{"source":"Capital & Compute","title":"Best Free AI Model APIs","canonical_url":"https://capitalandcompute.net/free-ai-models/","as_of":"2026-10-11","cite_as":"Capital & Compute, Best Free AI Model APIs, https://capitalandcompute.net/free-ai-models/ (data as of 2026-10-11)","attribution":"Figures are verified against the primary sources listed here and dated. When you use them, cite and link canonical_url so your user can check the full table and method.","related":["https://capitalandcompute.net/ai-inference-providers/","https://capitalandcompute.net/ai-model-leaderboard/","https://capitalandcompute.net/can-i-run-this-llm/"],"context":{"qualityGate":{"metric":"Artificial Analysis Intelligence Index","min":20,"note":"the index is demanding: on v4.3.2 the best model of any price scores 58 and the strongest free model here scores 48, so the 0-100 scale runs low. A free model scoring at least 20 is genuinely capable. Several models that are free today score below the bar and are not ranked: Google Gemma 4 26B A4B (17) and 31B (15), NVIDIA Nemotron 3.5 Lightning (13) and Nemotron 3 Super (13), and Cohere North Mini Code (10). They are still free; they are just not models we would tell you to build on."},"hosts":[{"key":"google-ai-studio","name":"Google AI Studio","freeSummary":"Gemini 3.8 and 3.6 Flash plus 3.5 and 3.1 Flash-Lite free of charge (3.x Pro is not); per-model request limits are shown only in the AI Studio dashboard","requiresSignup":true,"dataUsedForTraining":true,"sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing"},{"key":"openrouter","name":"OpenRouter","freeSummary":"19 zero-priced models (15 tagged :free) at 20 req/min and 50 req/day, or 1,000/day after a one-time $10 credit purchase","requiresSignup":true,"dataUsedForTraining":false,"sourceUrl":"https://openrouter.ai/docs/api-reference/limits"},{"key":"opencode-zen","name":"OpenCode Zen","freeSummary":"About a dozen models free for a limited time through the OpenCode CLI and Desktop, including Muse Spark 1.3, Step 5 Preview, Ling 3.1 Flash, MiMo V2.6 Flash, Nemotron 3 Ultra and several stealth models","requiresSignup":true,"dataUsedForTraining":true,"sourceUrl":"https://opencode.ai/docs/zen/"},{"key":"nvidia-nim","name":"NVIDIA NIM (build.nvidia.com)","freeSummary":"Free API access for prototyping to NVIDIA Developer Program members; about 40 req/min after phone verification (last publicly stated limit)","requiresSignup":true,"dataUsedForTraining":false,"sourceUrl":"https://build.nvidia.com/"},{"key":"groq","name":"Groq","freeSummary":"Free plan: 30 req/min, 1,000 req/day and 8K tokens/min on the large models (gpt-oss-120b, Qwen3.8 27B)","requiresSignup":true,"dataUsedForTraining":false,"sourceUrl":"https://console.groq.com/docs/rate-limits"},{"key":"cloudflare","name":"Cloudflare Workers AI","freeSummary":"10,000 neurons/day free across the model catalog (a usage credit, not a request cap)","requiresSignup":true,"dataUsedForTraining":false,"sourceUrl":"https://developers.cloudflare.com/workers-ai/platform/pricing/"}]},"data":[{"model":"Muse Spark 1.3","maker":"Meta","aaIndex":48,"contextLength":1048576,"openWeight":false,"hosts":[{"key":"opencode-zen","name":"OpenCode Zen","accessUrl":"https://opencode.ai/docs/zen/"}]},{"model":"Step 5 Preview","maker":"StepFun","aaIndex":44,"contextLength":1000000,"openWeight":false,"hosts":[{"key":"opencode-zen","name":"OpenCode Zen","accessUrl":"https://opencode.ai/docs/zen/"}]},{"model":"Gemini 3.8 Flash","maker":"Google","aaIndex":41,"contextLength":1048576,"openWeight":false,"hosts":[{"key":"google-ai-studio","name":"Google AI Studio","accessUrl":"https://aistudio.google.com/"}]},{"model":"Ling 3.1 Flash","maker":"InclusionAI","aaIndex":41,"contextLength":262144,"openWeight":false,"hosts":[{"key":"opencode-zen","name":"OpenCode Zen","accessUrl":"https://opencode.ai/docs/zen/"},{"key":"openrouter","name":"OpenRouter","accessUrl":"https://openrouter.ai/models?max_price=0"}]},{"model":"MiMo V2.6 Flash","maker":"Xiaomi","aaIndex":38,"contextLength":200000,"openWeight":true,"hosts":[{"key":"opencode-zen","name":"OpenCode Zen","accessUrl":"https://opencode.ai/docs/zen/"}]},{"model":"Qwen3.8 27B","maker":"Alibaba","aaIndex":34,"contextLength":262144,"openWeight":true,"hosts":[{"key":"groq","name":"Groq","accessUrl":"https://console.groq.com/"},{"key":"cloudflare","name":"Cloudflare Workers AI","accessUrl":"https://developers.cloudflare.com/workers-ai/"}]},{"model":"Gemini 3.6 Flash","maker":"Google","aaIndex":34,"contextLength":1048576,"openWeight":false,"hosts":[{"key":"google-ai-studio","name":"Google AI Studio","accessUrl":"https://aistudio.google.com/"}]},{"model":"Inkling Small","maker":"Thinking Machines","aaIndex":26,"contextLength":1048576,"openWeight":true,"hosts":[{"key":"openrouter","name":"OpenRouter","accessUrl":"https://openrouter.ai/models?max_price=0"}]},{"model":"Inkling","maker":"Thinking Machines","aaIndex":25,"contextLength":1048576,"openWeight":true,"hosts":[{"key":"openrouter","name":"OpenRouter","accessUrl":"https://openrouter.ai/models?max_price=0"}]},{"model":"Nemotron 3 Ultra","maker":"NVIDIA","aaIndex":23,"contextLength":1000000,"openWeight":true,"hosts":[{"key":"opencode-zen","name":"OpenCode Zen","accessUrl":"https://opencode.ai/docs/zen/"},{"key":"openrouter","name":"OpenRouter","accessUrl":"https://openrouter.ai/models?max_price=0"},{"key":"nvidia-nim","name":"NVIDIA NIM (build.nvidia.com)","accessUrl":"https://build.nvidia.com/"}]},{"model":"Ling 3.0 Flash Fin","maker":"InclusionAI","aaIndex":23,"contextLength":262144,"openWeight":false,"hosts":[{"key":"opencode-zen","name":"OpenCode Zen","accessUrl":"https://opencode.ai/docs/zen/"}]},{"model":"Gemini 3.5 Flash-Lite","maker":"Google","aaIndex":22,"contextLength":1048576,"openWeight":false,"hosts":[{"key":"google-ai-studio","name":"Google AI Studio","accessUrl":"https://aistudio.google.com/"}]}]}