Devstral Medium API — pricing & specs

Mistral AI's Devstral — tuned for agentic software-engineering and coding-agent workflows; the medium tier, tracking the newest release. On KeepRouter, Devstral Medium costs $0.40 per 1M input tokens and $2 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 devstral-medium-latest.

MakerMistral AI
ModalityText
Input price$0.40 per 1M tokens
Output price$2 per 1M tokens
CapabilitiesStreaming, Tool / function calling
APIsOpenAI-compatible & Anthropic-compatible
Model iddevstral-medium-latest

How pricing works for Devstral Medium

Devstral Medium is billed per token — $0.40 per 1M input tokens and $2 per 1M output tokens. As a worked example, a 1,000-token prompt with a 500-token reply costs about $0.0014. All prices are at cost (a 0% markup) with no monthly fee.

Calling Devstral Medium on KeepRouter

Point your OpenAI- or Anthropic-compatible client at KeepRouter, set the model to devstral-medium-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":"devstral-medium-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="devstral-medium-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: "devstral-medium-latest", messages: [{ role: "user", content: "Hello" }] });

Frequently asked questions

How much does Devstral Medium cost on KeepRouter?

Devstral Medium is $0.40 per 1M input tokens and $2 per 1M output tokens, billed at cost with no markup and no monthly fee.

How much does a typical Devstral Medium request cost?

On KeepRouter, a 1,000-token prompt with a 500-token reply costs about $0.0014 — billed at cost with no markup.

Who makes Devstral Medium?

Devstral Medium is made by Mistral AI. KeepRouter provides it through one OpenAI- and Anthropic-compatible API.

How do I call Devstral Medium via API?

Point your OpenAI- or Anthropic-compatible client at KeepRouter and set the model to "devstral-medium-latest". It works with the OpenAI SDK, the Anthropic SDK, and Claude Code — no provider-specific SDK needed.

Does Devstral Medium support streaming?

Yes. KeepRouter streams Devstral Medium responses over both the OpenAI and Anthropic APIs.

Does Devstral Medium support tool (function) calling?

Yes. KeepRouter passes tool calls through to Devstral Medium and translates them between the OpenAI and Anthropic formats.

Guides

Related models from Mistral AI

All models & pricing · Quickstart · KeepRouter vs OpenRouter · Glossary · Get an API key

Prices as of 2026-07-05.