Pareto 26.9 API

Unbiased's Pareto 26.9, 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.

Facts

Model name
pareto-26.9
Maker
Unbiased
Context window
262.1K tokens
Input price
$2.496 per million tokens
Output price
$7.487 per million tokens
Providers
1 independent provider
Regions
us

Providers

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "pareto-26.9",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Pareto 26.9?
Pareto 26.9 is a model from Unbiased.
How much does Pareto 26.9 cost?
Offers now ask $2.496 per million input tokens and $7.487 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 Pareto 26.9?
The largest offer takes 262,144 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Pareto 26.9 do?
Its providers list 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 Pareto 26.9 support?
Text · Images → Text.
Which providers serve Pareto 26.9?
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 Pareto 26.9?
Send "pareto-26.9" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Pareto 26.9 listed?
The exchange first listed it on 10/14/2026. This is not its release date.

Related pages