Free LLM API picker
Filter every free LLM API by model family, context window, tool calling, vision, card requirement, RPM and region, ranked by published rate-limit headroom.
One row per model an offer serves free, from the same catalog as every offer page; see how we verify. Need N requests a day? Try the rate-limit calculator.
58 free LLM APIs, 239 model rows
Ranked by the requests per day the published limits allow; rows with no published limit come last. A dash means the vendor publishes no figure for that cell.
| Offer | Model | Context | Tools | Vision | RPM | RPD | TPM | Req/day cap | Card | Status | Notes |
|---|---|---|---|---|---|---|---|---|---|---|---|
 Alibaba Cloud Model Studio Free Token Quota | qwen-maxQwen | — | — | — | 600 | — | 1,000,000 | 864,000by RPM | No card | Verified · Oct 12, 2026 | Singapore region account-level limit |
| Alibaba Cloud Model Studio Free Token Quota | qwen-plusQwen | — | — | — | 600 | — | 1,000,000 | 864,000by RPM | No card | Verified · Oct 12, 2026 | Singapore region account-level limit; other regions differ |
 OVHcloud AI Endpoints Free Tier | Qwen3.5-397B-A17BQwen | 262k | Yes | Yes | 400 | — | — | 576,000by RPM | Card | Verified · Oct 12, 2026 | Same per-project/per-model limits |
| OVHcloud AI Endpoints Free Tier | Qwen3.6-27BQwen | 262k | Yes | Yes | 400 | — | — | 576,000by RPM | Card | Verified · Oct 12, 2026 | Same per-project/per-model limits |
| OVHcloud AI Endpoints Free Tier | Qwen3.8-27BQwen | 262k | Yes | Yes | 400 | — | — | 576,000by RPM | Card | Verified · Oct 12, 2026 | 400 req/min per project and per model when authenticated; 2 req/min anonymous |
| OVHcloud AI Endpoints Free Tier | gpt-oss-120bGPT | — | — | — | 400 | — | — | 576,000by RPM | Card | Verified · Oct 12, 2026 | Worked example in the getting-started guide |
| OVHcloud AI Endpoints Free Tier | Stable Diffusion XLOther | — | — | — | 400 | — | — | 576,000by RPM | Card | Verified · Oct 12, 2026 | Image generation example in the getting-started guide |
 Scaleway Generative APIs Free Tier | glm-5.2Other | 256k | Yes | No | 300 | — | 200,000 | 432,000by RPM | No card | Verified · Oct 12, 2026 | Supported model; per-model limits in Organization quotas, not on docs |
| Scaleway Generative APIs Free Tier | qwen3.6-35b-a3bQwen | 256k | Yes | Yes | 300 | — | 200,000 | 432,000by RPM | No card | Verified · Oct 12, 2026 | Supported model |
 Cloudflare Workers AI Free Tier | @cf/google/gemma-4-26b-a4b-itGemma | — | — | — | 300 | — | — | 432,000by RPM | No card | Listed · Oct 21, 2026 | Text Generation: 300 requests per minute; counts against 10,000 free Neurons/day |
| Cloudflare Workers AI Free Tier | @cf/meta/llama-3.3-70b-instruct-fp8-fastLlama | — | — | — | 300 | — | — | 432,000by RPM | No card | Listed · Oct 21, 2026 | Text Generation: 300 requests per minute; counts against 10,000 free Neurons/day |
| Cloudflare Workers AI Free Tier | @cf/mistralai/mistral-small-3.1-24b-instructMistral | — | — | — | 300 | — | — | 432,000by RPM | No card | Listed · Oct 21, 2026 | Text Generation: 300 requests per minute; counts against 10,000 free Neurons/day |
| Cloudflare Workers AI Free Tier | @cf/openai/gpt-oss-120bGPT | — | — | — | 300 | — | — | 432,000by RPM | No card | Listed · Oct 21, 2026 | Text Generation: 300 requests per minute; counts against 10,000 free Neurons/day |
| Cloudflare Workers AI Free Tier | @cf/openai/gpt-oss-20bGPT | — | — | — | 300 | — | — | 432,000by RPM | No card | Listed · Oct 21, 2026 | Text Generation: 300 requests per minute; counts against 10,000 free Neurons/day |
| Cloudflare Workers AI Free Tier | @cf/qwen/qwen3-30b-a3b-fp8Qwen | — | — | — | 300 | — | — | 432,000by RPM | No card | Listed · Oct 21, 2026 | Text Generation: 300 requests per minute; counts against 10,000 free Neurons/day |
| Cloudflare Workers AI Free Tier | @cf/zai-org/glm-4.7-flashOther | — | — | — | 300 | — | — | 432,000by RPM | No card | Listed · Oct 21, 2026 | Text Generation: 300 requests per minute; counts against 10,000 free Neurons/day |
 AI21 Labs Free Trial | Jamba LargeOther | 256k | Yes | — | 200 | — | — | 288,000by RPM | No card | Verified · Oct 12, 2026 | Foundation model limits: 10 RPS, 200 RPM; same for trial keys |
| AI21 Labs Free Trial | Jamba MiniOther | 256k | Yes | — | 200 | — | — | 288,000by RPM | No card | Verified · Oct 12, 2026 | 10 RPS, 200 RPM |
 Mixedbread Free Starter Credits | Toast 1Other | — | — | — | 100 | — | — | 144,000by RPM | No card | Verified · Oct 12, 2026 | Starter tier: 100 queries/min, 6,000 uploads/min |
 Upstage AI Initiative Free Access | solar-pro4Other | — | — | — | 100 | — | 250,000 | 144,000by RPM | No card | Verified · Oct 12, 2026 | Default limits from the chat quickstart table; tier-assigned |
 LLM7.io Free Tier | nemotron-3-nano:30bOther | 1M | Yes | No | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | turbo tier (free token); limits shared across models |
| LLM7.io Free Tier | DeepSeek-V4-Flash-0731DeepSeek | 400k | Yes | No | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | Free token: 100,000 tokens per 24 hours, 60 req/min; limits shared across models |
| LLM7.io Free Tier | GLM-5.3-FlashOther | 400k | Yes | No | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | Catalog entry; free-token limits shared |
| LLM7.io Free Tier | minimax-m2.7Other | 180k | Yes | No | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | turbo tier (free token); limits shared across models |
