Models / Mistral

Devstral 2 2512 API pricing

$0.60 in, $2.40 out per million tokens.

devstral-2512managed routeOpenAI SDK

Price · per million tokens, USD

Get a key
TokensMistral list priceUplinkSwitchSaving
Input—$0.60—
Cached input—$0.00—
Output—$2.40—
No list price on record. Prices read from the live catalog on 2026-11-16; the page follows the catalog.
Real-model check: Steady since Oct 29

Devstral 2 2512 specs

Context window
262,144 tokens

Devstral 2 2512: what it is · from Mistral’s own model card, read 2026-10-29

Mistral AI’s Devstral 2, an agentic model for software engineering. Its card says it uses tools to explore codebases, edits multiple files and powers software-engineering agents; this is the FP8 instruct model, tuned to follow instructions for chat and agentic coding. It is served as devstral-2512 at $0.60 input and $2.40 output per million tokens, on the same key as every other model in the catalog.

Devstral 2 2512
DeveloperMistral
Parameters123B
Context256k tokens
Licensea modified MIT license
Downloads, 30 days to 2026-10-295,956
Sourcemistralai/Devstral-2-123B-Instruct-2512

From mistralai/Devstral-2-123B-Instruct-2512, read 2026-10-29.

curl
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"devstral-2512","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

Devstral 2 2512 next to Mistral’s other models · per million tokens, live

ModelHere, in / out1,000 chat turns
Ministral 14B 2512$0.20 / $0.20$0.50
Devstral 2 2512$0.60 / $2.40$2.40

A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.

Worked for Devstral 2 2512: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.60 input and $2.40 output per million tokens, that is $1.20 + $1.20 = $2.40, paid from prepaid credit with no subscription.

Devstral 2 2512 API key · base URL and setup

  1. Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
  2. Point your SDK or tool at https://api.uplinkswitch.com/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
  3. Send devstral-2512 as the model. The same key calls every other model in the catalog.
Python · OpenAI SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uplinkswitch.com/v1",
    api_key="sk-uplink-live-...",
)

completion = client.chat.completions.create(
    model="devstral-2512",
    messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)
TypeScript · OpenAI SDK
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.uplinkswitch.com/v1',
  apiKey: 'sk-uplink-live-...',
});

const completion = await client.chat.completions.create({
  model: 'devstral-2512',
  messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);
curl
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"devstral-2512","messages":[{"role":"user","content":"Hello"}]}'

What would it cost? · paste a prompt, priced before you send it

Input is counted at about 4 characters per token.

Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.

Devstral 2 2512 questions

Devstral 2 2512 is a model from Mistral, with a 262,144-token context window. Through UplinkSwitch it answers the OpenAI SDK on one key as devstral-2512.

$0.60 per million input tokens and $2.40 per million output tokens, with cached input at $0.00.

It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0018.

Devstral 2 2512 has a 262,144-token context window.

devstral-2512. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.

Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls Devstral 2 2512 and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.

Every day each model gets the same test prompt, and the results are public on /proof. Devstral 2 2512's latest result: Steady since Oct 29.

Yes: devstral-2512 on the OpenAI format at https://api.uplinkswitch.com/v1, $0.60 input and $2.40 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.

123B, per mistralai/Devstral-2-123B-Instruct-2512.

256k tokens, per mistralai/Devstral-2-123B-Instruct-2512.

Its weights are open on Hugging Face (mistralai/Devstral-2-123B-Instruct-2512); the license is a modified MIT license.

$0.24 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.60 input and $2.40 output per million tokens, from prepaid credit with no subscription.
Join on Telegram