 131072, free: yes) - https://huggingface.co/Qwen/Qwen2.5-3B
- gpt-oss-20b (ctx: 131072, free: yes) - https://console.groq.com/playground?model=openai/gpt-oss-20b
- DeepSeek-V2.5-Snapshot-1210 (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-ai_DeepSeek-V2.5-1210
- MiMo-V2-Flash-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/mimo-v2-flash-free
- gpt-oss-120b (ctx: 131072, free: yes) - https://console.groq.com/playground?model=openai/gpt-oss-120b
- aya-expanse-32b (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- deepseek-v4-flash (ctx: 131072, free: yes) - https://featherless.ai/models/deepseek-ai/DeepSeek-V4-Flash
- command-a-reasoning-08-2025 (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- Grok-2 (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-2
- Grok-2-Mini (ctx: 131072, free: yes) - https://freellmapi.co/model/grok-2-mini
- DeepSeek-V4-Flash-Free (ctx: 131072, free: yes) - https://kiraai.vn/models/deepseek-v4-flash-free/
- gemma-4-31b-it-mystery-fine-tune-heretic-uncensored-thinking (ctx: 131072, free: yes) - https://featherless.ai/models/DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking
- DeepSeek-V4-Flash-Free (ctx: 131072, free: yes) - https://www.orcarouter.ai/models/deepseek/deepseek-v4-flash-free
- llama-3.1-nemotron-8b-ultralong-4m-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct
- aya-vision-32b (ctx: 131072, free: yes) - https://docs.cohere.com/docs/command-a
- qwen3.6-27b-heretic2-uncensored-finetune-thinking (ctx: 131072, free: yes) - https://featherless.ai/models/DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking
- qwen3.6-21b-iq-ultra-heretic-uncensored-thinking (ctx: 131072, free: yes) - https://featherless.ai/models/DavidAU/Qwen3.6-21B-IQ-Ultra-Heretic-Uncensored-Thinking
- Qwen-3.8-Flash (ctx: 131072, free: yes) - https://kiraai.vn/models/qwen3.8-flash/
- MiMO-v2.5 (ctx: 131072, free: yes) - https://kiraai.vn/models/mimo-v2.5/
- Gemini-Omni-1.1-Flash (ctx: 131072, free: yes) - https://aistudio.google.com
- Qwen-2.5-72B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-72b-instruct
- qwen2.5-32b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-32B-Instruct
- GLM-5.3-Flash (ctx: 131072, free: yes) - https://kiraai.vn/models/glm-5.3-flash/
- HY3 (ctx: 131072, free: yes) - https://kiraai.vn/models/hy3/
- Qwen-2.5-Coder-32B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-coder-32b-instruct
- Qwen-2.5-Coder-14B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-coder-14b-instruct
- Qwen-2.5-Coder-7B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-coder-7b-instruct
- Qwen-2.5-Coder-1.5B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-coder-1.5b-instruct
- Qwen-2.5-VL-72B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-vl-72b-instruct
- Qwen-2.5-VL-7B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-vl-7b-instruct
- Qwen-2.5-32B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-32b-instruct
- DeepSeek-V4-Flash-Vision-Exp (ctx: 131072, free: yes) - https://kiraai.vn/models/deepseek-v4-flash-vision-exp/
- Qwen-2.5-14B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-14b-instruct
- Qwen-2.5-7B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-7b-instruct
- Ling-3.0-Flash-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/ling-3.0-flash-free
- Nemotron-Nano-9B-V2-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/nemotron-nano-9b-v2-free
- qwen2.5-14b-instruct (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-14B-Instruct
- qwen2.5-coder-7b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-Coder-7B
- GLM-4-9B-Chat (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-4-9b-chat
- CodeGeeX4-All-9B (ctx: 131072, free: yes) - https://freellmapi.co/model/codegeex4-all-9b
- GLM-3-Turbo (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-3-turbo
- Llama-3.1-Nemotron-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.1-nemotron-70b-instruct
- Llama-3.1-Nemotron-51B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.1-nemotron-51b-instruct
- qwen2.5-1.5b (ctx: 131072, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-1.5B
- SambaNova-/-DeepSeek-V3 (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_deepseek-v3
- Llama-3.3-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.3-70b-instruct
- Llama-3.2-90B-Vision-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.2-90b-vision-instruct
- Llama-3.2-11B-Vision-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.2-11b-vision-instruct
- Llama-3.2-3B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.2-3b-instruct
- Llama-3.2-1B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.2-1b-instruct
- Llama-3.1-405B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.1-405b-instruct
- Llama-3.1-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.1-70b-instruct
- Llama-3.1-8B-Instant (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-3.1-8b-instant
- Cerebras-/-Qwen-3-235B (ctx: 131072, free: yes) - https://freellmapi.co/model/cerebras_qwen-3-235b
- SambaNova-/-Llama-3.3-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_llama-3.3-70b-instruct
- SambaNova-/-DeepSeek-R1 (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_deepseek-r1