| LLM7.io Free Tier | gpt-oss:20bGPT | 128k | Yes | No | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | turbo tier (free token); limits shared across models |
| LLM7.io Free Tier | mistral-Nemo-Instruct-2407Mistral | 128k | No | No | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | turbo tier (free token); limits shared across models |
| LLM7.io Free Tier | codestral-latestMistral | 32k | Yes | No | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | turbo tier (free token); limits shared across models |
 Token Harbor Free Allowance | DeepSeek V4.1 FlashDeepSeek | — | — | — | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | Free plan allowance resets on a rolling 7-day period; no limits published |
| Token Harbor Free Allowance | DeepSeek V4.1 FlashDeepSeek | — | — | — | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | Free-plan model |
| Token Harbor Free Allowance | MiMo V2.6 FlashOther | — | — | — | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | Free plan model; lineup changes |
| Token Harbor Free Allowance | MiMo V2.6 FlashOther | — | — | — | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | Free allowance resets on a rolling 7-day period; limits unpublished |
| Token Harbor Free Allowance | TH-RudderOther | — | — | — | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | Free plan model |
| Token Harbor Free Allowance | TH-RudderOther | — | — | — | 60 | — | — | 86,400by RPM | No card | Verified · Oct 12, 2026 | Chat model offered free |
 Sarvam AI Free API Credits | sarvam-105bOther | — | — | — | 40 | — | — | 57,600by RPM | No card | Verified · Oct 12, 2026 | Starter tier chat limit for this model (other chat models 60 req/min) |
 AMD Radeon Cloud Free APIs | DeepSeek-V4-FlashDeepSeek | — | — | — | 30 | — | — | 43,200by RPM | No card | Verified · Oct 12, 2026 | Typical per-key 30 RPM and 8 concurrent; spend cap per account |
| AMD Radeon Cloud Free APIs | DeepSeek-V4-Flash-Vision-ExpDeepSeek | — | — | Yes | 30 | — | — | 43,200by RPM | No card | Verified · Oct 12, 2026 | Shared per-key limits |
| AMD Radeon Cloud Free APIs | DeepSeek-V4.1-FlashDeepSeek | — | — | — | 30 | — | — | 43,200by RPM | No card | Verified · Oct 12, 2026 | Shared per-key limits |
| AMD Radeon Cloud Free APIs | GLM-5.3-FlashOther | — | — | — | 30 | — | — | 43,200by RPM | No card | Verified · Oct 12, 2026 | Shared per-key limits |
| AMD Radeon Cloud Free APIs | MiMo-V2.6-FlashOther | — | — | — | 30 | — | — | 43,200by RPM | No card | Verified · Oct 12, 2026 | Shared per-key limits |
| AMD Radeon Cloud Free APIs | Qwen3.8-27BQwen | — | — | — | 30 | — | — | 43,200by RPM | No card | Verified · Oct 12, 2026 | Shared per-key limits |
| AMD Radeon Cloud Free APIs | Qwen3.8-Flash-NextQwen | — | — | — | 30 | — | — | 43,200by RPM | No card | Verified · Oct 12, 2026 | Shared per-key limits |
 Cohere Free Trial API | command-a-03-2025Other | 256k | — | — | 20 | — | — | 28,800by RPM | No card | Verified · Oct 12, 2026 | Trial chat limit |
| Cohere Free Trial API | command-a-plus-05-2026Other | 128k | — | — | 20 | — | — | 28,800by RPM | No card | Verified · Oct 12, 2026 | Trial chat limit 20 req/min; trial keys capped at 1,000 API calls a month |
| Cohere Free Trial API | command-a-vision-07-2025Other | 128k | — | Yes | 20 | — | — | 28,800by RPM | No card | Verified · Oct 12, 2026 | Trial chat limit; vision model |
| Agnes 2.5 FlashOther | — | — | — | 15 | — | — | 21,600by RPM | No card | Verified · Oct 12, 2026 | Free plan: 15 req/min, 7M tokens per day shared | |
| Laguna S 2.1Other | — | — | — | 15 | — | — | 21,600by RPM | No card | Verified · Oct 12, 2026 | Shared free-plan limits | |
| Nemotron 3.5 Lightning FreeOther | — | — | — | 15 | — | — | 21,600by RPM | No card | Verified · Oct 12, 2026 | Shared free-plan limits | |
 Agnes AI Free API | agnes-2.5-flashOther | 512k | Yes | Yes | 10 | — | — | 14,400by RPM | No card | Verified · Oct 12, 2026 | Default keys: text models effective 10 RPM; free keys and Token Plan keys use separate pools |
| Agnes AI Free API | agnes-3.0-flashOther | — | — | — | 10 | — | — | 14,400by RPM | No card | Verified · Oct 12, 2026 | Shares the text-model default 10 RPM |
 NVIDIA NIM Free Inference Endpoints | deepseek-v4.1-flashDeepSeek | 1.0M | Yes | Yes | 40 | 10,000 | — | 10,000by RPD | No card | Verified · Oct 12, 2026 | Free inference endpoint; limits not published |
| NVIDIA NIM Free Inference Endpoints | nemotron-3-ultra-550b-a55bOther | 1.0M | Yes | No | 40 | 10,000 | — | 10,000by RPD | No card | Verified · Oct 12, 2026 | Free inference endpoint |
| NVIDIA NIM Free Inference Endpoints | nemotron-3.5-lightning-30b-a3bOther | 1.0M | Yes | No | 40 | 10,000 | — | 10,000by RPD | No card | Verified · Oct 12, 2026 | Free inference endpoint; text input only |
 Cerebras Inference Free Trial | gpt-oss-120bGPT | 65k | — | — | 5 | — | 30,000 | 7,200by RPM | Card | Verified · Oct 12, 2026 | Free Trial: 5 RPM, 30K uncached TPM, 1M TPD; 65k context on free vs 131k paid |
| Cerebras Inference Free Trial | qwen-3.8-27bQwen | 64k | — | Yes | 5 | — | 30,000 | 7,200by RPM | Card | Verified · Oct 12, 2026 | Same Free Trial limits; 64k context on free; 2 images per request |
 Infron Free AI Models | deepseek/deepseek-v4.1-flash:freeDeepSeek | 1M | Yes | Yes | — | 1,000 | — | 1,000by RPD | No card | Verified · Oct 12, 2026 | Standard free model; 1,000 requests/day per account shared across free models; requires a $5+ balance |
 Groq Free Tier | openai/gpt-oss-120bGPT | 131k | — | — | 30 | 1,000 | 8,000 | 1,000by RPD | No card | Verified · Oct 12, 2026 | Free Plan Limits tab; TPD 200K |
