Models / Mistral
Devstral 2 2512 API pricing
$0.60 in, $2.40 out per million tokens.
Price · per million tokens, USD
Get a key| Tokens | Mistral list price | UplinkSwitch | Saving |
|---|---|---|---|
| Input | — | $0.60 | — |
| Cached input | — | $0.00 | — |
| Output | — | $2.40 | — |
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 | |
|---|---|
| Developer | Mistral |
| Parameters | 123B |
| Context | 256k tokens |
| License | a modified MIT license |
| Downloads, 30 days to 2026-10-29 | 5,956 |
| Source | mistralai/Devstral-2-123B-Instruct-2512 |
From mistralai/Devstral-2-123B-Instruct-2512, read 2026-10-29.
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
| Model | Here, in / out | 1,000 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
- Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
- 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.
- Send devstral-2512 as the model. The same key calls every other model in the catalog.
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)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 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.