GPT 4o API

OpenAI's GPT 4o, 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 gpt-4o 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: gpt-4o
Maker: OpenAI
Context window: 128K tokens
Input price: $2.496 per million tokens
Output price: $9.985 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $2.496 input and $9.985 output per million tokens, $1.248 cache read per million tokens, 128K tokens of context

Scores

HLE: 2.4, #270 of 273
GPQA: 54.3, #200 of 250
AA-LCR: 49.3, #164 of 237
Terminal-Bench Hard: 8.3, #121 of 166
LiveCodeBench: 30.9, #86 of 130
AIME 2025: 6.0, #95 of 100
MMLU-Pro: 74.8, #73 of 133
τ²-Bench: 25.1, #143 of 169
IFBench: 34.3, #147 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": "gpt-4o",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is GPT 4o?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does GPT 4o cost?: Offers now ask $2.496 per million input tokens and $9.985 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 GPT 4o?: 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 GPT 4o do?: Its providers list Documents, Vision, 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 GPT 4o support?: Text · Files · Images → Text.
Which providers serve GPT 4o?: 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 GPT 4o?: Send "gpt-4o" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was GPT 4o listed?: The exchange first listed it on 10/8/2026. This is not its release date.