| Groq Free Tier | openai/gpt-oss-20bGPT | 131k | — | — | 30 | 1,000 | 8,000 | 1,000by RPD | No card | Verified · Oct 12, 2026 | Free Plan Limits; TPD 200K |
| Groq Free Tier | qwen/qwen3.8-27bQwen | 131k | — | — | 30 | 1,000 | 8,000 | 1,000by RPD | No card | Verified · Oct 12, 2026 | Free Plan Limits; TPD 200K |
 Requesty Free Models | nvidia/nemotron-3-ultra-550b-a55bOther | 1M | Yes | — | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Free plan: 200 requests/day across all models |
| Requesty Free Models | nvidia/nemotron-3.5-lightning-30b-a3bOther | 1M | Yes | — | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Free plan shared daily cap |
| Requesty Free Models | google/gemma-4-31b-itGemma | 262k | Yes | Yes | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Free plan shared daily cap |
| Requesty Free Models | inclusionai/ling-3.1-flashOther | 262k | Yes | — | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Free plan shared daily cap |
| Requesty Free Models | mistral/leanstral-1-5Mistral | 262k | Yes | — | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Free plan shared daily cap |
| Requesty Free Models | meta/muse-glimmer-30bOther | 131k | Yes | Yes | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Free plan shared daily cap |
 Routeway Free Models | DeepSeek V4 Flash (Free)DeepSeek | — | Yes | — | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Free tier 200 req/day (cannot be increased); 20 RPM per the FAQ |
| Routeway Free Models | Gemma 4 26B MeroMero (Free)Gemma | — | Yes | Yes | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Shared free-tier limits |
| Routeway Free Models | Glimmer 30B (Free)Other | — | Yes | Yes | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Shared free-tier limits |
| Routeway Free Models | MiniMax M2.7 (Free)Other | — | Yes | — | 20 | 200 | — | 200by RPD | No card | Verified · Oct 12, 2026 | Shared free-tier limits |
 OpenRouter Free AI Models | Thinking Machines: Inkling (free)Other | 1.0M | Yes | Yes | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | Thinking Machines: Inkling Small (free)Other | 1.0M | Yes | Yes | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | MiniMax: MiniMax M3.1 Flash (free)Other | 1M | Yes | Yes | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | NVIDIA: Nemotron 3 Ultra (free)Other | 1M | Yes | No | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | All :free variants: 20 RPM; 50 RPD without credits, 1,000 RPD after 10+ credits |
| OpenRouter Free AI Models | NVIDIA: Nemotron 3.5 Lightning (free)Other | 1M | Yes | No | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | NVIDIA: Nemotron 3.5 Super VL (free)Other | 1M | Yes | Yes | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | Dots Studio: Dots3-Note Preview (free)Other | 512k | Yes | Yes | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | Google: Gemma 4 26B A4B (free)Google | 262k | Yes | Yes | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | Google: Gemma 4 31B (free)Google | 262k | Yes | Yes | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | NVIDIA: Nemotron 3 Super (free)Other | 262k | Yes | No | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | Poolside: Laguna S 2.1 (free)Other | 262k | Yes | No | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits; free use may train provider models |
| OpenRouter Free AI Models | Poolside: Laguna XS 2.1 (free)Other | 262k | Yes | No | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | XingChen: Xing4.0 29B A4B (free)Other | 262k | Yes | No | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | Cohere: North Mini Code (free)Other | 256k | Yes | No | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | NVIDIA: Nemotron 3 Nano Omni (free)Other | 256k | Yes | Yes | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | NVIDIA: Nemotron 3.5 Content Safety (free)Other | 128k | No | Yes | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
| OpenRouter Free AI Models | LiquidAI: LFM2.5-2.6B (free)Other | 66k | Yes | No | 20 | 50 | — | 50by RPD | No card | Verified · Oct 12, 2026 | Shared free-variant limits |
 OrcaRouter Free AI Models & API Credits | deepseek/deepseek-v4-flash-freeDeepSeek | — | — | — | 10 | 50 | — | 50by RPD | No card | Listed · Sep 10, 2026 | Limits published only at GET /api/free-package/public |
| OrcaRouter Free AI Models & API Credits | orcarouter/freeOther | — | — | — | 10 | 50 | — | 50by RPD | No card | Listed · Sep 10, 2026 | Difficulty-routed alias covering the free tier |
| OrcaRouter Free AI Models & API Credits | tencent/hy3-freeOther | — | — | — | 10 | 50 | — | 50by RPD | No card | Listed · Sep 10, 2026 | Free id in the catalog; lineup rotates |
 EmberCloud for Startups | glm-5.3-flashOther | 1.3M | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Context from the pricing page |
 OpenAI for Startups | gpt-5.6-lunaGPT | 1.1M | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits are standard API credits; limits follow the org usage tier (program adds upgrades) |
| OpenAI for Startups | gpt-5.6-solGPT | 1.1M | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits are standard API credits; limits follow the org usage tier (program adds upgrades) |
| OpenAI for Startups | gpt-6-astraGPT | 1.1M | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits are standard API credits; limits follow the org usage tier (program adds upgrades) |
