Codestral 2508 API

Mistral's Codestral 2508, 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 codestral-2508 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: codestral-2508
Maker: Mistral
Context window: 256K tokens
Input price: $0.301 per million tokens
Output price: $0.902 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.301 input and $0.902 output per million tokens, $0.301 cache read per million tokens, 256K tokens of context

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "codestral-2508",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Codestral 2508?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Codestral 2508 cost?: Offers now ask $0.301 per million input tokens and $0.902 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 Codestral 2508?: The largest offer takes 256,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Codestral 2508 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 Codestral 2508 support?: Text → Text.
Which providers serve Codestral 2508?: 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 Codestral 2508?: Send "codestral-2508" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Codestral 2508 listed?: The exchange first listed it on 10/8/2026. This is not its release date.

Codestral 2508 API

Facts

Providers

Request

Questions

Related pages