- SambaNova-/-Llama-3.1-405B (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_llama-3.1-405b-instruct
- SambaNova-/-Qwen2.5-72B (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_qwen2.5-72b-instruct
- SambaNova-/-Llama-3.1-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_llama-3.1-70b-instruct
- SambaNova-/-Qwen2.5-Coder-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_qwen2.5-coder-32b-instruct
- Cloudflare-/-Llama-3.3-70B-FP8-Fast (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_meta_llama-3.3-70b-instruct-fp8-fast
- Cloudflare-/-DeepSeek-R1-Distill-Qwen-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_deepseek-ai_deepseek-r1-distill-qwen-32b
- OpenRouter-/-Auto-Free-Router (ctx: 131072, free: yes) - https://freellmapi.co/model/openrouter_auto:free
- OpenRouter-/-DeepSeek-R1:free (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek_deepseek-r1:free
- OpenRouter-/-DeepSeek-R1-Distill-32B:free (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek_deepseek-r1-distill-qwen-32b:free
- OpenRouter-/-Qwen-2.5-72B:free (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen_qwen-2.5-72b-instruct:free
- SambaNova-/-Llama-3.1-8B (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_llama-3.1-8b-instruct
- SambaNova-/-Llama-3.2-90B-Vision (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_llama-3.2-90b-vision-instruct
- Cloudflare-/-Llama-3.2-3B (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_meta_llama-3.2-3b-instruct
- Cloudflare-/-Qwen2.5-Coder-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_qwen_qwen2.5-coder-32b-instruct
- OpenRouter-/-Free-Models-Aggregator (ctx: 131072, free: yes) - https://freellmapi.co/model/openrouter_free-models-router:free
- OpenRouter-/-DeepSeek-V3:free (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek_deepseek-chat:free
- SambaNova-/-Llama-3.2-11B-Vision (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_llama-3.2-11b-vision-instruct
- Cloudflare-/-Llama-3.2-1B (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_meta_llama-3.2-1b-instruct
- OpenRouter-/-Llama-3.3-70B:free (ctx: 131072, free: yes) - https://freellmapi.co/model/meta-llama_llama-3.3-70b-instruct:free
- OpenRouter-/-DeepSeek-R1-Distill-70B:free (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek_deepseek-r1-distill-llama-70b:free
- Step-1-128k (ctx: 131072, free: yes) - https://freellmapi.co/model/step-1-128k
- SenseChat-5.5 (ctx: 131072, free: yes) - https://freellmapi.co/model/sensechat-5-5
- hermes-4-70b (ctx: 131072, free: yes) - https://featherless.ai/models/NousResearch/Hermes-4-70B
- huihui-qwen3.6-27b-abliterated (ctx: 131072, free: yes) - https://featherless.ai/models/huihui-ai/Huihui-Qwen3.6-27B-abliterated
- lamarck-14b-v0.7 (ctx: 131072, free: yes) - https://featherless.ai/models/sometimesanotion/Lamarck-14B-v0.7
- Hermes-3-Llama-3.1-405B (ctx: 131072, free: yes) - https://freellmapi.co/model/hermes-3-llama-3.1-405b
- Hermes-3-Llama-3.1-8B (ctx: 131072, free: yes) - https://freellmapi.co/model/hermes-3-llama-3.1-8b
- OpenRouter-/-Qwen-2.5-Coder-32B:free (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen_qwen-2.5-coder-32b-instruct:free
- Hermes-3-Llama-3.1-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/hermes-3-llama-3.1-70b
- OpenRouter-/-Hermes-3-405B:free (ctx: 131072, free: yes) - https://freellmapi.co/model/nousresearch_hermes-3-llama-3.1-405b:free
- SiliconFlow-/-DeepSeek-R1 (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_deepseek-ai_DeepSeek-R1
- SiliconFlow-/-DeepSeek-R1-Distill-Qwen-7B (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_deepseek-ai_DeepSeek-R1-Distill-Qwen-7B
- SiliconFlow-/-Qwen2.5-32B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_Qwen_Qwen2.5-32B-Instruct
- SiliconFlow-/-Qwen2.5-Coder-32B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_Qwen_Qwen2.5-Coder-32B-Instruct
- SiliconFlow-/-DeepSeek-R1-Distill-Qwen-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_deepseek-ai_DeepSeek-R1-Distill-Qwen-32B
- SiliconFlow-/-DeepSeek-R1-Distill-Llama-8B (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_deepseek-ai_DeepSeek-R1-Distill-Llama-8B
- SiliconFlow-/-Qwen2.5-14B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_Qwen_Qwen2.5-14B-Instruct
- SiliconFlow-/-Qwen2.5-Coder-7B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_Qwen_Qwen2.5-Coder-7B-Instruct
- GPT-4.1-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/gpt-4.1-free
- SiliconFlow-/-DeepSeek-V3 (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_deepseek-ai_DeepSeek-V3
- SiliconFlow-/-DeepSeek-R1-Distill-Qwen-14B (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_deepseek-ai_DeepSeek-R1-Distill-Qwen-14B
- SiliconFlow-/-Qwen2.5-72B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_Qwen_Qwen2.5-72B-Instruct
- SiliconFlow-/-Qwen2.5-7B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_Qwen_Qwen2.5-7B-Instruct
- SiliconFlow-/-GLM-4-9B-Chat (ctx: 131072, free: yes) - https://freellmapi.co/model/siliconflow_THUDM_glm-4-9b-chat
- HuggingFace-/-Llama-3.3-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_meta-llama_Llama-3.3-70B-Instruct