| OpenAI for Startups | gpt-6-lunaGPT | 1.1M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits are standard API credits; limits follow the org usage tier (program adds upgrades) |
| OpenAI for Startups | gpt-6-solGPT | 1.1M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits are standard API credits; limits follow the org usage tier (program adds upgrades) |
| OpenAI for Startups | gpt-6.1-solGPT | 1.1M | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits are standard API credits; limits follow the org usage tier (program adds upgrades) |
 Nebius Token Factory $1 Trial Credit | DeepSeek V4.1 FlashDeepSeek | 1.0M | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Defaults only shown in the dashboard; the docs example is illustrative |
 Sarvam AI Startup Program | DeepSeek V4.1 FlashDeepSeek | 1.0M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits cover the Sarvam API stack; limits depend on the account tier; open-weight, beta |
| Sarvam AI Startup Program | GLM-5.3Other | 1.0M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits cover the Sarvam API stack; limits depend on the account tier; open-weight, beta |
 Together AI Startup Accelerator | moonshotai/Kimi-K3Other | 1.0M | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Accelerator credits cover serverless inference; function calling Yes in the serverless table; limits for program… |
| Together AI Startup Accelerator | zai-org/GLM-5.2Other | 1.0M | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Accelerator credits cover serverless inference; function calling Yes in the serverless table; limits for program… |
 DeepInfra DeepStart 50 Billion Free Inference Tokens | deepseek-ai/DeepSeek-V4-Flash-0731DeepSeek | 1.0M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | DeepStart tokens spend on the whole catalog; featured on the program page; DeepInfra publishes no per-model RPM |
| DeepInfra DeepStart 50 Billion Free Inference Tokens | deepseek-ai/DeepSeek-V4-Pro-0813DeepSeek | 1.0M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | DeepStart tokens spend on the whole catalog; featured on the program page; DeepInfra publishes no per-model RPM |
| DeepInfra DeepStart 50 Billion Free Inference Tokens | deepseek-ai/DeepSeek-V4.1-FlashDeepSeek | 1.0M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | DeepStart tokens spend on the whole catalog; featured on the program page; DeepInfra publishes no per-model RPM |
| DeepInfra DeepStart 50 Billion Free Inference Tokens | moonshotai/Kimi-K3Other | 1.0M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | DeepStart tokens spend on the whole catalog; featured on the program page; DeepInfra publishes no per-model RPM |
| DeepInfra DeepStart 50 Billion Free Inference Tokens | stepfun-ai/Step-5-PreviewOther | 1.0M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | DeepStart tokens spend on the whole catalog; featured on the program page; DeepInfra publishes no per-model RPM |
| DeepInfra DeepStart 50 Billion Free Inference Tokens | XiaomiMiMo/MiMo-V2.6-FlashOther | 1.0M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | DeepStart tokens spend on the whole catalog; featured on the program page; DeepInfra publishes no per-model RPM |
| DeepInfra DeepStart 50 Billion Free Inference Tokens | zai-org/GLM-5.2Other | 1.0M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | DeepStart tokens spend on the whole catalog; featured on the program page; DeepInfra publishes no per-model RPM |
| DeepInfra DeepStart 50 Billion Free Inference Tokens | zai-org/GLM-5.3Other | 1.0M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | DeepStart tokens spend on the whole catalog; featured on the program page; DeepInfra publishes no per-model RPM |
 AkashML $100 Free AI Token Credits | GLM 5.3Other | 1M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | No limits published |
 Anthropic AI for Science Program | Claude Haiku 5.5Claude | 1M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Standard suite |
| Anthropic AI for Science Program | Claude Opus 5.5Claude | 1M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Standard suite; no non-public models; limits follow the org tier |
| Anthropic AI for Science Program | Claude Sonnet 5.5Claude | 1M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Standard suite |
 Baseten AI Startup Program | DeepSeek V4.1 FlashDeepSeek | 1M | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Model API; tool use platform-wide; limits unpublished |
| Baseten AI Startup Program | Kimi K3Other | 1M | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Model API |
 Claude API New User Credits | Claude Haiku 5.5Claude | 1M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Limits follow the org tier |
| Claude API New User Credits | Claude Opus 5.5Claude | 1M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | New orgs may start in the Evaluation tier with unpublished limits |
| Claude API New User Credits | Claude Sonnet 5.5Claude | 1M | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Limits follow the org tier |
| EmberCloud for Startups | deepseek-v4-flashDeepSeek | 1M | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Context from the pricing page |
| EmberCloud for Startups | kimi-k3Other | 1M | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Context from the pricing page |
 Helyx AI Free Signup Credit | DeepSeek-V4-FlashDeepSeek | 1M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Live catalog; no per-model daily caps |
| Helyx AI Free Signup Credit | DeepSeek-V4-ProDeepSeek | 1M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Live catalog |
