Mistral Medium API — pricing & specs
Mistral AI's balanced mid-tier model for reasoning, coding, and general tasks; the "latest" alias tracks the newest Mistral Medium release. On KeepRouter, Mistral Medium costs $1.50 per 1M input tokens and $7.50 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 mistral-medium-latest.
| Maker | Mistral AI |
|---|---|
| Modality | Text |
| Input price | $1.50 per 1M tokens |
| Output price | $7.50 per 1M tokens |
| Capabilities | Streaming, Tool / function calling |
| APIs | OpenAI-compatible & Anthropic-compatible |
| Model id | mistral-medium-latest |
How pricing works for Mistral Medium
Mistral Medium is billed per token — $1.50 per 1M input tokens and $7.50 per 1M output tokens. As a worked example, a 1,000-token prompt with a 500-token reply costs about $0.0053. All prices are at cost (a 0% markup) with no monthly fee.
Calling Mistral Medium on KeepRouter
Point your OpenAI- or Anthropic-compatible client at KeepRouter, set the model to mistral-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 $KEEPROUTER_KEY" -H "Content-Type: application/json" \
-d '{"model":"mistral-medium-latest","messages":[{"role":"user","content":"Hello"}]}'Python
from openai import OpenAI
client = OpenAI(base_url="https://keeprouter.com/v1", api_key="$KEEPROUTER_KEY")
r = client.chat.completions.create(model="mistral-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: "mistral-medium-latest", messages: [{ role: "user", content: "Hello" }] });Frequently asked questions
How much does Mistral Medium cost on KeepRouter?
Mistral Medium is $1.50 per 1M input tokens and $7.50 per 1M output tokens, billed at cost with no markup and no monthly fee.
How much does a typical Mistral Medium request cost?
On KeepRouter, a 1,000-token prompt with a 500-token reply costs about $0.0053 — billed at cost with no markup.
Who makes Mistral Medium?
Mistral Medium is made by Mistral AI. KeepRouter provides it through one OpenAI- and Anthropic-compatible API.
How do I call Mistral Medium via API?
Point your OpenAI- or Anthropic-compatible client at KeepRouter and set the model to "mistral-medium-latest". It works with the OpenAI SDK, the Anthropic SDK, and Claude Code — no provider-specific SDK needed.
Does Mistral Medium support streaming?
Yes. KeepRouter streams Mistral Medium responses over both the OpenAI and Anthropic APIs.
Does Mistral Medium support tool (function) calling?
Yes. KeepRouter passes tool calls through to Mistral Medium and translates them between the OpenAI and Anthropic formats.
Guides
Related models from Mistral AI
- Codestral — $0.30 per 1M input tokens and $0.90 per 1M output tokens
- 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
All models & pricing · Quickstart · KeepRouter vs OpenRouter · Glossary · Get an API key
Prices as of 2026-07-05.