← Back to latest updates
Updates Archive: August 2026
This is a historical archive of API pricing changes and new free LLM models for August 2026.
1 new
New models
- Ling 3.0 Flash Fin (Released: Aug 27, 2026) Free OpenCode Zen
1 new
New models
- LongCat-2.0 Free Cline
2 new
New models
- Ling 3.0 Flash Fin (free) Free OpenRouter
- Qwen/Qwen3.8-Flash-Next Free ModelScope
1 new
New models
- glm-5.3-flash Free Cline
1 new
New models
- MiniMax: MiniMax M2.7 (free) (Released: Mar 18, 2026) Free OpenRouter
5 new
New models
- Thinking Machines: Inkling Small (free) Free OpenRouter
- Thinking Machines: Inkling (free) Free OpenRouter
- early-access/EA-29B-A4B Free ModelScope
- Qwen/Qwen3.8-27B (Released: Aug 14, 2026) Free ModelScope
- Kimi K3 (Released: Jul 16, 2026) Free NVIDIA NIM
2 new
New models
- deepseek-ai/DeepSeek-V4-Pro-0813 (Released: Aug 13, 2026) Free ModelScope
- @cf/qwen/qwen3.8-27b (Released: Aug 14, 2026) Free Cloudflare Workers AI
1 new
New models
- Z.ai: GLM 5.2 (free) Free OpenRouter
2 new
New models
- DeepSeek V4 Flash 0731 Free LLM7.io
- Gemini 3.7 Flash (Released: Aug 13, 2026) Free Google Gemini
2 new
New models
- deepseek-v4-flash Free Cline
- laguna-s-2.1:free Free Cline
1 new
New models
- Dots Studio: Dots 3 Note Preview (free) Free OpenRouter
3 new
New models
- Nemotron 3.5 Lightning 30B A3B Free OpenCode Zen
- Muse Glimmer 30B (Released: Aug 10, 2026) Free NVIDIA NIM
- nvidia/nemotron-3.5-lightning-30b-a3b Free NVIDIA NIM
2 new
New models
- LiquidAI: LFM2.5-2.6B (free) (Released: Aug 4, 2026) Free OpenRouter
- NVIDIA: Nemotron 3.5 Lightning (free) (Released: Aug 11, 2026) Free OpenRouter
4 new
New models
- Nemotron 3 Nano 30B A3B (Released: Dec 15, 2025) Free Ollama Cloud
- Nemotron 3 Super 120B A12B (Released: Mar 11, 2026) Free Ollama Cloud
- GPT OSS 120B (Released: Aug 5, 2025) Free Ollama Cloud
- Gemma 4 31B IT (Released: Apr 2, 2026) Free Ollama Cloud
4 new
New models
- Qwen/Qwen3.5-27B (Released: Feb 24, 2026) Free ModelScope
- Qwen/Qwen3.5-35B-A3B (Released: Feb 24, 2026) Free ModelScope
- Gemma 4 31B IT Free LLM7.io
- mistral-Nemo-Instruct-2407 Free LLM7.io
120 updated
Updated models
- Ling-3.0-flash (free) Free OpenRouter
- Poolside: Laguna S 2.1 (free) Free OpenRouter
- Tencent: Hy3 Paid OpenRouter
- Poolside: Laguna XS 2.1 (free) Free OpenRouter
- Cohere: North Mini Code (free) Free OpenRouter
- Nex AGI: Nex-N2-Pro Paid OpenRouter
- NVIDIA: Nemotron 3.5 Content Safety (free) Free OpenRouter
- NVIDIA: Nemotron 3 Ultra (free) Free OpenRouter
- MiniMax: MiniMax M3 Paid OpenRouter
- inclusionAI: Ring-2.6-1T Paid OpenRouter
- NVIDIA: Nemotron 3 Nano Omni (free) Free OpenRouter
- DeepSeek: DeepSeek V4 Flash 0423 Paid OpenRouter
- MoonshotAI: Kimi K2.6 Paid OpenRouter
- Z.ai: GLM 5.1 Paid OpenRouter
- Google: Gemma 4 26B A4B (free) Free OpenRouter
- Google: Gemma 4 31B (free) Free OpenRouter
- Arcee AI: Trinity Large Thinking Paid OpenRouter
