Codestral API — pricing & specs
Mistral AI's Codestral — a model specialized for code generation and completion, including fill-in-the-middle; the "latest" alias tracks the newest release. On KeepRouter, Codestral costs $0.30 per 1M input tokens and $0.90 per 1M output tokens, billed at cost with no markup and no monthly fee. Call it through the OpenAI- or Anthropic-compatible API with the model id codestral-latest.
| Maker | Mistral AI |
|---|---|
| Modality | Text |
| Input price | $0.30 per 1M tokens |
| Output price | $0.90 per 1M tokens |
| Capabilities | Streaming, Tool / function calling |
| APIs | OpenAI-compatible & Anthropic-compatible |
| Model id | codestral-latest |
How pricing works for Codestral
Codestral is billed per token — $0.30 per 1M input tokens and $0.90 per 1M output tokens. As a worked example, a 1,000-token prompt with a 500-token reply costs about $0.0008. All prices are at cost (a 0% markup) with no monthly fee.
Calling Codestral on KeepRouter
Point your OpenAI- or Anthropic-compatible client at KeepRouter, set the model to codestral-latest, and keep the rest of your code unchanged. Streaming and tool calling work over both APIs.
cURL
curl https://keeprouter.com/v1/chat/completions \
-H "Authorization: Bearer $KEEPROUTER_KEY" -H "Content-Type: application/json" \
-d '{"model":"codestral-latest","messages":[{"role":"user","content":"Hello"}]}'Python
from openai import OpenAI
client = OpenAI(base_url="https://keeprouter.com/v1", api_key="$KEEPROUTER_KEY")
r = client.chat.completions.create(model="codestral-latest", messages=[{"role":"user","content":"Hello"}])JavaScript
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://keeprouter.com/v1", apiKey: process.env.KEEPROUTER_KEY });
const r = await client.chat.completions.create({ model: "codestral-latest", messages: [{ role: "user", content: "Hello" }] });Frequently asked questions
How much does Codestral cost on KeepRouter?
Codestral is $0.30 per 1M input tokens and $0.90 per 1M output tokens, billed at cost with no markup and no monthly fee.
How much does a typical Codestral request cost?
On KeepRouter, a 1,000-token prompt with a 500-token reply costs about $0.0008 — billed at cost with no markup.
Who makes Codestral?
Codestral is made by Mistral AI. KeepRouter provides it through one OpenAI- and Anthropic-compatible API.
How do I call Codestral via API?
Point your OpenAI- or Anthropic-compatible client at KeepRouter and set the model to "codestral-latest". It works with the OpenAI SDK, the Anthropic SDK, and Claude Code — no provider-specific SDK needed.
Does Codestral support streaming?
Yes. KeepRouter streams Codestral responses over both the OpenAI and Anthropic APIs.
Does Codestral support tool (function) calling?
Yes. KeepRouter passes tool calls through to Codestral and translates them between the OpenAI and Anthropic formats.
Guides
Related models from Mistral AI
- Devstral Medium — $0.40 per 1M input tokens and $2 per 1M output tokens
- Magistral Medium — $2 per 1M input tokens and $5 per 1M output tokens
- Magistral Small — $0.50 per 1M input tokens and $1.50 per 1M output tokens
- Ministral 14B — $0.20 per 1M input tokens and $0.20 per 1M output tokens
- Ministral 3B — $0.10 per 1M input tokens and $0.10 per 1M output tokens
- Ministral 8B — $0.15 per 1M input tokens and $0.15 per 1M output tokens
All models & pricing · Quickstart · KeepRouter vs OpenRouter · Glossary · Get an API key
Prices as of 2026-07-05.