2026-11-16
Google AI Studio catalog and free-tier documentation refreshed
Reviewed official documentation; updated tracked model IDs and limits, added source links, and removed unsupported quota claims. Documentation review does not replace live API probes.
2026-11-16
Hugging Face Inference archived from recurring free API recommendations
Free Hugging Face accounts no longer receive monthly Inference Providers credits. Credits must be purchased or included in a paid subscription.
2026-11-16
SambaNova Cloud catalog and free-tier documentation refreshed
Reviewed official documentation; updated tracked model IDs and limits, added source links, and removed unsupported quota claims. Documentation review does not replace live API probes.
2026-11-16
Mistral AI archived from recurring free API recommendations
Mistral Free mode does not include API access. Creating API keys and using the API require billing activation and pay-as-you-go.
2026-11-16
OpenRouter catalog and free-tier documentation refreshed
Reviewed official documentation; updated tracked model IDs and limits, added source links, and removed unsupported quota claims. Documentation review does not replace live API probes.
2026-11-16
Cohere catalog and free-tier documentation refreshed
Reviewed official documentation; updated tracked model IDs and limits, added source links, and removed unsupported quota claims. Documentation review does not replace live API probes.
2026-11-16
Cerebras archived from recurring free API recommendations
Cerebras now offers a $5, 30-day trial after adding a verified payment method. There is no recurring free API tier.
2026-11-16
BigModel catalog and free-tier documentation refreshed
Reviewed official documentation; updated tracked model IDs and limits, added source links, and removed unsupported quota claims. Documentation review does not replace live API probes.
2026-11-16
Groq catalog and free-tier documentation refreshed
Reviewed official documentation; updated tracked model IDs and limits, added source links, and removed unsupported quota claims. Documentation review does not replace live API probes.
2026-11-16
GitHub Models archived from recurring free API recommendations
GitHub Models was fully retired on July 30, 2026. Its catalog, playground, inference API and BYOK are no longer available.
2026-11-16
Ollama Cloud archived from recurring free API recommendations
Ollama Cloud now charges per token. The $0 subscription plan is pay-as-you-go, without included recurring free inference credits. Local inference on your own hardware remains free.
2026-11-16
AIHubMix catalog and free-tier documentation refreshed
Reviewed official documentation; updated tracked model IDs and limits, added source links, and removed unsupported quota claims. Documentation review does not replace live API probes.
2026-03-30
Added Google AI Studio provider
Added Google AI Studio. Google's free API gateway for Gemini models — Gemini 2.5 Flash and Flash-Lite are permanently free with no credit card required.
2026-03-30
AIHubMix added 19 free models
AIHubMix added 19 free models: GPT-4.1 Free (1M), GPT-4.1 Mini Free (1M), GPT-4.1 Nano Free (1M), GPT-4o Free (1M), Gemini 3 Flash Preview Free (1M), Gemini 2.0 Flash Free (1M), Coding GLM 5.1 Free (128K), Coding GLM 5 Free (128K), Coding GLM 5 Turbo Free (128K), Coding GLM 4.7 Free (128K), GLM-4.7 Flash Free (128K), Coding GLM 4.6 Free (200K), Coding MiniMax M2.7 Free (200K), Coding MiniMax M2.5 Free (200K), Coding MiniMax M2.1 Free (200K), Coding MiniMax M2 Free (200K), Step 3.5 Flash Free (256K), Kimi for Coding Free (256K), MiMo V2 Flash Free (256K).
2026-03-30
Groq added 14 free models
Groq added 14 free models: Allam 2 7B (4K), Groq Compound (128K), Groq Compound Mini (128K), Llama 3.1 8B Instant (128K), Llama 3.3 70B Versatile (128K), Llama 4 Scout 17B (10M), Llama Prompt Guard 2 22M (512), Llama Prompt Guard 2 86M (512), Kimi K2 Instruct (128K), Kimi K2 Instruct (0905) (128K), GPT OSS 120B (128K), GPT OSS 20B (128K), GPT OSS Safeguard 20B (128K), Qwen3 32B (128K).