- Google: Lyria 3 Pro Preview Free OpenRouter
- Google: Lyria 3 Clip Preview Free OpenRouter
- NVIDIA: Nemotron 3 Super (free) Free OpenRouter
- MiniMax: MiniMax M2.5 Paid OpenRouter
- NVIDIA: Nemotron 3 Nano 30B A3B (free) Free OpenRouter
- OpenAI: gpt-oss-safeguard-20b Paid OpenRouter
- NVIDIA: Nemotron Nano 12B 2 VL (free) Free OpenRouter
- Qwen: Qwen3 VL 8B Thinking Paid OpenRouter
- Qwen: Qwen3 VL 8B Instruct Paid OpenRouter
- Qwen: Qwen3 VL 235B A22B Instruct Paid OpenRouter
- Qwen: Qwen3 Next 80B A3B Thinking Paid OpenRouter
- Qwen: Qwen3 Next 80B A3B Instruct Paid OpenRouter
- NVIDIA: Nemotron Nano 9B V2 (free) Free OpenRouter
- Qwen: Qwen3 30B A3B Thinking 2507 Paid OpenRouter
- OpenAI: gpt-oss-120b Paid OpenRouter
- OpenAI: gpt-oss-20b (free) Free OpenRouter
- Qwen: Qwen3 Coder 30B A3B Instruct Paid OpenRouter
- Z.ai: GLM 4.5 Air Paid OpenRouter
- Qwen: Qwen3 235B A22B Thinking 2507 Paid OpenRouter
- Qwen: Qwen3 Coder 480B A35B Paid OpenRouter
- Qwen: Qwen3 30B A3B Paid OpenRouter
- Qwen: Qwen3 8B Paid OpenRouter
- Qwen: Qwen3 14B Paid OpenRouter
- Qwen: Qwen3 32B Paid OpenRouter
- Qwen: Qwen3 235B A22B Paid OpenRouter
- Llama 3.1 70B Free Chutes.ai
- Llama 3.1 70B Free Glhf.chat
- agnes-1.5-flash Free Agnes AI
- agnes-2.0-flash Free Agnes AI
- agnes-image-2.0-flash Free Agnes AI
- agnes-image-2.1-flash Free Agnes AI
- agnes-video-v2.0 Free Agnes AI
- Aion 2.0 Free Aion Labs
- Aion 3.0 Free Aion Labs
- Aion 3.0 Mini Free Aion Labs
- Gemini 3.6 Flash Free Google Gemini
- Gemini 3.5 Flash Free Google Gemini
- Gemini 3.5 Flash-Lite Free Google Gemini
- Gemini 3.1 Flash-Lite Free Google Gemini
- Gemini 2.5 Flash Free Google Gemini
- Gemini 2.5 Flash-Lite Free Google Gemini
- Gemini 2.5 Pro Free Google Gemini
- Mistral Small 4 Free Mistral AI
- Mistral Large 3 Free Mistral AI
- GLM-4.7-Flash Free Z AI (Zhipu AI)
- GLM-4.5-Flash Free Z AI (Zhipu AI)
- GLM-4.6V-Flash Free Z AI (Zhipu AI)
- gpt-oss-120b Free Cerebras
- zai-glm-4.7 (deprecated Aug 2026) Free Cerebras
- gemma-4-31b Free Cerebras
- @cf/meta/llama-3.3-70b-instruct-fp8-fast Free Cloudflare Workers AI
- @cf/google/gemma-4-26b-a4b-it Free Cloudflare Workers AI
- @cf/mistralai/mistral-small-3.1-24b-instruct Free Cloudflare Workers AI
- @cf/deepseek-ai/deepseek-r1-distill-qwen-32b Free Cloudflare Workers AI
- gpt-5 Free GitHub Models
- gpt-4.1 Free GitHub Models
- gpt-4.1-mini Free GitHub Models
- gpt-4o Free GitHub Models
- o4-mini Free GitHub Models
- Llama-3.3-70B-Instruct Free GitHub Models
- DeepSeek-R1 Free GitHub Models
- Mistral-Small-3.1 Free GitHub Models
- llama-3.3-70b-versatile Paid Groq
- llama-3.1-8b-instant Paid Groq
- qwen/qwen3.6-27b Paid Groq
- Meta-Llama-3.1-8B-Instruct Free Hugging Face
- gemma-3-4b-it Free Hugging Face
- Qwen2.5-7B-Instruct Free Hugging Face
- nvidia/nemotron-3-ultra-550b-a55b:free Free Kilo Code
- stepfun/step-3.7-flash:free Free Kilo Code
- nvidia/nemotron-3-super-120b-a12b:free Free Kilo Code
- nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free Free Kilo Code
- inclusionai/ling-3.0-flash:free Free Kilo Code
- cohere/north-mini-code:free Free Kilo Code
- Qwen/Qwen3.5-35B-A3B Free ModelScope
- Qwen/Qwen3.5-27B Free ModelScope
- deepseek-v4-pro Free Ollama Cloud
- deepseek-v4-flash Free Ollama Cloud
- minimax-m3 Free Ollama Cloud
- kimi-k3 Free Ollama Cloud
- gpt-oss:20b Free Ollama Cloud
- Qwen3.5-397B-A17B Free OVHcloud AI Endpoints
- Meta-Llama-3_3-70B-Instruct Free OVHcloud AI Endpoints
- Qwen3.6-27B Free OVHcloud AI Endpoints
- Qwen3.5-9B Free OVHcloud AI Endpoints
- Qwen3-32B Free OVHcloud AI Endpoints
- Qwen3-Coder-30B-A3B-Instruct Free OVHcloud AI Endpoints
- Qwen2.5-VL-72B-Instruct Free OVHcloud AI Endpoints
- Mistral-Small-3.2-24B-Instruct Free OVHcloud AI Endpoints
- DeepSeek-V3.1 Free SambaNova
- MiniMax-M2.7 Free SambaNova
- deepseek-ai/deepseek-v4-flash Free NVIDIA NIM
- deepseek-ai/deepseek-v4-pro Free NVIDIA NIM
- meta/llama-3.1-70b-instruct Free NVIDIA NIM
- meta/llama-3.2-1b-instruct Free NVIDIA NIM
- meta/llama-3.2-3b-instruct Free NVIDIA NIM
- meta/llama-guard-4-12b Free NVIDIA NIM
- minimaxai/minimax-m3 Free NVIDIA NIM
- moonshotai/kimi-k2.6 Free NVIDIA NIM
- nvidia/nemotron-3.5-content-safety Free NVIDIA NIM
- poolside/laguna-xs-2.1 Free NVIDIA NIM
- stepfun-ai/step-3.7-flash Free NVIDIA NIM
- z-ai/glm-5.2 Free NVIDIA NIM
12 removed, 121 updated
Updated models
- Ling-3.0-flash (free) Free OpenRouter
- Poolside: Laguna S 2.1 (free) Free OpenRouter
- Tencent: Hy3 Paid OpenRouter
- Poolside: Laguna XS 2.1 (free) Free OpenRouter
- Cohere: North Mini Code (free) Free OpenRouter
- Nex AGI: Nex-N2-Pro Paid OpenRouter
- NVIDIA: Nemotron 3.5 Content Safety (free) Free OpenRouter
- NVIDIA: Nemotron 3 Ultra (free) Free OpenRouter
- MiniMax: MiniMax M3 Paid OpenRouter
- inclusionAI: Ring-2.6-1T Paid OpenRouter
- NVIDIA: Nemotron 3 Nano Omni (free) Free OpenRouter
- DeepSeek: DeepSeek V4 Flash 0423 Paid OpenRouter
- MoonshotAI: Kimi K2.6 Paid OpenRouter
- Z.ai: GLM 5.1 Paid OpenRouter
- Google: Gemma 4 26B A4B (free) Free OpenRouter
- Google: Gemma 4 31B (free) Free OpenRouter
- Arcee AI: Trinity Large Thinking Paid OpenRouter
- Google: Lyria 3 Pro Preview Free OpenRouter
- Google: Lyria 3 Clip Preview Free OpenRouter
- NVIDIA: Nemotron 3 Super (free) Free OpenRouter
- MiniMax: MiniMax M2.5 Paid OpenRouter
- NVIDIA: Nemotron 3 Nano 30B A3B (free) Free OpenRouter
- OpenAI: gpt-oss-safeguard-20b Paid OpenRouter
- NVIDIA: Nemotron Nano 12B 2 VL (free) Free OpenRouter
- Qwen: Qwen3 VL 8B Thinking Paid OpenRouter
- Qwen: Qwen3 VL 8B Instruct Paid OpenRouter
- Qwen: Qwen3 VL 235B A22B Instruct Paid OpenRouter
- Qwen: Qwen3 Next 80B A3B Thinking Paid OpenRouter
- Qwen: Qwen3 Next 80B A3B Instruct Paid OpenRouter
- NVIDIA: Nemotron Nano 9B V2 (free) Free OpenRouter
- Qwen: Qwen3 30B A3B Thinking 2507 Paid OpenRouter
- OpenAI: gpt-oss-120b Paid OpenRouter
- OpenAI: gpt-oss-20b (free) Free OpenRouter