- HuggingFace-/-Llama-3.2-90B-Vision (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_meta-llama_Llama-3.2-90B-Vision-Instruct
- HuggingFace-/-Qwen2.5-32B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_Qwen_Qwen2.5-32B-Instruct
- HuggingFace-/-Llama-3.2-3B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_meta-llama_Llama-3.2-3B-Instruct
- HuggingFace-/-Llama-3.1-8B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_meta-llama_Llama-3.1-8B-Instruct
- HuggingFace-/-Qwen2.5-Coder-32B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_Qwen_Qwen2.5-Coder-32B-Instruct
- HuggingFace-/-DeepSeek-R1-Distill-Llama-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_deepseek-ai_DeepSeek-R1-Distill-Llama-70B
- GPT-4o-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/gpt-4o-free
- HuggingFace-/-Llama-3.2-1B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_meta-llama_Llama-3.2-1B-Instruct
- HuggingFace-/-Llama-3.1-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_meta-llama_Llama-3.1-70B-Instruct
- HuggingFace-/-Qwen2.5-Coder-7B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_Qwen_Qwen2.5-Coder-7B-Instruct
- HuggingFace-/-DeepSeek-R1-Distill-Qwen-14B (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_deepseek-ai_DeepSeek-R1-Distill-Qwen-14B
- HuggingFace-/-Nemotron-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_nvidia_Llama-3.1-Nemotron-70B-Instruct-HF
- Cloudflare-/-Llama-3.2-11B-Vision (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_@cf_meta_llama-3.2-11b-vision-instruct
- HuggingFace-/-Llama-3.2-11B-Vision (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_meta-llama_Llama-3.2-11B-Vision-Instruct
- HuggingFace-/-Qwen2.5-72B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_Qwen_Qwen2.5-72B-Instruct
- HuggingFace-/-DeepSeek-R1-Distill-Qwen-7B (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_deepseek-ai_DeepSeek-R1-Distill-Qwen-7B
- HuggingFace-/-Hermes-3-Llama-3.1-8B (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_NousResearch_Hermes-3-Llama-3.1-8B
- GPT-4.1-Nano-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/gpt-4.1-nano-free
- Cloudflare-/-Llama-3.3-70B-Instruct-Fast (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_@cf_meta_llama-3.3-70b-instruct-fp8-fast
- Cloudflare-/-Llama-3.1-8B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_@cf_meta_llama-3.1-8b-instruct
- SambaNova-/-Llama-3.1-405B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_Meta-Llama-3.1-405B-Instruct
- SambaNova-/-DeepSeek-R1-Full (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_DeepSeek-R1
- HuggingFace-/-DeepSeek-R1-Distill-Qwen-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/hf_deepseek-ai_DeepSeek-R1-Distill-Qwen-32B
- Cloudflare-/-Llama-3.2-3B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_@cf_meta_llama-3.2-3b-instruct
- Cloudflare-/-Llama-3.1-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_@cf_meta_llama-3.1-70b-instruct
- SambaNova-/-Llama-3.1-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_Meta-Llama-3.1-70B-Instruct
- SambaNova-/-DeepSeek-V3-Full (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_DeepSeek-V3
- SambaNova-/-Llama-3.2-11B-Vision (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_Llama-3.2-11B-Vision-Instruct
- Cerebras-/-Llama-3.1-70B-Fast (ctx: 131072, free: yes) - https://freellmapi.co/model/cerebras_llama3.1-70b
- DeepInfra-/-Llama-3.3-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/deepinfra_meta-llama_Llama-3.3-70B-Instruct
- Cloudflare-/-Llama-3.2-1B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_@cf_meta_llama-3.2-1b-instruct
- Cloudflare-/-DeepSeek-R1-Distill-Qwen-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/cf_@cf_deepseek-ai_deepseek-r1-distill-qwen-32b
- GPT-4.1-Mini-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/gpt-4.1-mini-free
- SambaNova-/-Llama-3.1-8B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_Meta-Llama-3.1-8B-Instruct
- SambaNova-/-Qwen2.5-72B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_Qwen2.5-72B-Instruct
- SambaNova-/-Llama-3.2-90B-Vision (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_Llama-3.2-90B-Vision-Instruct
- Cerebras-/-DeepSeek-R1-Distill-70B-2000tps (ctx: 131072, free: yes) - https://freellmapi.co/model/cerebras_deepseek-r1-distill-llama-70b
- DeepInfra-/-DeepSeek-R1-Distill-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/deepinfra_deepseek-ai_DeepSeek-R1-Distill-Llama-70B
- Together-/-DeepSeek-R1-Distill-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/together_deepseek-ai_DeepSeek-R1-Distill-Llama-70B
- Novita-/-DeepSeek-R1-Serverless (ctx: 131072, free: yes) - https://freellmapi.co/model/novita_deepseek-ai_deepseek-r1
- Hyperbolic-/-DeepSeek-R1-ZeroCost (ctx: 131072, free: yes) - https://freellmapi.co/model/hyperbolic_deepseek-ai_DeepSeek-R1
- Hyperbolic-/-Llama-3.2-11B-Vision (ctx: 131072, free: yes) - https://freellmapi.co/model/hyperbolic_meta-llama_Llama-3.2-11B-Vision-Instruct
- SambaNova-/-Llama-3.3-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_Meta-Llama-3.3-70B-Instruct
- SambaNova-/-DeepSeek-R1-Distill-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_DeepSeek-R1-Distill-Llama-70B
