O1 Mini API

OpenAI's O1 Mini, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send o1-mini as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: o1-mini
Maker: OpenAI
Context window: 128K tokens
Input price: $1.209 per million tokens
Output price: $4.836 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $1.209 input and $4.836 output per million tokens, $0.605 cache read per million tokens, 128K tokens of context

Scores

HLE: 3.6, #255 of 273
GPQA: 60.3, #177 of 250
LiveCodeBench: 57.6, #48 of 130
MMLU-Pro: 74.2, #78 of 133

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "o1-mini",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is O1 Mini?: O1 Mini is a model from OpenAI.
How much does O1 Mini cost?: Offers now ask $1.209 per million input tokens and $4.836 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of O1 Mini?: The largest offer takes 128,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can O1 Mini do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does O1 Mini support?: Text → Text.
Which providers serve O1 Mini?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call O1 Mini?: Send "o1-mini" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was O1 Mini listed?: The exchange first listed it on 10/10/2026. This is not its release date.