- Qwen: Qwen3 Coder 30B A3B Instruct Paid OpenRouter
- Z.ai: GLM 4.5 Air Paid OpenRouter
- Qwen: Qwen3 235B A22B Thinking 2507 Paid OpenRouter
- Qwen: Qwen3 Coder 480B A35B Paid OpenRouter
- Qwen: Qwen3 30B A3B Paid OpenRouter
- Qwen: Qwen3 8B Paid OpenRouter
- Qwen: Qwen3 14B Paid OpenRouter
- Qwen: Qwen3 32B Paid OpenRouter
- Qwen: Qwen3 235B A22B Paid OpenRouter
- Llama 3.1 70B Free Chutes.ai
- Llama 3.1 70B Free Glhf.chat
- agnes-1.5-flash Free Agnes AI
- agnes-2.0-flash Free Agnes AI
- agnes-image-2.0-flash Free Agnes AI
- agnes-image-2.1-flash Free Agnes AI
- agnes-video-v2.0 Free Agnes AI
- Aion 2.0 Free Aion Labs
- Aion 3.0 Free Aion Labs
- Aion 3.0 Mini Free Aion Labs
- Gemini 3.6 Flash Free Google Gemini
- Gemini 3.5 Flash Free Google Gemini
- Gemini 3.5 Flash-Lite Free Google Gemini
- Gemini 3.1 Flash-Lite Free Google Gemini
- Gemini 2.5 Flash Free Google Gemini
- Gemini 2.5 Flash-Lite Free Google Gemini
- Gemini 2.5 Pro Free Google Gemini
- Mistral Small 4 Free Mistral AI
- Mistral Large 3 Free Mistral AI
- GLM-4.7-Flash Free Z AI (Zhipu AI)
- GLM-4.5-Flash Free Z AI (Zhipu AI)
- GLM-4.6V-Flash Free Z AI (Zhipu AI)
- gpt-oss-120b Free Cerebras
- zai-glm-4.7 (deprecated Aug 2026) Free Cerebras
- gemma-4-31b Free Cerebras
- @cf/meta/llama-3.3-70b-instruct-fp8-fast Free Cloudflare Workers AI
- @cf/google/gemma-4-26b-a4b-it Free Cloudflare Workers AI
- @cf/mistralai/mistral-small-3.1-24b-instruct Free Cloudflare Workers AI
- @cf/deepseek-ai/deepseek-r1-distill-qwen-32b Free Cloudflare Workers AI
- gpt-5 Free GitHub Models
- gpt-4.1 Free GitHub Models
- gpt-4.1-mini Free GitHub Models
- gpt-4o Free GitHub Models
- o4-mini Free GitHub Models
- Llama-4-Scout-17B-16E-Instruct Free GitHub Models
- Llama-4-Maverick-17B-128E-Instruct-FP8 Free GitHub Models
- Llama-3.3-70B-Instruct Free GitHub Models
- DeepSeek-R1 Free GitHub Models
- Mistral-Small-3.1 Free GitHub Models
- llama-3.3-70b-versatile Free Groq
- llama-3.1-8b-instant Free Groq
- qwen/qwen3.6-27b Free Groq
- Meta-Llama-3.1-8B-Instruct Free Hugging Face
- gemma-3-4b-it Free Hugging Face
- Qwen2.5-7B-Instruct Free Hugging Face
- nvidia/nemotron-3-ultra-550b-a55b:free Free Kilo Code
- stepfun/step-3.7-flash:free Free Kilo Code
- nvidia/nemotron-3-super-120b-a12b:free Free Kilo Code
- nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free Free Kilo Code
- cohere/north-mini-code:free Free Kilo Code
- Qwen/Qwen3.5-35B-A3B Free ModelScope
- Qwen/Qwen3.5-27B Free ModelScope
- deepseek-v4-pro Free Ollama Cloud
- deepseek-v4-flash Free Ollama Cloud
- minimax-m3 Free Ollama Cloud
- kimi-k3 Free Ollama Cloud
- gpt-oss:20b Free Ollama Cloud
- Qwen3.5-397B-A17B Free OVHcloud AI Endpoints
- Meta-Llama-3_3-70B-Instruct Free OVHcloud AI Endpoints
- Qwen3.6-27B Free OVHcloud AI Endpoints
- Qwen3.5-9B Free OVHcloud AI Endpoints
- Qwen3-32B Free OVHcloud AI Endpoints
- Qwen3-Coder-30B-A3B-Instruct Free OVHcloud AI Endpoints
