Coding Router:high API

Nanogpt's Coding Router:high, 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
coding-router:high
Maker
Nanogpt
Context window
1M tokens
Input price
$1.101 per million tokens
Output price
$2.202 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": "coding-router:high",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Coding Router:high?
Coding Router:high is a model from Nanogpt.
How much does Coding Router:high cost?
Offers now ask $1.101 per million input tokens and $2.202 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 Coding Router:high?
The largest offer takes 1,000,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Coding Router:high 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 Coding Router:high support?
Text → Text.
Which providers serve Coding Router:high?
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 Coding Router:high?
Send "coding-router:high" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Coding Router:high listed?
The exchange first listed it on 10/10/2026. This is not its release date.

Related pages