How much does Mistral Small 2603 cost?

On the Respan gateway, Mistral Small 2603 costs $0.15 per 1M input tokens and $0.60 per 1M output tokens on every provider, after gateway discounts.

Which providers serve Mistral Small 2603 on Respan?

Mistral Small 2603 is available through 2 providers: Mistral and OpenRouter.

What is Mistral Small 2603's context window?

Mistral Small 2603 accepts up to 262K tokens of context on its largest provider route.

How do I use Mistral Small 2603 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-small-2603". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How does Mistral Small 2603 score on benchmarks?

Mistral Small 2603 has 4 published benchmark scores, including GPQA Diamond 71.2%, MMLU-Pro 78%, and SAGE 1.1 59.2%. Each score links to where it was published; the data is collected by Respan.

Mistral Small 2603

Q: What is Mistral Small 2603?

Mistral Small 2603 is a model from Mistral, released on Mar 16, 2026. The mistral-small model is a cost-efficient reasoning model designed for low-latency workloads. It leverages the Mixtral-8X7B-v0.1 architecture, which incorporates a sparse mixture of experts with 12B active parameters. With improved reasoning capabilities, the model demonstrates a broad range of functionalities, including code generation and reasoning. It also supports multiple languages such as English, French, German, Italian, and Spanish, making it a versatile option for various linguistic tasks.

The mistral-small model is a cost-efficient reasoning model designed for low-latency workloads. It leverages the Mixtral-8X7B-v0.1 architecture, which incorporates a sparse mixture of experts with 12B active parameters. With improved reasoning capabilities, the model demonstrates a broad range of functionalities, including code generation and reasoning. It also supports multiple languages such as English, French, German, Italian, and Spanish, making it a versatile option for various linguistic tasks.

Input / output price: $0.15 / $0.60 per 1M
Context: 262K tokens
Released: Mar 16, 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-small-2603".

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-small-2603",

    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-small-2603",

  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-small-2603",

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

}'

Read docs

Providers

2 providers, cheapest first, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
Mistral`mistral/mistral-small-2603`	262K	$0.15/M	$0.60/M	$0.01/M
OpenRouter`openrouter/mistralai/mistral-small-2603`	262K	$0.15/M	$0.60/M	$0.01/M

Is a provider down? Mistral AI status, OpenRouter status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input: $0.15 per 1M
Average output: $0.60 per 1M
Average cache read: $0.01 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.15/MMistral and OpenRouter

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

33tokens/sacross providers

Faster than 44% of the other 472 models on the gateway

Response latency

Lower is better

0.6sacross providers

Faster than 89% of the other 498 models on the gateway

Benchmarks

4 published scores from 3 sources, each linked to where it was published.

Published scores

Benchmark	Score	Source	Published
GPQA Diamondhuggingface.co	71.2%	huggingface.co	Mar 16, 2026
Artificial Analysis Long Context ReasoningMistral	0.72	Mistral	Mar 16, 2026

Benchmark	Score	Source	Published
MMLU-Prohuggingface.co	78%	huggingface.co	Mar 16, 2026

Benchmark	Score	Source	Published
SAGE 1.1Vals AI	59.2%	Vals AI	Oct 31, 2026

Apps

Use Mistral Small 2603 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.