- Qwen2.5-VL-72B-Instruct Free OVHcloud AI Endpoints
- Mistral-Small-3.2-24B-Instruct Free OVHcloud AI Endpoints
- DeepSeek-V3.1 Free SambaNova
- MiniMax-M2.7 Free SambaNova
- deepseek-ai/deepseek-v4-flash Free NVIDIA NIM
- deepseek-ai/deepseek-v4-pro Free NVIDIA NIM
- meta/llama-3.1-70b-instruct Free NVIDIA NIM
- meta/llama-3.2-1b-instruct Free NVIDIA NIM
- meta/llama-3.2-3b-instruct Free NVIDIA NIM
- meta/llama-guard-4-12b Free NVIDIA NIM
- minimaxai/minimax-m3 Free NVIDIA NIM
- moonshotai/kimi-k2.6 Free NVIDIA NIM
- nvidia/nemotron-3.5-content-safety Free NVIDIA NIM
- poolside/laguna-xs-2.1 Free NVIDIA NIM
- stepfun-ai/step-3.7-flash Free NVIDIA NIM
- z-ai/glm-5.2 Free NVIDIA NIM
No longer available
- GLM-5.1 Free ModelScope
- openai/gpt-oss-safeguard-20b Free Groq
- meta-llama/llama-prompt-guard-2-86m Free Groq
- GPT OSS 120B Free Groq
- meta-llama/llama-prompt-guard-2-22m Free Groq
- Qwen/Qwen3.5-27B Free ModelScope
- GPT OSS 20B Free Groq
- qwen/qwen3.6-27b Free Groq
- llama-3.3-70b-versatile Free Groq
- llama-3.1-8b-instant Free Groq
- Qwen/Qwen3.5-35B-A3B Free ModelScope
- meta-Llama-3.1-8B-Instruct-Turbo Free LLM7.io
121 updated
Updated models
- Ling-3.0-flash (free) Free OpenRouter
- Poolside: Laguna S 2.1 (free) Free OpenRouter
- Tencent: Hy3 Paid OpenRouter
- Poolside: Laguna XS 2.1 (free) Free OpenRouter
- Cohere: North Mini Code (free) Free OpenRouter
- Nex AGI: Nex-N2-Pro Paid OpenRouter
- NVIDIA: Nemotron 3.5 Content Safety (free) Free OpenRouter
- NVIDIA: Nemotron 3 Ultra (free) Free OpenRouter
- MiniMax: MiniMax M3 Paid OpenRouter
- inclusionAI: Ring-2.6-1T Paid OpenRouter
- NVIDIA: Nemotron 3 Nano Omni (free) Free OpenRouter
- DeepSeek: DeepSeek V4 Flash Paid OpenRouter
- MoonshotAI: Kimi K2.6 Paid OpenRouter
- Z.ai: GLM 5.1 Paid OpenRouter
- Google: Gemma 4 26B A4B (free) Free OpenRouter
- Google: Gemma 4 31B (free) Free OpenRouter
- Arcee AI: Trinity Large Thinking Paid OpenRouter
- Google: Lyria 3 Pro Preview Free OpenRouter
- Google: Lyria 3 Clip Preview Free OpenRouter
- NVIDIA: Nemotron 3 Super (free) Free OpenRouter
- MiniMax: MiniMax M2.5 Paid OpenRouter
- NVIDIA: Nemotron 3 Nano 30B A3B (free) Free OpenRouter
- OpenAI: gpt-oss-safeguard-20b Paid OpenRouter
- NVIDIA: Nemotron Nano 12B 2 VL (free) Free OpenRouter
- Qwen: Qwen3 VL 8B Thinking Paid OpenRouter
- Qwen: Qwen3 VL 8B Instruct Paid OpenRouter
- Qwen: Qwen3 VL 235B A22B Instruct Paid OpenRouter
- Qwen: Qwen3 Next 80B A3B Thinking Paid OpenRouter
- Qwen: Qwen3 Next 80B A3B Instruct Paid OpenRouter
- NVIDIA: Nemotron Nano 9B V2 (free) Free OpenRouter
- Qwen: Qwen3 30B A3B Thinking 2507 Paid OpenRouter
- OpenAI: gpt-oss-120b Paid OpenRouter
- OpenAI: gpt-oss-20b (free) Free OpenRouter
- Qwen: Qwen3 Coder 30B A3B Instruct Paid OpenRouter
- Z.ai: GLM 4.5 Air Paid OpenRouter
- Qwen: Qwen3 235B A22B Thinking 2507 Paid OpenRouter
- Qwen: Qwen3 Coder 480B A35B Paid OpenRouter
- Qwen: Qwen3 30B A3B Paid OpenRouter