- SambaNova-/-Qwen2.5-Coder-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/sambanova_Qwen2.5-Coder-32B-Instruct
- Cerebras-/-Llama-3.3-70B-Fast (ctx: 131072, free: yes) - https://freellmapi.co/model/cerebras_llama3.3-70b
- DeepInfra-/-DeepSeek-V3-Fast (ctx: 131072, free: yes) - https://freellmapi.co/model/deepinfra_deepseek-ai_DeepSeek-V3
- DeepInfra-/-Llama-3.2-11B-Vision (ctx: 131072, free: yes) - https://freellmapi.co/model/deepinfra_meta-llama_Llama-3.2-11B-Vision-Instruct
- Together-/-DeepSeek-V3 (ctx: 131072, free: yes) - https://freellmapi.co/model/together_deepseek-ai_DeepSeek-V3
- Novita-/-DeepSeek-V3-Serverless (ctx: 131072, free: yes) - https://freellmapi.co/model/novita_deepseek-ai_deepseek-v3
- Hyperbolic-/-DeepSeek-V3-ZeroCost (ctx: 131072, free: yes) - https://freellmapi.co/model/hyperbolic_deepseek-ai_DeepSeek-V3
- Cerebras-/-Llama-3.1-8B-Fast (ctx: 131072, free: yes) - https://freellmapi.co/model/cerebras_llama3.1-8b
- DeepInfra-/-Qwen2.5-Coder-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/deepinfra_Qwen_Qwen2.5-Coder-32B-Instruct
- Together-/-Qwen2.5-72B-Turbo (ctx: 131072, free: yes) - https://freellmapi.co/model/together_Qwen_Qwen2.5-72B-Instruct-Turbo
- Novita-/-Llama-3.3-70B-Instruct (ctx: 131072, free: yes) - https://freellmapi.co/model/novita_meta-llama_llama-3.3-70b-instruct
- Hyperbolic-/-Llama-3.3-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/hyperbolic_meta-llama_Llama-3.3-70B-Instruct
- Legal-Llama-3.1-70B (ctx: 131072, free: yes) - https://freellmapi.co/model/law-ai_legal-llama-3.1-70b
- Together-/-Llama-3.3-70B-Turbo (ctx: 131072, free: yes) - https://freellmapi.co/model/together_meta-llama_Llama-3.3-70B-Instruct-Turbo
- Together-/-Llama-3.2-3B-Turbo (ctx: 131072, free: yes) - https://freellmapi.co/model/together_meta-llama_Llama-3.2-3B-Instruct-Turbo
- Novita-/-Qwen-2.5-Coder-32B (ctx: 131072, free: yes) - https://freellmapi.co/model/novita_qwen_qwen-2.5-coder-32b-instruct
- Legal-Llama-3.1-8B (ctx: 131072, free: yes) - https://freellmapi.co/model/law-ai_legal-llama-3.1-8b
- GLM-4.7-Flash-Free (ctx: 131072, free: yes) - https://aihubmix.com/model/glm-4.7-flash-free
- Qwen-3.8-Flash (ctx: 131072, free: yes) - https://docs.b.ai/llmservice/models/qwen3-8-flash/
- MiMO-v2.5 (ctx: 131072, free: yes) - https://docs.b.ai/llmservice/models/mimo-v2.5/
- Gemini-2.5-Flash-Native-Audio-Preview-09-2025 (ctx: 131072, free: yes) - https://aistudio.google.com
- Dolphin-2.9.4-Llama3.1-8B (ctx: 131072, free: yes) - https://freellmapi.co/model/cognitivecomputations_dolphin-2.9.4-llama3.1-8b
- GLM-4.7-Flash (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-4-7-flash
- Llama-4-Preview (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-4-preview
- Qwen-2.5-Plus (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-plus
- Kimi-Chat-128k (ctx: 131072, free: yes) - https://freellmapi.co/model/kimi-chat-128k
- Llama-4-Scout (ctx: 131072, free: yes) - https://freellmapi.co/model/llama-4-scout
- Qwen-2.5-Turbo (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-turbo
- Qwen-2.5-Max (ctx: 131072, free: yes) - https://freellmapi.co/model/qwen-2.5-max
- GLM-4-Flash (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-4-flash
- Moonshot-v1-128k (ctx: 131072, free: yes) - https://freellmapi.co/model/moonshot-v1-128k
- GLM-Zero-Preview (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-zero-preview
- DeepSeek-V4-Flash (ctx: 131072, free: yes) - https://freellmapi.co/model/deepseek-v4-flash
- Moonshot-v1-Auto (ctx: 131072, free: yes) - https://freellmapi.co/model/moonshot-v1-auto
- GLM-4-Air (ctx: 131072, free: yes) - https://freellmapi.co/model/glm-4-air
- Qwen2.5-72B-Base (ctx: 131072, free: yes) - https://freellmapi.co/model/Qwen_Qwen2.5-72B-Base
- Qwen2.5-32B-Base (ctx: 131072, free: yes) - https://freellmapi.co/model/Qwen_Qwen2.5-32B-Base
- Qwen2.5-14B-Base (ctx: 131072, free: yes) - https://freellmapi.co/model/Qwen_Qwen2.5-14B-Base
- Qwen2.5-7B-Base (ctx: 131072, free: yes) - https://freellmapi.co/model/Qwen_Qwen2.5-7B-Base
- Mistral-Large-2 (ctx: 128000, free: yes) - https://github.com/marketplace/models
- nemotron-nano-9b-v2 (ctx: 128000, free: yes) - https://build.nvidia.com/nvidia/nemotron-nano-9b-v2
- HuggingFace-/-Phi-4-Mini-3.8B (ctx: 128000, free: yes) - https://freellmapi.co/model/hf_microsoft_Phi-4-mini
- GitHub-Models-/-GPT-4o-Mini-Azure (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_gpt-4o-mini
- GPT-5.3-Codex (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-5-3-codex
- OpenRouter-/-Mistral-Nemo-12B:free (ctx: 128000, free: yes) - https://freellmapi.co/model/mistralai_mistral-nemo:free
- Phi-3.5-MoE-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/phi-3.5-moe-instruct
- Granite-3.0-8B-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/granite-3.0-8b-instruct
- Granite-3.0-8B-Code-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/granite-3.0-8b-code-instruct
- Phi-3.5-Vision-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/phi-3.5-vision-instruct
- Phi-3.5-Mini-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/phi-3.5-mini-instruct
- Z.ai:-GLM-5.2 (ctx: 128000, free: yes) - https://openrouter.ai/z-ai/glm-5.2:free