| Helyx AI Free Signup Credit | gemini-3.1-flash-liteGemini | 1M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Live catalog |
| Helyx AI Free Signup Credit | MiniMax-M3Other | 1M | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Live catalog |
 Inception - 100M Free Tokens for Mercury 3 | Mercury 3Other | 1M | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | 1M context, up to 131,072 output tokens; 100M free tokens for new accounts; no per-model free limits published |
| Together AI Startup Accelerator | deepseek-ai/DeepSeek-V4.1-FlashDeepSeek | 1M | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Accelerator credits cover serverless inference; function calling Yes in the serverless table; limits for program… |
| Together AI Startup Accelerator | Qwen/Qwen3.6-PlusQwen | 1M | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Accelerator credits cover serverless inference; function calling Yes in the serverless table; limits for program… |
| Together AI Startup Accelerator | MiniMaxAI/MiniMax-M3Other | 524k | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Accelerator credits cover serverless inference; function calling Yes in the serverless table; limits for program… |
| Together AI Startup Accelerator | thinkingmachines/InklingOther | 524k | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Accelerator credits cover serverless inference; function calling Yes in the serverless table; limits for program… |
 Pollinations Free API | openai-fastGPT | 400k | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Alias of GPT-5 Nano (openai/gpt-5-nano); priced in Pollen but not paid-only, so Quest Pollen can pay; no Pollinations… |
| EmberCloud for Startups | qwen3-coder-nextQwen | 262k | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Context from the pricing page |
| Helyx AI Free Signup Credit | gemma-4-31B-itGemma | 262k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Live catalog |
| NVIDIA NIM Free Inference Endpoints | nemotron-3.5-super-vl-120b-a12bOther | 262k | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free inference endpoint; text, image and video input |
 Vercel AI Gateway Free Tier | inclusionai/ling-3.1-flashOther | 262k | Yes | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Free-tier-eligible; per-model limits lower than paid and not published as numbers |
| AkashML $100 Free AI Token Credits | QWEN3.6 35B A3BQwen | 256k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | No limits published |
| AkashML $100 Free AI Token Credits | QWEN3.8 27BQwen | 256k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | $100 credits usable on all models; no limits published |
| Scaleway Generative APIs Free Tier | deepseek-v4-flash-0731DeepSeek | 256k | Yes | No | — | — | — | not published | No card | Verified · Oct 12, 2026 | Supported model |
| Scaleway Generative APIs Free Tier | qwen3.8-27bQwen | 256k | Yes | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Supported model |
 SmarToken $5 Signup Credit | kimi-k2Other | 256k | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Models catalog; no rate limits published |
| Vercel AI Gateway Free Tier | poolside/laguna-s-2.1-freeOther | 256k | Yes | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Free-tier-eligible; limits unpublished |
| EmberCloud for Startups | glm-5Other | 203k | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | No rate limits published |
 Z.AI Free API Tier | GLM-4.7-FlashOther | 200k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Priced Free; concurrency set by the platform per plan |
| Together AI Startup Accelerator | meta-models/Muse-Glimmer-30BOther | 131k | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Accelerator credits cover serverless inference; function calling Yes in the serverless table; limits for program… |
| Together AI Startup Accelerator | openai/gpt-oss-120bGPT | 131k | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Accelerator credits cover serverless inference; function calling Yes in the serverless table; limits for program… |
| AkashML $100 Free AI Token Credits | GPT OSS 120BGPT | 128k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | No limits published |
| SmarToken $5 Signup Credit | deepseek-chatDeepSeek | 128k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Credit consumption varies by route; no rate limits published |
| SmarToken $5 Signup Credit | doubao-seedOther | 128k | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Models catalog |
| SmarToken $5 Signup Credit | glm-4-flashOther | 128k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Models catalog |
| SmarToken $5 Signup Credit | qwen-plusQwen | 128k | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Models catalog |
| Inception - 100M Free Tokens for Mercury 3 | Mercury Edit 2Other | 32k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | FIM / next-edit model |
 SiliconFlow Free Credits and Free Models | mistralai/Mistral-7B-Instruct-v0.2Mistral | 32k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free LLM list |
| SiliconFlow Free Credits and Free Models | Qwen/Qwen2-1.5B-InstructQwen | 32k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free LLM list |
| SiliconFlow Free Credits and Free Models | Qwen/Qwen2-7B-InstructQwen | 32k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | On the free LLM list; limits fixed but unpublished |