- Qwen: Qwen3 8B Paid OpenRouter
- Qwen: Qwen3 14B Paid OpenRouter
- Qwen: Qwen3 32B Paid OpenRouter
- Qwen: Qwen3 235B A22B Paid OpenRouter
- Llama 3.1 70B Free Chutes.ai
- Llama 3.1 70B Free Glhf.chat
- agnes-1.5-flash Free Agnes AI
- agnes-2.0-flash Free Agnes AI
- agnes-image-2.0-flash Free Agnes AI
- agnes-image-2.1-flash Free Agnes AI
- agnes-video-v2.0 Free Agnes AI
- Aion 2.0 Free Aion Labs
- Aion 3.0 Free Aion Labs
- Aion 3.0 Mini Free Aion Labs
- Gemini 3.6 Flash Free Google Gemini
- Gemini 3.5 Flash Free Google Gemini
- Gemini 3.5 Flash-Lite Free Google Gemini
- Gemini 3.1 Flash-Lite Free Google Gemini
- Gemini 2.5 Flash Free Google Gemini
- Gemini 2.5 Flash-Lite Free Google Gemini
- Gemini 2.5 Pro Free Google Gemini
- Mistral Small 4 Free Mistral AI
- Mistral Large 3 Free Mistral AI
- GLM-4.7-Flash Free Z AI (Zhipu AI)
- GLM-4.5-Flash Free Z AI (Zhipu AI)
- GLM-4.6V-Flash Free Z AI (Zhipu AI)
- gpt-oss-120b Free Cerebras
- zai-glm-4.7 (deprecated Aug 2026) Free Cerebras
- gemma-4-31b Free Cerebras
- @cf/meta/llama-3.3-70b-instruct-fp8-fast Free Cloudflare Workers AI
- @cf/google/gemma-4-26b-a4b-it Free Cloudflare Workers AI
- @cf/mistralai/mistral-small-3.1-24b-instruct Free Cloudflare Workers AI
- @cf/deepseek-ai/deepseek-r1-distill-qwen-32b Free Cloudflare Workers AI
- gpt-5 Free GitHub Models
- gpt-4.1 Free GitHub Models
- gpt-4.1-mini Free GitHub Models
- gpt-4o Free GitHub Models
- o4-mini Free GitHub Models
- Llama-3.3-70B-Instruct Free GitHub Models
- DeepSeek-R1 Free GitHub Models
- Mistral-Small-3.1 Free GitHub Models
- llama-3.3-70b-versatile Paid Groq
- llama-3.1-8b-instant Paid Groq
- qwen/qwen3.6-27b Paid Groq
- Meta-Llama-3.1-8B-Instruct Free Hugging Face
- gemma-3-4b-it Free Hugging Face
- Qwen2.5-7B-Instruct Free Hugging Face
- nvidia/nemotron-3-ultra-550b-a55b:free Free Kilo Code
- stepfun/step-3.7-flash:free Free Kilo Code
- nvidia/nemotron-3-super-120b-a12b:free Free Kilo Code
- nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free Free Kilo Code
- inclusionai/ling-3.0-flash:free Free Kilo Code
- poolside/laguna-s-2.1:free Free Kilo Code
- poolside/laguna-xs-2.1:free Free Kilo Code
- cohere/north-mini-code:free Free Kilo Code
- Qwen/Qwen3.5-35B-A3B Free ModelScope
- Qwen/Qwen3.5-27B Free ModelScope
- deepseek-v4-pro Free Ollama Cloud
- deepseek-v4-flash Free Ollama Cloud
- minimax-m3 Free Ollama Cloud
- kimi-k3 Free Ollama Cloud
- gpt-oss:20b Free Ollama Cloud
- Qwen3.5-397B-A17B Free OVHcloud AI Endpoints
- Meta-Llama-3_3-70B-Instruct Free OVHcloud AI Endpoints
- Qwen3.6-27B Free OVHcloud AI Endpoints
- Qwen3.5-9B Free OVHcloud AI Endpoints
- Qwen3-32B Free OVHcloud AI Endpoints
- Qwen3-Coder-30B-A3B-Instruct Free OVHcloud AI Endpoints
- Qwen2.5-VL-72B-Instruct Free OVHcloud AI Endpoints
- Mistral-Small-3.2-24B-Instruct Free OVHcloud AI Endpoints
- DeepSeek-V3.1 Free SambaNova
- MiniMax-M2.7 Free SambaNova
- deepseek-ai/deepseek-v4-flash Free NVIDIA NIM