- Phi-3-Medium-128k-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/phi-3-medium-128k-instruct
- Ministral-8B-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/ministral-8b-instruct
- Ministral-3B-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/ministral-3b-instruct
- IBM-/-Granite-8B-Code-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/ibm-granite_granite-8b-code-instruct
- HuggingFace-/-Mistral-Nemo-Instruct-2407 (ctx: 128000, free: yes) - https://freellmapi.co/model/hf_mistralai_Mistral-Nemo-Instruct-2407
- HuggingFace-/-Phi-3.5-Vision-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/hf_microsoft_Phi-3.5-vision-instruct
- Cerebras-/-Llama-3.1-8B (ctx: 128000, free: yes) - https://freellmapi.co/model/cerebras_llama-3.1-8b
- Groq-/-Llama-3.2-11B-Vision (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_llama-3.2-11b-vision-preview
- Mistral-Large-2411 (ctx: 128000, free: yes) - https://freellmapi.co/model/mistral-large-2411
- SenseTime-/-SenseChat-5.5 (ctx: 128000, free: yes) - https://freellmapi.co/model/SenseTime_SenseChat-5.5
- Groq-/-Llama-3.1-70B-Versatile (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_llama-3.1-70b-versatile
- nemotron-nano-12b-v2-vl (ctx: 128000, free: yes) - https://build.nvidia.com/nvidia/nemotron-nano-12b-v2-vl
- Command-A (ctx: 128000, free: yes) - https://freellmapi.co/model/command-a
- Groq-/-Qwen-2.5-Coder-32B-LPU (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_qwen-2.5-coder-32b
- qwen2.5-vl-72b-instruct (ctx: 128000, free: yes) - https://featherless.ai/models/Qwen/Qwen2.5-VL-72B-Instruct
- Pixtral 12B Vision (Mistral Free Tier) (ctx: 128000, free: yes) - https://mistral.ai/news/pixtral-12b/
- Granite-3.0-2B-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/granite-3.0-2b-instruct
- Granite-3.0-2B-Code-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/granite-3.0-2b-code-instruct
- Phi-4-Mini (ctx: 128000, free: yes) - https://freellmapi.co/model/phi-4-mini
- Llama 3.2 11B Vision Instruct (ctx: 128000, free: yes) - https://huggingface.co/inference-api
- Cerebras-/-Llama-3.1-70B (ctx: 128000, free: yes) - https://freellmapi.co/model/cerebras_llama-3.1-70b
- Qwen3-Coder-30B-A3B-Instruct-GGUF (ctx: 128000, free: yes) - https://huggingface.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
- DeepSeek-Coder-V2-Lite-16B (ctx: 128000, free: yes) - https://freellmapi.co/model/deepseek-ai_DeepSeek-Coder-V2-Lite-Instruct
- Mistral-/-Ministral-3B-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/mistralai_Ministral-3B-Instruct-2410
- Phi-3-Small-128k-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/phi-3-small-128k-instruct
- tiny-random-LlamaForCausalLM (ctx: 128000, free: yes) - https://huggingface.co/hmellor/tiny-random-LlamaForCausalLM
- Qwen3.6-35B-A3B-NVFP4 (ctx: 128000, free: yes) - https://huggingface.co/nvidia/Qwen3.6-35B-A3B-NVFP4
- IBM-/-Granite-3B-Code-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/ibm-granite_granite-3b-code-instruct
- IBM-/-Granite-3.1-2B-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/ibm-granite_granite-3.1-2b-instruct
- Groq-/-Llama-3.2-1B-Preview (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_llama-3.2-1b-preview
- DeepSeek-R1-Distill-Qwen-32B (ctx: 128000, free: yes) - https://console.groq.com/docs/models
- Phi-3-Mini-128k-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/phi-3-mini-128k-instruct
- Mistral-Medium-3.5 (ctx: 128000, free: yes) - https://freellmapi.co/model/mistral-medium-3.5
- Meta Llama 3.3 70B Instruct (ctx: 128000, free: yes) - https://huggingface.co
- IBM-/-Granite-3.1-8B-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/ibm-granite_granite-3.1-8b-instruct
- Mistral-/-Pixtral-Large-124B-Vision (ctx: 128000, free: yes) - https://freellmapi.co/model/mistralai_Pixtral-Large-Instruct-2411
- Groq-/-Llama-3.2-90B-Vision (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_llama-3.2-90b-vision-preview
- GPT-4o-Realtime-Preview (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4o-realtime-preview
- GitHub-Models-/-Phi-3.5-MoE (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_Phi-3.5-MoE-instruct
- Phi 3 Mini 4K Instruct (ctx: 128000, free: yes) - https://huggingface.co
- Qwen3-32B (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen3-32B
- GitHub-Models-/-Phi-3.5-Vision (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_Phi-3.5-vision-instruct
- GitHub-Models-/-Command-R (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_Cohere-command-r-08-2024
- Groq-/-Llama-3.3-70B-Versatile (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_llama-3.3-70b-versatile
- Qwen3-8B (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen3-8B
- nemotron-3.5-content-safety (ctx: 128000, free: yes) - https://build.nvidia.com/nvidia/nemotron-3.5-content-safety
- DeepSeek-R1 (ctx: 128000, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-R1
- GitHub-Models-/-GPT-4o-Azure (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_gpt-4o
- GitHub-Models-/-Phi-3.5-Mini (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_Phi-3.5-mini-instruct
- Cerebras-/-Llama-3.3-70B (ctx: 128000, free: yes) - https://freellmapi.co/model/cerebras_llama-3.3-70b
