← Model list

Devstral 2

mistral·mistral/devstral-2512·Deprecated·Open weights·devstral series

Mistral's coding-agent model for repository work, terminal tasks, and software fixes

At a glance
Official price$0.40 / $2.00 per 1M
Cache read · Mistral
Lowest paid$0.40 / $2.00
Merge Gateway Gateway · 1.4× spread
Context262,144
⚠ Providers report 200,000–262,144; the table below is authoritative
Output limit262,144
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextPDF
Knowledge cutoff2025-12
Released / updated2025-12-09 / 2025-12-09

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence19.2
Value24
Coding31.3
Agentic10.6
Output speed37 tok/s
TTFT1.5 s
Cost per task$0
Value formulaIQ 19.2 ÷ min blended $0.800 = 24

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 10 providers9 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Merge GatewayGateway$0.40$2.00$0.04256,000256,000
MistralOfficial
devstral-latest
First-party$0.40$2.00262,144262,144deprecated
MistralOfficialFirst-party$0.40$2.00262,144262,144deprecated
Vercel AI Gateway
mistral/devstral-2
Cloud$0.40$2.00256,000256,000
Eden AIGateway$0.40$2.00262,144262,144
DevPass (LLM Gateway)Gateway$0.40$2.00262,144262,144deprecated
Pioneer
devstral-2
Gateway$0.40$2.00$0.40$0.40256,000131,072
CortecsGateway$0.446$2.23$0.045262,000262,000
GreenPT
devstral-2-123b-instruct-2512
Gateway$0.57$2.74200,00016,384
AnyAPIGateway262,144262,144deprecated

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Merge Gateway$136.80
2Cortecs$152.48
3Mistral · Official$180.00
4Mistral · Official$180.00
5Vercel AI Gateway$180.00
6Eden AI$180.00
Switch to Merge Gateway to save $43.20/mo (24%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark3 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index23.7indexSource ↗
SciCode33.1percent correctSource ↗
Terminal-Bench Hard18.9success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.00$02026-08-052026-08-132026-08-05 · Input list $0.402026-08-06 · Input list $0.402026-08-07 · Input list $0.402026-08-08 · Input list $0.402026-08-09 · Input list $0.402026-08-10 · Input list $0.402026-08-11 · Input list $0.402026-08-12 · Input list $0.402026-08-13 · Input list $0.402026-08-05 · Output list $2.002026-08-06 · Output list $2.002026-08-07 · Output list $2.002026-08-08 · Output list $2.002026-08-09 · Output list $2.002026-08-10 · Output list $2.002026-08-11 · Output list $2.002026-08-12 · Output list $2.002026-08-13 · Output list $2.002026-08-05 · Min blended $0.802026-08-06 · Min blended $0.802026-08-07 · Min blended $0.802026-08-08 · Min blended $0.802026-08-09 · Min blended $0.802026-08-10 · Min blended $0.802026-08-11 · Min blended $0.802026-08-12 · Min blended $0.802026-08-13 · Min blended $0.80