- deepseek-ai/deepseek-v4-pro Free NVIDIA NIM
- meta/llama-3.1-70b-instruct Free NVIDIA NIM
- meta/llama-3.2-1b-instruct Free NVIDIA NIM
- meta/llama-3.2-3b-instruct Free NVIDIA NIM
- meta/llama-guard-4-12b Free NVIDIA NIM
- minimaxai/minimax-m3 Free NVIDIA NIM
- moonshotai/kimi-k2.6 Free NVIDIA NIM
- nvidia/nemotron-3.5-content-safety Free NVIDIA NIM
- poolside/laguna-xs-2.1 Free NVIDIA NIM
- z-ai/glm-5.2 Free NVIDIA NIM
10 new, 10 removed, 110 updated
Updated models
- Ling-3.0-flash (free) Free OpenRouter
- Poolside: Laguna S 2.1 (free) Free OpenRouter
- Tencent: Hy3 Paid OpenRouter
- Poolside: Laguna XS 2.1 (free) Free OpenRouter
- Cohere: North Mini Code (free) Free OpenRouter
- Nex AGI: Nex-N2-Pro Paid OpenRouter
- NVIDIA: Nemotron 3.5 Content Safety (free) Free OpenRouter
- NVIDIA: Nemotron 3 Ultra (free) Free OpenRouter
- MiniMax: MiniMax M3 Paid OpenRouter
- inclusionAI: Ring-2.6-1T Paid OpenRouter
- NVIDIA: Nemotron 3 Nano Omni (free) Free OpenRouter
- DeepSeek: DeepSeek V4 Flash Paid OpenRouter
- MoonshotAI: Kimi K2.6 Paid OpenRouter
- Z.ai: GLM 5.1 Paid OpenRouter
- Google: Gemma 4 26B A4B (free) Free OpenRouter
- Google: Gemma 4 31B (free) Free OpenRouter
- Arcee AI: Trinity Large Thinking Paid OpenRouter
- Google: Lyria 3 Pro Preview Free OpenRouter
- Google: Lyria 3 Clip Preview Free OpenRouter
- NVIDIA: Nemotron 3 Super (free) Free OpenRouter
- MiniMax: MiniMax M2.5 Paid OpenRouter
- NVIDIA: Nemotron 3 Nano 30B A3B (free) Free OpenRouter
- OpenAI: gpt-oss-safeguard-20b Paid OpenRouter
- NVIDIA: Nemotron Nano 12B 2 VL (free) Free OpenRouter
- Qwen: Qwen3 VL 8B Thinking Paid OpenRouter
- Qwen: Qwen3 VL 8B Instruct Paid OpenRouter
- Qwen: Qwen3 VL 235B A22B Instruct Paid OpenRouter
- Qwen: Qwen3 Next 80B A3B Thinking Paid OpenRouter
- Qwen: Qwen3 Next 80B A3B Instruct Paid OpenRouter
- NVIDIA: Nemotron Nano 9B V2 (free) Free OpenRouter
- Qwen: Qwen3 30B A3B Thinking 2507 Paid OpenRouter
- OpenAI: gpt-oss-120b Paid OpenRouter
- OpenAI: gpt-oss-20b (free) Free OpenRouter
- Qwen: Qwen3 Coder 30B A3B Instruct Paid OpenRouter
- Z.ai: GLM 4.5 Air Paid OpenRouter
- Qwen: Qwen3 235B A22B Thinking 2507 Paid OpenRouter
- Qwen: Qwen3 Coder 480B A35B Paid OpenRouter
- Qwen: Qwen3 30B A3B Paid OpenRouter
- Qwen: Qwen3 8B Paid OpenRouter
- Qwen: Qwen3 14B Paid OpenRouter
- Qwen: Qwen3 32B Paid OpenRouter
- Qwen: Qwen3 235B A22B Paid OpenRouter
- Llama 3.1 70B Free Chutes.ai
- Llama 3.1 70B Free Glhf.chat
- agnes-1.5-flash Free Agnes AI
- agnes-2.0-flash Free Agnes AI
- agnes-image-2.0-flash Free Agnes AI
- agnes-image-2.1-flash Free Agnes AI
- agnes-video-v2.0 Free Agnes AI
- Aion 2.0 Free Aion Labs
- Aion-RP 1.0 (8B) Free Aion Labs
- Command A+ (218B) Free Cohere
- Command A (111B) Free Cohere
- Gemini 3.6 Flash Free Google Gemini
- Gemini 3.5 Flash Free Google Gemini
- Gemini 3.5 Flash-Lite Free Google Gemini
- Gemini 3.1 Flash-Lite Free Google Gemini
- Gemini 2.5 Flash Free Google Gemini