| SiliconFlow Free Credits and Free Models | THUDM/glm-4-9b-chatOther | 32k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free LLM list |
| Qwen 3.6 35BQwen | 16k | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Self-hosted open model included in the grant; 100,000 requests per month per key | |
| Vercel AI Gateway Free Tier | convaiinnovations/layaOther | 8k | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Free-tier-eligible (8.2K context) |
| AkashML $100 Free AI Token Credits | Llama 3.3 70BLlama | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | No limits published |
| Alibaba Cloud Free Trial | qwen-maxQwen | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Named on the free-quota page |
| Alibaba Cloud Free Trial | qwen-plusQwen | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Independent free quota per model (typically 1,000,000 tokens), valid 90 days |
| Alibaba Cloud Free Trial | qwen3.6-plusQwen | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Named on the free-quota page |
| Alibaba Cloud Model Studio Free Token Quota | qwen3.8-maxQwen | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Singapore region limits listed as Dynamic |
 Alysis Code Free Tier | Claude Haiku 5.5Claude | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free-allowance table |
| Alysis Code Free Tier | DeepSeek V4.1 FlashDeepSeek | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free-allowance table; 50 credits every 30 days shared across models |
| Alysis Code Free Tier | GLM 5.3 FlashOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free-allowance table; shared credit pool |
| Alysis Code Free Tier | GPT-6 LunaGPT | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free-allowance table |
| Google: Gemma 3n 4B (free)Gemma | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free plan model; API call rate unpublished | |
| inclusionAI: Ling 3.0 Flash Fin (free)Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free plan model; API call rate unpublished | |
| Qwen: Qwen3.8 27B (free)Qwen | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free plan: 100K tokens/day, 'Limited API calls' with no figures | |
| Baseten AI Startup Program | GLM-5.3Other | — | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Model API |
| Baseten AI Startup Program | GPT OSS 120BGPT | — | Yes | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Model API |
 fal Startup Program | GPT Image 2GPT | — | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits apply to the fal catalog; no per-model limits published; image generation and editing |
| fal Startup Program | Kling 3.0Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits apply to the fal catalog; no per-model limits published; text/image to video |
| fal Startup Program | Nano Banana 2Other | — | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits apply to the fal catalog; no per-model limits published; image generation and editing |
| fal Startup Program | Nano Banana 2.1Other | — | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits apply to the fal catalog; no per-model limits published; image editing |
| fal Startup Program | Nano Banana ProOther | — | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits apply to the fal catalog; no per-model limits published; image generation and editing |
| fal Startup Program | Seedream 5.0Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits apply to the fal catalog; no per-model limits published; listed under Image Models in the site… |
| fal Startup Program | Veo 3.1Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits apply to the fal catalog; no per-model limits published; listed under Video Models in the site… |
 Fireworks for Startups | DeepSeek V4.1 FlashDeepSeek | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Build Credits auto-apply to Fireworks usage (offer row); listed in the Fireworks model library; limits for program… |
| Fireworks for Startups | GLM 5.2Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Build Credits auto-apply to Fireworks usage (offer row); listed in the Fireworks model library; limits for program… |
| Fireworks for Startups | GLM 5.3 FlashOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Build Credits auto-apply to Fireworks usage (offer row); listed in the Fireworks model library; limits for program… |
| Fireworks for Startups | GLM-5Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Build Credits auto-apply to Fireworks usage (offer row); listed in the Fireworks model library; limits for program… |
| Fireworks for Startups | Kimi K3Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Build Credits auto-apply to Fireworks usage (offer row); listed in the Fireworks model library; limits for program… |
| Fireworks for Startups | Minimax M3Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Build Credits auto-apply to Fireworks usage (offer row); listed in the Fireworks model library; limits for program… |
| Fireworks for Startups | Qwen3.8 Flash NextQwen | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Build Credits auto-apply to Fireworks usage (offer row); listed in the Fireworks model library; limits for program… |
| Fireworks for Startups | Qwen3.8 MaxQwen | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Build Credits auto-apply to Fireworks usage (offer row); listed in the Fireworks model library; limits for program… |
 Google Cloud AI Startup Program | Gemini 2.5 FlashGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits cover Gemini on Vertex AI (offer row); listed in the Vertex AI model catalog; limits for program… |