- Mistral-Nemo-12B-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/mistral-nemo-12b-instruct
- GitHub-Models-/-Mistral-Nemo-12B (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_Mistral-Nemo
- Groq-/-DeepSeek-R1-Distill-70B (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_deepseek-r1-distill-llama-70b
- Mistral-Small-2409 (ctx: 128000, free: yes) - https://freellmapi.co/model/mistral-small-2409
- Qwen2.5-3B-Instruct (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen2.5-3B-Instruct
- Groq-/-Llama-3.2-3B-Preview (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_llama-3.2-3b-preview
- GitHub-Models-/-OpenAI-o1-Mini (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_o1-mini
- Groq-/-DeepSeek-R1-Distill-32B (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_deepseek-r1-distill-qwen-32b
- Llama 3.3 70B Instruct (Cloudflare Edge) (ctx: 128000, free: yes) - https://developers.cloudflare.com/workers-ai/models/
- Llama-3.2-11B-Vision-Preview (ctx: 128000, free: yes) - https://console.groq.com/docs/models
- GPT-5-Search-API (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-5-search-api
- GPT-5 (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-5
- GLM-4 9B Chat (ctx: 128000, free: yes) - https://siliconflow.cn
- GPT-5.2 (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-5-2
- nvidia-nemotron-3-ultra-550b-a55b-nvfp4 (ctx: 128000, free: yes) - https://app.fireworks.ai/models/fireworks/nvidia-nemotron-3-ultra-550b-a55b-nvfp4
- Llama-3.2-1B-Instruct (ctx: 128000, free: yes) - https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct
- Mistral-Large-2407 (ctx: 128000, free: yes) - https://freellmapi.co/model/mistral-large-2407
- Llama-3.3-70B-Versatile (ctx: 128000, free: yes) - https://console.groq.com/docs/models
- NVIDIA:-Nemotron-Nano-9B-V2 (ctx: 128000, free: yes) - https://openrouter.ai/nvidia/nemotron-nano-9b-v2:free
- Groq-/-Llama-3.1-8B-Instant (ctx: 128000, free: yes) - https://freellmapi.co/model/groq_llama-3.1-8b-instant
- StepFun-/-Step-1-Flash (ctx: 128000, free: yes) - https://freellmapi.co/model/stepfun_step-1-flash
- Reka-Core-20240904 (ctx: 128000, free: yes) - https://freellmapi.co/model/reka-core-20240904
- Reka-Flash-20240904 (ctx: 128000, free: yes) - https://freellmapi.co/model/reka-flash-20240904
- Qwen2.5-1.5B-Instruct (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct
- tiny-Qwen2ForCausalLM-2.5 (ctx: 128000, free: yes) - https://huggingface.co/trl-internal-testing/tiny-Qwen2ForCausalLM-2.5
- Mistral-/-Pixtral-12B-Vision (ctx: 128000, free: yes) - https://freellmapi.co/model/mistralai_Pixtral-12B-2409
- DeepSeek-V4-Flash-0731 (ctx: 128000, free: yes) - https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731
- Qwen3-4B (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen3-4B
- GPT-4o-Mini-Realtime-Preview (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4o-mini-realtime-preview
- Reka-Edge-20240904 (ctx: 128000, free: yes) - https://freellmapi.co/model/reka-edge-20240904
- Qwen3-0.6B (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen3-0.6B
- o1-Mini (ctx: 128000, free: yes) - https://freellmapi.co/model/o1-mini
- DeepSeek-Coder-V2-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/deepseek-coder-v2-instruct
- GPT-4o-Mini (ctx: 128000, free: yes) - https://github.com/marketplace/models
- Command-R (ctx: 128000, free: yes) - https://cohere.com/models/command-r
- Qwen2.5-7B-Instruct (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen2.5-7B-Instruct
- Llama-3.2-90B-Vision-Preview (ctx: 128000, free: yes) - https://console.groq.com/docs/models
- Qwen2.5-7B-Instruct-AWQ (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-AWQ
- Qwen2.5-0.5B-Instruct (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct
- NVIDIA:-Nemotron-Nano-12B-2-VL (ctx: 128000, free: yes) - https://openrouter.ai/nvidia/nemotron-nano-12b-v2-vl:free
- GPT-5.4-Nano (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-5-4-nano
- IBM-/-Granite-34B-Code-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/ibm-granite_granite-34b-code-instruct
- Mistral-/-Ministral-8B-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/mistralai_Ministral-8B-Instruct-2410
- o1-Preview (ctx: 128000, free: yes) - https://freellmapi.co/model/o1-preview
- DeepSeek-R1-Distill-Llama-70B (ctx: 128000, free: yes) - https://console.groq.com/docs/models
- Meta-Llama-3.3-70B-Instruct (ctx: 128000, free: yes) - https://cloud.sambanova.ai
- 01.AI-/-Yi-Coder-9B-Chat (ctx: 128000, free: yes) - https://freellmapi.co/model/01-ai_Yi-Coder-9B-Chat
- Qwen3-4B-Instruct-2507 (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507
- HuggingFace-/-Phi-3.5-Mini-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/hf_microsoft_Phi-3.5-mini-instruct
- ChatGPT-4o-Latest (ctx: 128000, free: yes) - https://freellmapi.co/model/chatgpt-4o-latest
- GPT-4o (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4o
- GPT-5-Nano (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-5-nano
- GPT-4o-2024-11-20 (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4o-2024-11-20
- GPT-4o-2024-08-06 (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4o-2024-08-06
