Coding Router API

Nanogpt's Coding Router, 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
Maker
Nanogpt
Context window
1M tokens
Input price
$1.100 per million tokens
Output price
$2.199 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",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Coding Router?
Coding Router is a model from Nanogpt.
How much does Coding Router cost?
Offers now ask $1.100 per million input tokens and $2.199 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?
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 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 support?
Text → Text.
Which providers serve Coding Router?
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?
Send "coding-router" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Coding Router listed?
The exchange first listed it on 10/10/2026. This is not its release date.

Related pages