Inference APIs with no card and no phone
Usable model-inference endpoints, in the inference topic or categorised as inference elsewhere, whose stated identity needs neither a card nor a phone.
| # | offer | badges | |
|---|---|---|---|
| 1 | OVHcloud AI Endpoints (anonymous tier) no key required; 22 model ids on /v1/models, each carrying a pricing object in USD per token. Twelve of the 22 are chat models and two of those, Qwen3Guard-G... | ★ qualifiesanonymousno cardMrequest-rate | |
| 2 | AI Horde Text and image generation on volunteer GPUs, free, with no account: the README says use API key '0000000000' for anonymous usage, with 'No need to register',... | caveatanonymousno cardDrequest-rate | |
| 3 | Atlas Cloud open Reported tiers for maintainers of public, OSI-licensed projects: Starter at USD 50 to 150 per month for 3 months at roughly 100 to 1,000 stars, Growth at USD... | caveatemailno cardRwrite-gated | |
| 4 | Cartesia Free plan at USD 0 with '20K credits / month' plus '$1 prepaid agents / month'. The plan table converts that for you: Sonic-3.6 text to speech gets '~27' min... | caveatemailno cardDvolume-quota | |
| 5 | Cloudflare Workers AI A perpetual daily allowance of 10,000 Neurons on the Workers Free plan: 'Our free allocation allows anyone to use a total of 10,000 Neurons per day at no cha... | caveatemailno cardDrequest-rate | |
| 6 | Cohere trial keys A trial key is free and covers every model and endpoint, and is capped at '1,000 API calls a month' across the account, with Chat at 20 requests a minute per... | caveatemailno cardDrequest-rate | |
| 7 | Deepgram 'Free $200 Credit' with 'No minimums. No expiration. No credit card required.' on the pricing page; the terms state 'Credits expire upon the closing or termi... | caveatemailno cardDrequest-rate | |
| 8 | ElevenLabs Free plan at USD 0 with '10k credits per month'. One shared monthly pool across every product, with the vendor's own per-product rates: 'Text to Speech 1 cre... | caveatemailno cardDvolume-quota | |
| 9 | Gladia 'New accounts get EUR 50 in free credits, valid for one year. That's roughly 312 hours of async transcription on solaria-3, 185 hours on solaria-1, or 73 hou... | caveatemailno cardDretention-clamped | |
| 10 | Google Gemini API The free tier still exists and the pricing page still prints 'Free of charge' against input, output and caching for Gemini 3.8 Flash, 2.5 Flash-Lite and a do... | caveatemailno cardDrequest-rate | |
| 11 | Groq Cloud A free plan per model, printed as RPM / RPD / TPM / TPD: openai/gpt-oss-120b and openai/gpt-oss-20b at 30 requests a minute, 1,000 a day, 8,000 tokens a minu... | caveatemailno cardDrequest-rate | |
| 12 | Inference.net The Kuzco GPU network, now trading as Inference.net. Pay-as-you-go starts at $0 with '1M included Gateway requests', 1M tracing spans, 14-day data retention,... | caveatemailno cardDrequest-rate | |
| 13 | Leonardo.Ai Free plan at USD 0 a month with 'Fast Tokens 150 / day', 'Model Access Auto Only', 'Creations access Public', 'Quality settings Basic', 'Personal collections... | caveatemailno cardDrequest-rate | |
| 14 | Nineteen AI Bittensor subnet 19 (Rayon Labs) advertises Llama 3.1 8B at 'Less Than $0.00 / M Tokens', footnoted 'currently'. The app exposes an API key page and an OpenA... | caveatemailno cardDrequest-rate | |
| 15 | Nomic a Free plan that needs no card: 'No credit card required', 'Limited agent requests', 'Access to core Platform surfaces'. Paid tiers are Individual at USD 20 ... | caveatemailno cardDrequest-rate | |
| 16 | OpenAI Codex Quoted: 'Open-source maintainers can apply for API credits, six months of ChatGPT Pro with Codex, and Codex Security', and 'Over the past year, the Codex Ope... | caveatemailno cardDwrite-gated | |
| 17 | OpenRouter Free-model requests are capped by a table keyed on lifetime credits purchased, not on account age: 'Less than 10' credits in all time gives 20 requests a min... | caveatemailno cardDrequest-rate | |
| 18 | Recraft A Free plan exists and is described in the vendor's own FAQ: 'Images generated on the Free plan are owned by Recraft. They are publicly visible in the commun... | caveatemailno cardRrequest-rate | |
| 19 | Speechmatics 'Start with $100 in free credits, no card required', with the page data carrying 'signupCredits: 100' and a footnote 'No card required'. The headline 'from $... | caveatemailno cardDrequest-rate | |
| 20 | Suno Free plan at USD 0: the vendor's own help centre states 'The Free plan offers 50 credits that replenish daily. This is enough to make 10 songs per day', and ... | caveatemailno cardDrequest-rate | |
| 21 | Z.ai GLM Flash Two models are priced Free on every column of the official pricing table, with no credit and no trial window: GLM-4.7-Flash and GLM-4.5-Flash, both 'Free | F... | caveatemailno cardDrequest-rate | |
| 22 | BlockRun 7 of 117 model ids on /v1/models carry an input price of 0; the rest carry list prices spanning openai, google, anthropic, xai, zai, bytedance, deepseek, qwe... | caveatanonymousno cardMrequest-rate | |
| 23 | Cloudflare Workers AI 10,000 Neurons per day at no charge on both the Free and the Paid Workers plan. The page states the daily figure; the monthly figure of 300,000 and the token... | caveatemailno cardDrequest-rate | |
| 24 | free.ai 513 model entries in /v1/models, 45 of them marked self_hosted true; every id probed answers from one backend, Qwen/Qwen3-30B-A3B-Instruct | caveatanonymousno cardM | |
| 25 | Google Gemini API gemini-3.8-flash is 'Free of charge' for input and output on the Free Tier | caveatemailno cardDrequest-rate | |
| 26 | Groq a Free Plan per model, printed as RPM / RPD / TPM / TPD in the page's own units: openai/gpt-oss-120b and openai/gpt-oss-20b at 30 / 1K / 8K / 200K, qwen/qwen... | caveatemailno cardDrequest-rate | |
| 27 | Kilo Gateway 14 of the 401 ids in the catalogue end in ':free' and require no key; three more are free without the suffix (reflection/beam-free, kilo-auto/free, openroute... | caveatanonymousno cardMrequest-rate | |
| 28 | LLM7 no key required for the ids probed; /v1/models lists 68 ids, none with a zero price | caveatanonymousno cardMrequest-rate | |
| 29 | Mistral La Plateforme a free API tier exists: 'We offer various tiers on the platform, including a free API tier with restrictive rate limits. The free API tier is designed to all... | caveatemailno cardDrequest-rate | |
| 30 | OpenRouter :free model ids free-model request caps stated for model IDs ending in :free, selected by all-time credits purchased | caveatemailno cardDrequest-rate | |
| 31 | Pollinations the Classic API lists one model, openai-fast, described as 'GPT-OSS 20B Reasoning LLM (OVH)', with aliases openai, gpt-oss, gpt-oss-20b and ovh-reasoning | caveatanonymousno cardMrequest-rate |
The query
SELECT rid, vorder FROM record WHERE (topic='inference' OR category LIKE '%inference%') AND grp='usable' AND needs_card=0 AND needs_phone=0 AND identity_basis='stated' AND duplicate_of IS NULL ORDER BY vorder ASC NULLS LAST
Run it yourself: /api/v1/need/inference-no-card-no-phone, the MCP tool need, or fr need inference-no-card-no-phone.