MistralCertifiedReleased 05/29/2024

Mistral Codestral

Mistral's cutting-edge language model for coding released end of July 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.

View API reference ↓
Input / output priceFrom$0.30 / $0.90per 1M
24h uptime100.00%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "mistral/codestral",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
Mistral128K4K0.3 s—$0.30$0.90Read $0.030Write —2 featuresYesYesGlobalCertified

Uptime

24 hours

Request success rate per provider.

Mistral100.00%

Throughput

last hour

P50 output tokens per second.

Mistral—

Latency

last hour

P50 time to first token.

Mistral0.3 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "mistral/codestral",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. mistral/codestral. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. Mistral Codestral supports up to 4,000 output tokens.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choiceresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 128K-token context window

More models by Mistral

ModelContextInputOutputCacheRelease
mistral/mistral-large-41.05M$0.70$2.10Read $0.070Write —10/29/2026
mistral/mistral-medium-3.5262K$1.50$7.50Read $0.15Write —04/29/2026
mistral/ministral-14b262K$0.20$0.20Read $0.020Write —12/02/2025
mistral/mistral-large-3262K$0.50$1.50Read $0.050Write —12/02/2025
mistral/ministral-3b131K$0.100$0.100Read $0.010Write —10/16/2024
mistral/ministral-8b262K$0.15$0.15Read $0.015Write —10/16/2024
mistral/mistral-small262K$0.15$0.60Read $0.015Write —09/17/2024
mistral/mistral-nemo131K$0.029$0.030Read —Write —07/18/2024