4 providers · 17 free models · Last updated: 01 Nov 2026
Keyless inference endpoints require no API key or account creation. Callable immediately via IP rate-limiting on OVHcloud, Kilo Gateway, and Hugging Face.
Total available in this directory: 4 providers, 17 free models. Verified limits below.
Anonymous IP-based rate limiting without mandatory signup.
Base URL: https://endpoints.ai.cloud.ovh.net/v1
Model: Mistral 7B (Serverless)
Provider: OVHcloud AI Endpointsfrom openai import OpenAI
client = OpenAI(
base_url="https://endpoints.ai.cloud.ovh.net/v1",
api_key="your-api-key", # from OVHcloud AI Endpoints
)
response = client.chat.completions.create(
model="Mistral 7B (Serverless)",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)| Model | Provider | Cost | Context | RPM | TPM | RPD | Day tokens | Verified |
|---|---|---|---|---|---|---|---|---|
| ~80 free models (Llama 3.x/4, Qwen, Gemma, DeepSeek-R1 distills, FLUX, Whisper, BGE embeddings) | Cloudflare Workers AI | $0 | 8K-128K+ (model-dependent) | 300 text gen (720-1,500 other tasks) | Model-dependent | Not published | 10,000 neurons/day | 2026-08-30 |
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | Cloudflare Workers AI | $0 | 128K | 300 | Model-dependent | Not published | 10,000 neurons/day | 2026-10-29 |
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | Cloudflare Workers AI | $0 | 128K | 300 | Model-dependent | Not published | 10,000 neurons/day | 2026-10-29 |
| @cf/qwen/qwen2.5-72b-instruct | Cloudflare Workers AI | $0 | 128K | 300 | Model-dependent | Not published | 10,000 neurons/day | 2026-10-29 |
| @cf/meta/llama-3.1-8b-instruct | Cloudflare Workers AI | $0 | 128K | 300 | Model-dependent | Not published | 10,000 neurons/day | 2026-10-29 |
| Llama 3.2 8B (Serverless) | Hugging Face | $0 | Model-dependent | ~300 req/hour (Serverless) | Model max context | Not published | Small monthly credit pool (PRO: 2M credits/mo) | 2026-10-29 |
| Qwen 2.5 7B (Serverless) | Hugging Face | $0 | Model-dependent | ~300 req/hour (Serverless) | Model max context | Not published | Small monthly credit pool (PRO: 2M credits/mo) | 2026-10-29 |
| Mistral 7B (Serverless) | Hugging Face | $0 | Model-dependent | ~300 req/hour (Serverless) | Model max context | Not published | Small monthly credit pool (PRO: 2M credits/mo) | 2026-10-29 |
| Inference Providers gateway (15+ partners) | Hugging Face | $0 | Model-dependent | ~300 req/hour (Serverless) | Model max context | Not published | Small monthly credit pool (PRO: 2M credits/mo) | 2026-10-29 |
| cohere/north-mini-code:free | Kilo Gateway | $0 | 250K | 20 | Provider-dependent | 200/day | Not published | 2026-11-01 |
| poolside/laguna-s-2.1:free | Kilo Gateway | $0 | 256K | 20 | Provider-dependent | 200/day | Not published | 2026-10-31 |
| poolside/laguna-xs-2.1:free | Kilo Gateway | $0 | 256K | 20 | Provider-dependent | 200/day | Not published | 2026-10-31 |
| liquid/lfm-2.5-2.6b:free | Kilo Gateway | $0 | 64K | 20 | Provider-dependent | 200/day | Not published | 2026-11-01 |
| dots-studio/dots-3-note-preview:free | Kilo Gateway | $0 | 500K | 20 | Provider-dependent | 200/day | Not published | 2026-11-01 |
| nvidia/nemotron-3.5-lightning:free | Kilo Gateway | $0 | 1000000 | 20 | Provider-dependent | 200/day | Not published | 2026-11-01 |
| nvidia/nemotron-3.5-super-vl:free | Kilo Gateway | $0 | 1000000 | 20 | Provider-dependent | 200/day | Not published | 2026-11-01 |
| 10 free models (anonymous keyless) | OVHcloud AI Endpoints | $0 | Model-dependent | 2/min per IP | Not published | Not published | Not published | 2026-11-01 |
Machine-readable: Markdown Twin · providers.json · sitemap.xml