Open source models, served fast.
DeepSeek, Qwen, Gemma and Llama on our infrastructure, behind one API that speaks the OpenAI format.
Response
< 300 ms
4+
99.9%
$0.10
Open models, one catalog
Pick a model by id. Prices are per million tokens.
DeepSeek V3
deepseek-v3
$0.27 / $1.10
Qwen 2.5 72B
qwen-2.5-72b
$0.35 / $0.40
Llama 3.3 70B
llama-3.3-70b
$0.23 / $0.40
Gemma 3 27B
gemma-3-27b
$0.10 / $0.20
Median< 300 ms
Time to first token, measured across the catalog.
Uptime99.9%
Rolling 90-day availability across all regions.
Live throughput
Readings stream as the model warms up.
Tokens per second42
Sustained across a 4K-token reply.
Drop-in OpenAI compatible.
Keep your client and change the base URL.
Built to be trusted
No prompt logging
Requests are not stored or used for training.
Region pinning
Choose where your requests are served.
Uptime target
Models, prices and limits are published in the documentation.
Change the base URL, keep your code.
Point any OpenAI client at infere.dev, pick an open model by its id, and stream the reply. No new SDK.
curl https://api.infere.dev/v1/chat/completions \ -H "Authorization: Bearer $INFERE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-v3", "stream": true, "messages": [{"role": "user", "content": "Explain KV caching in one line."}] }'{ "id": "chatcmpl_8f2a91", "model": "deepseek-v3", "choices": [ { "message": { "role": "assistant", "content": "KV caching stores attention keys and values so each new token reuses past work." }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 14, "completion_tokens": 19 }}