O1 API

OpenAI's O1, 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 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
Maker: OpenAI
Context window: 200K tokens
Input price: $14.984 per million tokens
Output price: $59.937 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $14.984 input and $59.937 output per million tokens, $7.492 cache read per million tokens, 200K tokens of context

Scores

HLE: 7.0, #180 of 273
GPQA: 74.7, #135 of 250
AA-LCR: 65.0, #133 of 237
Terminal-Bench Hard: 12.9, #116 of 166
LiveCodeBench: 67.9, #31 of 130
MMLU-Pro: 84.1, #21 of 133
τ²-Bench: 62.6, #89 of 169
IFBench: 70.3, #39 of 178

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",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is O1?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does O1 cost?: Offers now ask $14.984 per million input tokens and $59.937 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?: The largest offer takes 200,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can O1 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 support?: Text → Text.
Which providers serve O1?: 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?: Send "o1" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was O1 listed?: The exchange first listed it on 10/8/2026. This is not its release date.