How much does Devstral 2512 cost?

On the Respan gateway, Devstral 2512 costs $0.40 per 1M input tokens and $2.00 per 1M output tokens on OpenRouter, after gateway discounts.

Which providers serve Devstral 2512 on Respan?

Devstral 2512 is served by OpenRouter.

What is Devstral 2512's context window?

Devstral 2512 accepts up to 262K tokens of context.

How do I use Devstral 2512 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 "devstral-2512". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How does Devstral 2512 score on benchmarks?

Devstral 2512 has 4 published benchmark scores, including SWE-bench Verified 72.2% and LMArena WebDev 1197. Each score links to where it was published; the data is collected by Respan.

Devstral 2512

Q: What is Devstral 2512?

Devstral 2512 is a model from Mistral, released on Dec 9, 2025. Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring codebases and orchestrating changes across multiple files while maintaining architecture-level context. It tracks framework dependencies, detects failures, and retries with corrections—solving challenges like bug fixing and modernizing legacy systems. The model can be fine-tuned to prioritize specific languages or optimize for large enterprise codebases. It is available under a modified MIT license.

Input / output price: $0.40 / $2.00 per 1M
Context: 262K tokens
Released: Dec 9, 2025

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 "devstral-2512".

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="devstral-2512",

    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: "devstral-2512",

  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": "devstral-2512",

    "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
OpenRouter`openrouter/mistralai/devstral-2512`	262K	$0.40/M	$2.00/M	$0.04/M

Is a provider down? OpenRouter status

Pricing

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

Input: $0.40 per 1M
Output: $2.00 per 1M
Cache read: $0.04 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.40/MOpenRouter

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

18tokens/sacross providers

Faster than 27% of the other 472 models on the gateway

Response latency

Lower is better

1.5sacross providers

Faster than 67% of the other 498 models on the gateway

Benchmarks

4 published scores from 2 sources, each linked to where it was published.

Published scores

Benchmark	Score	Source	Published
SWE-bench Verifiedhuggingface.co	72.2%	huggingface.co	Dec 9, 2025
SWE-bench Multilingualhuggingface.co	61.3%	huggingface.co	Dec 9, 2025
Terminal Bench 2huggingface.co	32.6%	huggingface.co	Dec 9, 2025