Devstral 2
by Mistral AIChat
Mistral's coding-agent model for repository work, terminal tasks, and software fixes
- Context
- 262K tokens
- Max output
- 209,715 tokens
- Parameters
- 125B total
- Released
- 2025-12-09
- Weights
- Open
mistral/devstral-2512 · also seen as mistral.devstral-2-123b, devstral-2, Devstral-2-123B-Instruct-2512-int4-AutoRound, mistralai/devstral-2512, +2 more
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2025-12-09
- Weights
- Opennot gated
- Input
- Text
- Output
- Text
- Context window
- 262,144 max across endpoints
- Max output
- 209,715
- Providers
- 6 + 11 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.400–$0.605 in · $2.00–$3.03 out per 1M tokens · 4 of 6 providers have a comparable price
More details
- Last updated
- 2025-12-09
- Knowledge cutoff
- 2025-12
- Weights link
- Hugging Face · mistralai/Devstral-2-123B-Instruct-2512
- Parameters
- 125B total
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.40 in / $2.00 out per 1M tokens at Amazon Bedrock on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Devstral 2 |
|---|---|---|---|---|---|
| mistral-small-4-119b-2603Mistral AI | $0.567 | $0.40 | $1.40 | 262K | +0% |
| ERNIE 4.5 VL 424B A47BBaidu | $0.558 | $0.42 | $1.25 | 123K | −1% cheaper |
| Inkling SmallThinking Machines | $0.575 | $0.45 | $1.20 | 1.05M | +1% |
| Llama 3 70B InstructMeta | $0.548 | $0.51 | $0.74 | 8.2K | −3% cheaper |
| Seed 2.1 TurboByteDance Seed | $0.59 | $0.354 | $1.77 | 262K | +4% |
| Qwen3.6 27BAlibaba (Qwen) | $0.543 | $0.203 | $2.24 | 262K | −4% cheaper |
| Seed 2.0 LiteByteDance Seed | $0.542 | $0.25 | $2.00 | 131K | −4% cheaper |
| Seed 1.6ByteDance Seed | $0.542 | $0.25 | $2.00 | 256K | −4% cheaper |
More from Mistral AI
Newest Mistral AI models in the catalogue. All Mistral AI models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Mistral Large 4 | 2026-10-06 | 1.05M | from $0.68 |
| Voxtral Small 24B 2507 STT | 2026-08-13 | — | unpriced |
| Leanstral 1.5 | 2026-06-30 | 262K | unpriced |
| Mistral Code Latest | 2026-06-02 | 128K | from $0.30 |
| Mistral Code Agent Latest | 2026-06-02 | 256K | from $0.40 |
| Voxtral Mini Transcribe | 2026-05-15 | 16.4K | unpriced |
| Mistral Medium 3.5 | 2026-04-30 | 262K | from $1.50 |
| Mistral Medium 3.5 | 2026-04-29 | 262K | from $1.50 |