- GitHub-Models-/-Mistral-Large-2411 (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_Mistral-Large-2411
- GPT-5.4-Mini (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-5-4-mini
- Llama 3.3 70B Instruct (Cloudflare Edge) (ctx: 128000, free: yes) - https://developers.cloudflare.com/workers-ai/models/
- o4-Mini (ctx: 128000, free: yes) - https://freellmapi.co/model/o4-mini
- GPT-5-Mini (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-5-mini
- Llama 3.3 70B Instruct (ctx: 128000, free: yes) - https://siliconflow.cn
- GLM 4 9B Chat (ctx: 128000, free: yes) - https://siliconflow.cn
- 01.AI-/-Yi-Coder-1.5B-Chat (ctx: 128000, free: yes) - https://freellmapi.co/model/01-ai_Yi-Coder-1.5B-Chat
- GitHub-Models-/-Command-R-Plus (ctx: 128000, free: yes) - https://freellmapi.co/model/gh_Cohere-command-r-plus-08-2024
- Phi-3-Medium-128k-Instruct (ctx: 128000, free: yes) - https://openrouter.ai/microsoft/phi-3-medium-128k-instruct:free
- GPT-4o-Mini (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4o-mini
- GPT-4o-Mini-2024-07-18 (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4o-mini-2024-07-18
- GPT-4-Turbo (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4-turbo
- Command-R-Plus-08-2024 (ctx: 128000, free: yes) - https://freellmapi.co/model/command-r-plus-08-2024
- GPT-4-0125-Preview (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4-0125-preview
- Command-R-Plus (ctx: 128000, free: yes) - https://freellmapi.co/model/command-r-plus
- Reka-Core (ctx: 128000, free: yes) - https://freellmapi.co/model/reka-core
- GPT-4-1106-Preview (ctx: 128000, free: yes) - https://freellmapi.co/model/gpt-4-1106-preview
- Llama-3.3-70B (ctx: 128000, free: yes) - https://inference.cerebras.ai
- Command-R-08-2024 (ctx: 128000, free: yes) - https://freellmapi.co/model/command-r-08-2024
- Qwen3-1.7B (ctx: 128000, free: yes) - https://huggingface.co/Qwen/Qwen3-1.7B
- IBM-/-Granite-20B-Code-Instruct (ctx: 128000, free: yes) - https://freellmapi.co/model/ibm-granite_granite-20b-code-instruct
- Llama-3.3-70B-Instruct (ctx: 128000, free: yes) - https://github.com/marketplace/models
- Reka-Flash (ctx: 128000, free: yes) - https://freellmapi.co/model/reka-flash
- Llama-3.3-70B-Versatile (ctx: 128000, free: yes) - https://freellmapi.co/model/llama-3.3-70b-versatile
- GPT-4o (ctx: 128000, free: yes) - https://github.com/marketplace/models
- Reka-Edge (ctx: 128000, free: yes) - https://freellmapi.co/model/reka-edge
- Llama-3.1-8B-Instruct (ctx: 128000, free: yes) - https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct
- Command-R (ctx: 128000, free: yes) - https://freellmapi.co/model/command-r
- Pixtral-Large-2411 (ctx: 128000, free: yes) - https://freellmapi.co/model/pixtral-large-2411
- NVIDIA:-Nemotron-3.5-Content-Safety (ctx: 128000, free: yes) - https://openrouter.ai/nvidia/nemotron-3.5-content-safety:free
- Qwen-2.5-Coder-32B (ctx: 128000, free: yes) - https://console.groq.com/docs/models
- Cloudflare-/-Mistral-Nemo-12B (ctx: 128000, free: yes) - https://freellmapi.co/model/cf_@cf_mistral_mistral-nemo-12b-instruct
- DeepSeek-V2-236B-Base (ctx: 128000, free: yes) - https://freellmapi.co/model/deepseek-ai_DeepSeek-V2-Base
- Pixtral-12B (ctx: 128000, free: yes) - https://freellmapi.co/model/pixtral-12b
- Dolphin-2.9.3-Mistral-Nemo (ctx: 128000, free: yes) - https://freellmapi.co/model/cognitivecomputations_dolphin-2.9.3-mistral-nemo-12b
- Gemini-3.5-Transcribe (ctx: 98304, free: yes) - https://aistudio.google.com
- DeepSeek-V3 (ctx: 65536, free: yes) - https://cloud.infini-ai.com/platform/ai/genstudio
- Mixtral-8x22B-Instruct (ctx: 65536, free: yes) - https://freellmapi.co/model/mixtral-8x22b-instruct
- WizardLM-2-8x22B (ctx: 65536, free: yes) - https://freellmapi.co/model/wizardlm-2-8x22b
- Kira-Mini-1.0 (ctx: 65536, free: yes) - https://kiraai.vn/models/kira-mini-1.0/
- Jamba-Instruct (ctx: 65536, free: yes) - https://freellmapi.co/model/jamba-instruct
- Upstage-/-Solar-Pro-Preview (ctx: 65536, free: yes) - https://freellmapi.co/model/upstage_solar-pro-preview-instruct
- Mixtral 8x22B Instruct (ctx: 65536, free: yes) - https://build.nvidia.com
- Devstral-Small (ctx: 65536, free: yes) - https://freellmapi.co/model/devstral-small
- Nano-Banana-2 (ctx: 65536, free: yes) - https://aistudio.google.com
- Nano-Banana-2-Lite (ctx: 65536, free: yes) - https://aistudio.google.com
- Nano-Banana-2 (ctx: 65536, free: yes) - https://aistudio.google.com
- LiquidAI:-LFM2.5-2.6B (ctx: 65536, free: yes) - https://openrouter.ai/liquid/lfm-2.5-2.6b:free
- RWKV-5-World-7B-Eagle (ctx: 65536, free: yes) - https://freellmapi.co/model/BlinkDL_rwkv-5-world-7b
- gemini-3-pro-image-preview (ctx: 65536, free: yes) - https://aistudio.google.com/prompts/new_chat?model=google/gemini-3-pro-image-preview
- DeepSeek-R1 (ctx: 65536, free: yes) - https://cloud.infini-ai.com/platform/ai/genstudio
- DeepSeek R1 (ctx: 64000, free: yes) - https://siliconflow.cn/en
- DeepSeek R1 Distill Llama 70B (ctx: 64000, free: yes) - https://siliconflow.cn
- DeepSeek-V3-Chat (ctx: 64000, free: yes) - https://openrouter.ai/deepseek/deepseek-chat:free
- DeepSeek-V3 (ctx: 64000, free: yes) - https://cloud.siliconflow.cn/models