| Google Cloud AI Startup Program | Gemini 3.5 Flash-LiteGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits cover Gemini on Vertex AI (offer row); listed in the Vertex AI model catalog; limits for program… |
| Google Cloud AI Startup Program | Gemini 3.5 TranscribeGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits cover Gemini on Vertex AI (offer row); listed in the Vertex AI model catalog; limits for program… |
| Google Cloud AI Startup Program | Gemini 3.6 FlashGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits cover Gemini on Vertex AI (offer row); listed in the Vertex AI model catalog; limits for program… |
| Google Cloud AI Startup Program | Gemini 3.8 FlashGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits cover Gemini on Vertex AI (offer row); listed in the Vertex AI model catalog; limits for program… |
| Google Cloud AI Startup Program | Gemini 3.8 LiveGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits cover Gemini on Vertex AI (offer row); listed in the Vertex AI model catalog; limits for program… |
 Google Gemini Developer API Free Tier | Gemini 3.8 LiveGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Live API on the free tier |
| Google Gemini Developer API Free Tier | gemini-2.5-flashGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | 2.5 models limited to users who used them before |
| Google Gemini Developer API Free Tier | gemini-3.1-flash-liteGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free tier; limits unpublished |
| Google Gemini Developer API Free Tier | gemini-3.5-flash-liteGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free tier; recommended for new projects |
| Google Gemini Developer API Free Tier | gemini-3.6-flashGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free of charge on the free tier; limits unpublished |
| Google Gemini Developer API Free Tier | gemini-3.8-flashGemini | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free tier on the pricing page; limits shown only in AI Studio |
 Hume AI Free Tier | EVIOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Speech-to-speech; limits in the API docs |
 Mistral AI Free Plan | CodestralMistral | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Coding model (v25.08) |
| Mistral AI Free Plan | Mistral Large 4Mistral | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free mode limits only in Admin Panel > API > Limits |
| Mistral AI Free Plan | Mistral Small 4Mistral | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Apache 2.0 open model on Studio |
| OpenAI for Startups | gpt-image-2GPT | — | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Program credits are standard API credits; limits follow the org usage tier (program adds upgrades); image generation,… |
 OpenCode Zen Free Models | Beam FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id beam-free; 30-day retention; not available in some countries |
| OpenCode Zen Free Models | Big PickleOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id big-pickle; stealth model, data may be used to improve the model |
| OpenCode Zen Free Models | DeepSeek V4.1 Flash FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id deepseek-v4.1-flash-free; zero-retention provider |
| OpenCode Zen Free Models | Exo FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id exo-free; data may be used to improve the model |
| OpenCode Zen Free Models | GLM-5.3-Flash FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id glm-5.3-flash-free; zero-retention provider |
| OpenCode Zen Free Models | Jev 1.13 FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id jev-1.13-free; classification endpoint, not chat |
| OpenCode Zen Free Models | LL Alpha FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id ll-alpha-free; stealth model, data used to improve it, 30-day retention |
| OpenCode Zen Free Models | LongCat 2.5 Preview FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id longcat-2.5-preview-free; zero-retention provider |
| OpenCode Zen Free Models | MiMo-V2.5 FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id mimo-v2.5-free; limited time |
| OpenCode Zen Free Models | MiMo-V2.6-Flash FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id mimo-v2.6-flash-free; limited time |
| OpenCode Zen Free Models | MiniMax M3.1 Flash FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id minimax-m3.1-flash-free; zero-retention provider |
| OpenCode Zen Free Models | Nemotron 3 Ultra FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id nemotron-3-ultra-free; NVIDIA trial use only, use is logged |
| OpenCode Zen Free Models | Nemotron 3.5 Lightning FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id nemotron-3.5-lightning-free; NVIDIA trial use only, use is logged |
| OpenCode Zen Free Models | Nemotron 3.5 Super VL FreeOther | — | — | — | — | — | — | not published | Card | Verified · Oct 12, 2026 | Model id nemotron-3.5-super-vl-free; NVIDIA trial use only, use is logged |
 Replicate Try for Free | ideogram-ai/ideogram-v3-turboOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Image generation; free for a limited number of runs |
 Runware Startup Program | Nano Banana 2.1Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Image model on the Runware catalog |
| Sarvam AI Startup Program | MayuraOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits cover the Sarvam API stack; limits depend on the account tier; text translation |
