Codestral 2

mistralai/codestral-2

by Mistral·Text·256K context·Released 2026-01-19·Mistral Commercial

code

Overview

Mistral's dedicated code model. Fill-in-the-middle completion, low-latency IDE autocomplete, dozens of languages. Cheap and fast for quick code tasks. Not a general chat model; use it when the workload is specifically coding.

Benchmarks

Standardized scores (0–100), normalized across the catalog.

Intelligence68

Coding85

Instruction following82

Providers

LLMRouteHub routes to the cheapest healthy provider by default.

Provider	Input	Output	Throughput	Uptime
Lambda	$0.33	$0.99	146 tok/s	99.5%
Hyperbolic	$0.35	$1.06	136 tok/s	99.4%
Parasail	$0.42	$1.27	126 tok/s	99.2%
DeepInfra	$0.49	$1.48	115 tok/s	99.1%

Use this model

curl https://llmroutehub.com/api/v1/chat/completions \
  -H "Authorization: Bearer $LLMROUTEHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/codestral-2",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'