2026-03-30
Cohere added 6 free models
Cohere added 6 free models: Command A (256K), Command R+ (128K), Command R (128K), Command R7B (128K), Aya Expanse 32B (128K), Aya Expanse 8B (8K).
2026-03-30
Hugging Face Inference added 6 free models
Hugging Face Inference added 6 free models: Llama 3.3 70B Instruct (128K), DeepSeek V3 (0324) (128K), GPT OSS 120B (128K), DeepSeek R1 (128K), Qwen3 235B A22B (128K), Kimi K2 Instruct (128K).
2026-03-30
Cerebras added 4 free models
Cerebras added 4 free models: Llama 3.1 8B (128K), GPT OSS 120B (128K), Qwen3 235B A22B Preview (128K), Z.ai GLM 4.7 Preview (128K).
2026-03-30
SambaNova Cloud added 8 free models
SambaNova Cloud added 8 free models: Llama 3.3 70B Instruct (128K), Llama 3.1 8B Instruct (128K), Llama 3.1 70B Instruct (128K), Llama 3.1 405B Instruct (128K), Llama 3.2 1B Instruct (128K), Llama 3.2 3B Instruct (128K), Llama 3.2 11B Vision Instruct (128K), Llama 3.2 90B Vision Instruct (128K).
2026-03-30
GitHub Models added 5 free models
GitHub Models added 5 free models: GPT-4o (8K), GPT-4o Mini (8K), Llama 3.3 70B Instruct (8K), DeepSeek R1 (8K), Phi-4 (8K).
2026-03-30
Google AI Studio added 3 free models
Google AI Studio added 3 free models: Gemini 2.5 Flash-Lite (1M), Gemini 2.5 Flash (1M), Gemini 2.5 Pro (1M).
2026-03-30
Added AIHubMix provider
Added AIHubMix. Unified OpenAI-compatible API aggregating OpenAI, Claude, Gemini, DeepSeek, GLM, Qwen and more — with load balancing and high concurrency support.
2026-03-30
Added Groq provider
Added Groq. High-speed LLM inference powered by LPU hardware — free tier includes Llama, Kimi, Qwen and more with generous rate limits.
2026-03-30
Added Cohere provider
Added Cohere. Trial API key with free access to Command A, Command R+, Command R7B and Aya Expanse. Limited to 20 RPM and 1,000 calls/month. Non-commercial use only.
2026-03-30
Added Hugging Face Inference provider
Added Hugging Face Inference. Unified inference router across 18+ providers (Groq, SambaNova, Together, Cerebras, etc.) — free users get $0.10/month in credits, no credit card required.
2026-03-30
Added Cerebras provider
Added Cerebras. Ultra-fast LLM inference via custom wafer-scale chips — free tier offers 30 RPM and 1M tokens/day with no credit card required.
2026-03-30
Added SambaNova Cloud provider
Added SambaNova Cloud. RDU-accelerated inference with a persistent free tier — no credit card required. Llama 3.1/3.2/3.3 series up to 405B, 200K tokens/day free.
2026-03-30
Added GitHub Models provider
Added GitHub Models. Free model inference via GitHub PAT — access GPT-4o, Llama, Phi, DeepSeek and more. Low tier: 15 RPM/150 RPD; High tier: 10 RPM/50 RPD. No credit card required.
2026-03-29
OpenRouter added 5 free models
OpenRouter added 5 free models: Step 3.5 Flash (128K), MiniMax M2.5 (131K), Nemotron 3 Super 120B (131K), Nemotron 3 Nano 30B (131K), GLM-4.5 Air (131K).
2026-03-29
BigModel added 4 free models
BigModel added 4 free models: GLM-4.7 Flash (200K), GLM-4 Flash (250414) (128K), GLM-4V Flash (8K), GLM-4.1V Thinking Flash (32K).
2026-03-29
Added OpenRouter provider
Added OpenRouter. Aggregates multiple LLM providers — some models are permanently free with no credit card required.
2026-03-29
Added BigModel provider
Added BigModel. Zhipu AI's open platform featuring GLM series models — permanently free API, available in China, OpenAI-compatible.