| Sarvam AI Startup Program | Saaras v4Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits cover the Sarvam API stack; limits depend on the account tier; speech to text, 23 languages |
| Sarvam AI Startup Program | Sarvam VisionOther | — | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits cover the Sarvam API stack; limits depend on the account tier; document intelligence / OCR |
| Sarvam AI Startup Program | Sarvam-105BOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits cover the Sarvam API stack; limits depend on the account tier; also sarvam-105b-conversations |
| Sarvam AI Startup Program | Sarvam-TranslateOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Startup-program credits cover the Sarvam API stack; limits depend on the account tier; text translation, 23 languages |
 Speechmatics $100 Free Credit | EnhancedOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | STT model; Free tier: $100 credit, 2 concurrent real-time sessions |
| Speechmatics $100 Free Credit | Linden 1Other | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | STT model named on the pricing page |
| Speechmatics $100 Free Credit | StandardOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | STT model; 2 concurrent Realtime sessions on Free |
| Upstage AI Initiative Free Access | Document ParseOther | — | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Limits assigned by commitment tier; table not fetchable |
 YepAPI Free $5 Credit | Nemotron 3 SuperOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | $0.00/M input; no hard limits published |
| Z.AI Free API Tier | GLM-4.5-FlashOther | — | — | — | — | — | — | not published | No card | Verified · Oct 12, 2026 | Priced Free |
| Z.AI Free API Tier | GLM-4.6V-FlashOther | — | — | Yes | — | — | — | not published | No card | Verified · Oct 12, 2026 | Free vision model |
| GLM-4.7-FlashOther | 200k | — | — | — | — | — | not published | No card | Listed · Oct 21, 2026 | Free text model; 128K max output; limits unpublished | |
| GLM-4-Flash-250414Other | 128k | — | — | — | — | — | not published | No card | Listed · Oct 21, 2026 | Free text model; 16K max output; limits unpublished | |
| GLM-4.5-FlashOther | 128k | — | — | — | — | — | not published | No card | Listed · Oct 21, 2026 | Free text model; 96K max output; limits unpublished | |
| GLM-4.6V-FlashOther | 128k | — | Yes | — | — | — | not published | No card | Listed · Oct 21, 2026 | Free vision reasoning model; 32K max output; limits unpublished | |
| GLM-4.1V-Thinking-FlashOther | 64k | — | Yes | — | — | — | not published | No card | Listed · Oct 21, 2026 | Free vision reasoning model; 16K max output; limits unpublished | |
| GLM-4V-FlashOther | 16k | — | Yes | — | — | — | not published | No card | Listed · Oct 21, 2026 | Free image-understanding model; 1K max output; limits unpublished | |
 BytePlus Free Trial | gpt-oss-120bGPT | — | — | — | — | — | — | not published | No card | Listed · Sep 12, 2026 | Listed under ModelArk free tokens; doc-page limits are not free-tier specific |
| BytePlus Free Trial | seed-1.6Other | — | — | — | — | — | — | not published | No card | Listed · Sep 12, 2026 | Listed under ModelArk free tokens |
 Experiential Labs Free Plan | GPT-6 Luna DecisionsGPT | — | — | — | — | — | — | not published | Card | Listed · Sep 10, 2026 | Tagged Free |
| Experiential Labs Free Plan | JevOther | — | — | — | — | — | — | not published | Card | Listed · Sep 10, 2026 | Tagged Free on the models page; no rate limits published |
Compare the nine best-known free tiers side by side on the free LLM APIs comparison, or size a workload with the rate-limit calculator.
Understand it
A few minutes of play-along, no sign-up.
- Why is the mini or flash model the free one? · Knowledge distillation (teacher and student models) · 5 min
- How does it call a function it can’t run? · Tool calling (function calling) · 5 min
Frequently asked questions
- How are the rows ranked?
- By the requests per day the published limits allow: the smallest of requests per day, requests per minute times 1,440, a monthly request cap divided by 30, and (when you give a request size) tokens per minute or per day scaled to a day. A daily token cap appears under the TPM figure and a monthly request cap under the RPD figure. Rows with a published number come first, verified before listed; rows whose vendor publishes no limit come last.
- What does "not published" mean?
- The vendor does not state that limit for its free tier on a page we can cite. aifree.dev never guesses a number, so the cell stays empty and the row is not ranked above rows with real figures. Check the offer page for the vendor link and the notes.
- Why do some rows share one quota?
- Routers such as OpenRouter apply one free-tier cap across every free model, so two rows from the same offer do not add up. The tool never sums models of one offer; the calculator picks the best single model per offer for the same reason.
- Why does Gemini show no numbers?
- Google's rate-limits page no longer publishes free-tier requests per minute or day for the Gemini API, so those cells are empty. The offer remains listed with the models it serves and ranks after rows with published limits.
- How current are the limits?
- Rows come from the same catalog as the offer pages and are re-checked monthly against the vendor page quoted in the offer. When a vendor changes a cap the row updates with the next check; the offer page shows the date of the last one.