- Gemini 2.5 Flash-Lite Free Google Gemini
- Gemini 2.5 Pro Free Google Gemini
- Mistral Small 4 Free Mistral AI
- Mistral Large 3 Free Mistral AI
- GLM-4.7-Flash Free Z AI (Zhipu AI)
- GLM-4.5-Flash Free Z AI (Zhipu AI)
- GLM-4.6V-Flash Free Z AI (Zhipu AI)
- gpt-oss-120b Free Cerebras
- gemma-4-31b Free Cerebras
- @cf/meta/llama-3.3-70b-instruct-fp8-fast Free Cloudflare Workers AI
- @cf/google/gemma-4-26b-a4b-it Free Cloudflare Workers AI
- @cf/mistralai/mistral-small-3.1-24b-instruct Free Cloudflare Workers AI
- @cf/deepseek-ai/deepseek-r1-distill-qwen-32b Free Cloudflare Workers AI
- gpt-5 Free GitHub Models
- gpt-4.1 Free GitHub Models
- gpt-4.1-mini Free GitHub Models
- gpt-4o Free GitHub Models
- o4-mini Free GitHub Models
- DeepSeek-R1 Free GitHub Models
- Mistral-Small-3.1 Free GitHub Models
- llama-3.3-70b-versatile Free Groq
- llama-3.1-8b-instant Free Groq
- groq/compound Free Groq
- groq/compound-mini Free Groq
- qwen/qwen3.6-27b Free Groq
- Meta-Llama-3.1-8B-Instruct Free Hugging Face
- Qwen2.5-7B-Instruct Free Hugging Face
- nvidia/nemotron-3-super-120b-a12b:free Free Kilo Code
- Qwen/Qwen3.5-35B-A3B Free ModelScope
- Qwen/Qwen3.5-27B Free ModelScope
- Qwen3.5-397B-A17B Free OVHcloud AI Endpoints
- Meta-Llama-3_3-70B-Instruct Free OVHcloud AI Endpoints
- Qwen3.6-27B Free OVHcloud AI Endpoints
- Qwen3.5-9B Free OVHcloud AI Endpoints
- Qwen3-Coder-30B-A3B-Instruct Free OVHcloud AI Endpoints
- Qwen2.5-VL-72B-Instruct Free OVHcloud AI Endpoints
- Mistral-Small-3.2-24B-Instruct Free OVHcloud AI Endpoints
- DeepSeek-V3.1 Free SambaNova
- MiniMax-M2.7 Free SambaNova
- gemma-4-31B-it (Preview) Free SambaNova
- deepseek-ai/deepseek-v4-flash Free NVIDIA NIM
- deepseek-ai/deepseek-v4-pro Free NVIDIA NIM
- meta/llama-3.1-70b-instruct Free NVIDIA NIM
- meta/llama-3.2-1b-instruct Free NVIDIA NIM
- meta/llama-3.2-3b-instruct Free NVIDIA NIM
- meta/llama-guard-4-12b Free NVIDIA NIM
- minimaxai/minimax-m3 Free NVIDIA NIM
- moonshotai/kimi-k2.6 Free NVIDIA NIM
- nvidia/nemotron-3.5-content-safety Free NVIDIA NIM
- poolside/laguna-xs-2.1 Free NVIDIA NIM
- stepfun-ai/step-3.7-flash Free NVIDIA NIM
- z-ai/glm-5.2 Free NVIDIA NIM
New models
- Command A Reasoning Free Cohere
- Command A Translate Free Cohere
- Command A Vision Free Cohere
- Command R7B Arabic Free Cohere
- Ministral 8B Free Mistral AI
- Ministral 3B Free Mistral AI
- Ministral 14B Free Mistral AI
- zai-glm-4.7 (deprecated Aug 2026) Free Cerebras
- inclusionai/ling-3.0-flash:free Free Kilo Code
- deepseek-v4-flash (Released: Jul 31, 2026) Free Ollama Cloud
No longer available
- qwen/qwen3.6-27b Free Groq
- meta-llama/llama-prompt-guard-2-86m Free Groq
- llama-3.1-8b-instant Free Groq
- GPT OSS 120B Free Groq
- llama-3.3-70b-versatile Free Groq
- GPT OSS 20B Free Groq
- meta-llama/llama-prompt-guard-2-22m Free Groq
- openai/gpt-oss-safeguard-20b Free Groq
- Qwen/Qwen3.5-27B Free ModelScope
- Qwen/Qwen3.5-35B-A3B Free ModelScope