- Mixtral 8x22B Instruct (ctx: 64000, free: yes) - https://build.nvidia.com
- open-mistral-7b (ctx: 32768, free: yes) - https://docs.mistral.ai/models/
- Liquid-LFM-40B-MoE (ctx: 32768, free: yes) - https://openrouter.ai/liquid/lfm-40b:free
- HuggingFace-/-QwQ-32B-Preview (ctx: 32768, free: yes) - https://freellmapi.co/model/hf_Qwen_QwQ-32B-Preview
- GitHub-Models-/-Mistral-Small-2501 (ctx: 32768, free: yes) - https://freellmapi.co/model/gh_Mistral-Small-24B-Instruct-2501
- Nano-Banana (ctx: 32768, free: yes) - https://aistudio.google.com
- Codestral-2405 (ctx: 32768, free: yes) - https://freellmapi.co/model/codestral-2405
- Mixtral-8x7B-Instruct (ctx: 32768, free: yes) - https://freellmapi.co/model/mixtral-8x7b-instruct
- Mistral-7B-Instruct-v0.3 (ctx: 32768, free: yes) - https://freellmapi.co/model/mistral-7b-instruct-v0.3
- HuggingFace-/-OpenR1-Qwen-7B-Math (ctx: 32768, free: yes) - https://freellmapi.co/model/open-r1_OpenR1-Qwen-7B
- InternVL2.5-78B-Vision (ctx: 32768, free: yes) - https://freellmapi.co/model/internlm_internvl2_5-78b
- InternVL2.5-1B-Vision (ctx: 32768, free: yes) - https://freellmapi.co/model/internlm_internvl2_5-1b
- StateSpaces-/-Mamba-2-7B-SSM (ctx: 32768, free: yes) - https://freellmapi.co/model/state-spaces_mamba2-7b
- OpenRouter-/-Mistral-7B-Instruct:free (ctx: 32768, free: yes) - https://freellmapi.co/model/mistralai_mistral-7b-instruct:free
- HuggingFace-/-LLaVA-NeXT-Mistral-7B (ctx: 32768, free: yes) - https://freellmapi.co/model/hf_llava-hf_llava-v1.6-mistral-7b-hf
- Mistral-7B-Instruct-v0.2 (ctx: 32768, free: yes) - https://freellmapi.co/model/mistral-7b-instruct-v0.2
- HuggingFace-/-Mistral-Small-24B-Instruct-2501 (ctx: 32768, free: yes) - https://freellmapi.co/model/hf_mistralai_Mistral-Small-24B-Instruct-2501
- minimax-m2.1 (ctx: 32768, free: yes) - https://novita.ai/models/MiniMaxAI/MiniMax-M2.1
- qwen2.5-7b-instruct-uncensored-flux (ctx: 32768, free: yes) - https://featherless.ai/models/mrkrak3n/Qwen2.5-7B-Instruct-Uncensored-Flux
- OpenRouter-/-QwQ-32B-Preview:free (ctx: 32768, free: yes) - https://freellmapi.co/model/qwen_qwq-32b-preview:free
- nemotron-3-embed-1.8 (ctx: 32768, free: yes) - https://openrouter.ai/nvidia/nemotron-3-embed-1.8:free
- Cloudflare-/-Mistral-7B-v0.2 (ctx: 32768, free: yes) - https://freellmapi.co/model/cf_mistral_mistral-7b-instruct-v0.2
- SenseTime-/-SenseChat-Lite (ctx: 32768, free: yes) - https://freellmapi.co/model/SenseTime_SenseChat-Lite
- Tencent-/-Hunyuan-Standard (ctx: 32768, free: yes) - https://freellmapi.co/model/Tencent_Hunyuan-Standard-Instruct
- Qwen2.5-3B-Base-Edge (ctx: 32768, free: yes) - https://freellmapi.co/model/Qwen_Qwen2.5-3B-Base
- Yi-Large (ctx: 32768, free: yes) - https://freellmapi.co/model/yi-large
- qwen2.5-0.5b-portuguese-hybrid-reasoning (ctx: 32768, free: yes) - https://featherless.ai/models/cnmoro/Qwen2.5-0.5B-Portuguese-Hybrid-Reasoning
- Moonshot-v1-32k (ctx: 32768, free: yes) - https://freellmapi.co/model/moonshot-v1-32k
- Baichuan-3-Turbo (ctx: 32768, free: yes) - https://freellmapi.co/model/baichuan-3-turbo
- Tencent-/-Hunyuan-Lite-Free (ctx: 32768, free: yes) - https://freellmapi.co/model/Tencent_Hunyuan-Lite
- Vistral-7B-Chat-Vietnamese (ctx: 32768, free: yes) - https://freellmapi.co/model/Viet-Mistral_Vistral-7B-Chat
- DeepSeek-V2-Lite-16B-Base (ctx: 32768, free: yes) - https://freellmapi.co/model/deepseek-ai_DeepSeek-V2-Lite
- StateSpaces-/-Mamba-2-2.7B-SSM (ctx: 32768, free: yes) - https://freellmapi.co/model/state-spaces_mamba2-2.7b
- InternLM2-Chat-20B (ctx: 32768, free: yes) - https://freellmapi.co/model/internlm2-chat-20b
- InternVL-2.5-78B (ctx: 32768, free: yes) - https://freellmapi.co/model/internvl-2.5-78b
- InternVL-2.5-8B (ctx: 32768, free: yes) - https://freellmapi.co/model/internvl-2.5-8b
- InternVL-2.5-1B (ctx: 32768, free: yes) - https://freellmapi.co/model/internvl-2.5-1b
- SenseChat-Code (ctx: 32768, free: yes) - https://freellmapi.co/model/sensechat-code
- Megrez-3B-Instruct (ctx: 32768, free: yes) - https://freellmapi.co/model/Infinigence_Megrez-3B-Instruct
- Solar-Mini (ctx: 32768, free: yes) - https://freellmapi.co/model/solar-mini
- openthinker-32b (ctx: 32768, free: yes) - https://featherless.ai/models/open-thoughts/OpenThinker-32B
- Baichuan-4 (ctx: 32768, free: yes) - https://freellmapi.co/model/baichuan-4
- Baichuan-2-Turbo (ctx: 32768, free: yes) - https://freellmapi.co/model/baichuan-2-turbo
- Step-1-32k (ctx: 32768, free: yes) - https://freellmapi.co/model/step-1-32k
- phi-4-mini-instruct (ctx: 32768, free: yes) - https://huggingface.co/microsoft/Phi-4-mini-instruct
- Step-1V-32k (ctx: 32768, free: yes) - https://freellmapi.co/model/step-1v-32k
- gemma-2-9b-it (ctx: 32768, free: yes) - https://huggingface.co/google/gemma-2-9b-it
- InternLM2-Chat-7B (ctx: 32768, free: yes) - https://freellmapi.co/model/internlm2-chat-7b
- InternVL-2.5-26B (ctx: 32768, free: yes) - https://freellmapi.co/model/internvl-2.5-26b
- InternVL-2.5-4B (ctx: 32768, free: yes) - https://freellmapi.co/model/internvl-2.5-4b
- SenseChat-5 (ctx: 32768, free: yes) - https://freellmapi.co/model/sensechat-5
- Baichuan-/-Baichuan2-53B (ctx: 32768, free: yes) - https://freellmapi.co/model/baichuan-inc_Baichuan2-53B