Devstral 2 2512
Mistral AI · released Nov 28, 2025 · mistralai/Devstral-2-123B-Instruct-2512
- Type
- Open weightsCustom licence
- Params
- 125B
- Context
- 262K
about 197K words of context · download allowed, licence restricts use
Our take
Written Aug 2, 2026Devstral 2 is a 125-billion-parameter coding specialist from Mistral AI that accepts text and files for web development and code generation tasks. It offers a 262,144-token request limit and has shown stable measured performance on the Arena Code leaderboard, though its custom restricted licence and single-benchmark coverage are notable limitations.
Choose this for code generation where the large request limit fits extensive codebases, if you prefer a dense architecture, and if Mistral's licence terms work for you. Skip it if you need a permissive open licence, measured throughput from multiple providers, or validation across general chat or reasoning benchmarks.
The case for it
- Stable, well-measured code benchmark performance: three consecutive Arena Code evaluations varied by only 0.0293 points.
- Very large request limit for code tasks: 262,144 tokens fits extensive codebases and multi-file projects.
- Identical pricing across both tracked providers.
The case against it
- Custom restricted licence — not Apache 2.0; terms are undisclosed, so redistribution and commercial restrictions are possible.
- No measured throughput on one of two providers; only Mistral direct lists 25 tokens per second.
- Single benchmark coverage with no cross-domain validation: only Arena Code scores available, no general chat or reasoning benchmarks measured.
How good is it?
IntelligencePuzzles, maths, exam questions
Nobody we watch has scored Devstral 2 2512 for this. We would take the rating from Arena Text (overall).
CodingWriting and fixing code on its own
Devstral 2 2512 is not on Arena Coding, which is where the rating would come from, so there is no rating here. It is on Arena Code (WebDev), in 73rd of 74 with 1193.9.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Devstral 2 2512 for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Nobody we watch has scored this model for writing. Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage.
Every published score for this model1 scoreEvery figure we hold, from 1 board, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M1 Ultra (64-core GPU) · 128 GB
Room to spare. 12.9 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.40 in / $2.00 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.40 / $2.00 | 262K | not measured | Unknown | Unknown | Unknown |
| Mistral AI | $0.40 / $2.00 | 262K | 25 tok/s | No | Yes30 days | Unknown |
Mistral AIAcross the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Mistral AI | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 35h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- mistralai/Devstral-2-123B-Instruct-2512
- Architecture
- Dense
- Modality record
- text+file->text
- Catalogue slug
- mistralai-devstral-2-2512