What is Mistral Medium 3.5 2604?

Mistral Medium 3.5 2604 is a model from Mistral, released on Apr 28, 2026. Mistral Medium 3 5 is a Mistral AI model for coding, reasoning, instruction following, or multimodal language tasks.

How much does Mistral Medium 3.5 2604 cost?

On the Respan gateway, Mistral Medium 3.5 2604 costs $1.50 per 1M input tokens and $7.50 per 1M output tokens on Mistral, after gateway discounts.

Which providers serve Mistral Medium 3.5 2604 on Respan?

Mistral Medium 3.5 2604 is served by Mistral.

What is Mistral Medium 3.5 2604's context window?

Mistral Medium 3.5 2604 accepts up to 262K tokens of context.

How do I use Mistral Medium 3.5 2604 with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "mistral/mistral-medium-2604". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Where does Mistral Medium 3.5 2604 rank on the Respan Index?

Mistral Medium 3.5 2604 scores 26.6 out of 100 on the Respan Index v1.1, ranking #94 of 161 models. By category: Coding 7.1, Agents 43.7, Reasoning 20.5, Knowledge & language 17.7 (estimated), and Human preference 46.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

How does Mistral Medium 3.5 2604 score on benchmarks?

Mistral Medium 3.5 2604 has 9 published benchmark scores, including SWE-bench Verified 77.6%, Tau3 Telecom 91.4, and LMArena Elo 1426. Each score links to where it was published; the data is collected by Respan.

Mistral Medium 3.5 2604

Mistral Medium 3 5 is a Mistral AI model for coding, reasoning, instruction following, or multimodal language tasks.

Input / output price: $1.50 / $7.50 per 1M
Context: 262K tokens
Released: Apr 28, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "mistral/mistral-medium-2604".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="mistral/mistral-medium-2604",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "mistral/mistral-medium-2604",

  messages: [{ role: "user", content: "Hello!" }],

});

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

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "mistral/mistral-medium-2604",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
Mistral`mistral/mistral-medium-2604`	262K	$1.50/M	$7.50/M	$0.15/M

Is a provider down? Mistral AI status

Pricing

USD per 1M tokens on Mistral, after gateway discounts.

Input: $1.50 per 1M
Output: $7.50 per 1M
Cache read: $0.15 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$1.50/MMistral

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

8.9tokens/sacross providers

Faster than 10% of the other 472 models on the gateway

Response latency

Lower is better

0.3sacross providers

Faster than 94% of the other 498 models on the gateway

Benchmarks

The Respan Index plus 9 published scores from 4 sources, each linked to where it was published.

26.6/ 100

Respan Index#94 of 161

161 ranked models. The shaded band is this model's 95% interval, 21.0 to 42.9. MiniMax M2.7 and Step 3.5 Flash fall inside it, so the gap is within the margin of error.

94Mistral Medium 3.526.6
92MiniMax M2.727.0
95Step 3.5 Flash26.5

Published scores

Benchmark	Score	Source	Published
SWE-bench VerifiedMistral	77.6%	Mistral	May 22, 2026
WeirdMLHåvard Tveit Ihle	43.7%	Håvard Tveit Ihle	Oct 5, 2026

Benchmark	Score	Source	Published
Tau3 TelecomMistral	91.4	Mistral	May 22, 2026

Benchmark	Score	Source	Published
LMArena EloLMArena	1426 Elo · #84 of 163	LMArena	Oct 28, 2026
LMArena WebDevLMArena	1264 Elo · #102 of 113	LMArena	Oct 28, 2026
LMArena VisionLMArena	1200 Elo · #71 of 87	LMArena	Oct 19, 2026
LMArena AgentLMArena	-0.1265 · #54 of 59	LMArena	Oct 28, 2026