LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← 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

Specs & pricing

Input / output per 1M tokens
Official price·Mistral
$0.40 / $2.00
Blended $0.80 · Cache read —
Lowest paid·NanoGPTGateway
$0.40 / $1.40
Blended $0.65 · 1.4× spread
1 more $0 channels
Context
262,144
Output limit
262,144
Knowledge cutoff
2025-12
Released / updated
2025-12-09 / 2025-12-09
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextPDF
Weights
Hugging Face

Devstral 2 by mistral is offered by 16 providers on this page. Public prices are shown for 14 of them. Its official list price is $0.40 per 1M input tokens and $2.00 per 1M output tokens. The lowest paid channel is NanoGPT at $0.40 / $1.40 per 1M, about 1.2× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 128,000 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-12.

Available at 16 providers14 with public prices · 1 free

  • ProviderInput / Output
  • InferXGateway
    Devstral-2-123B-Instruct-2512-int4-AutoRound
    Free
    Context 128,000 ⚠Output limit 128,000
  • NanoGPTGateway
    mistralai/devstral-2-123b-instruct-2512
    $0.40 / $1.40
    Cache read $0.20Context 262,144Output limit 65,536
  • MistralOfficialFirst-party
    $0.40 / $2.00
    Context 262,144Output limit 262,144deprecated
  • MistralOfficialFirst-party
    devstral-latest
    $0.40 / $2.00
    Context 262,144Output limit 262,144deprecated
  • LLM GatewayGateway
    $0.40 / $2.00
    Context 262,144Output limit 262,144
  • Amazon BedrockCloud
    mistral.devstral-2-123b
    $0.40 / $2.00
    Context 262,144Output limit 8,192deprecated
  • DevPass (LLM Gateway)Gateway
    $0.40 / $2.00
    Context 262,144Output limit 262,144deprecated
  • Merge GatewayGateway
    $0.40 / $2.00
    Cache read $0.04Context 256,000 ⚠Output limit 256,000
  • OpenRouterGateway
    $0.40 / $2.00
    Cache read $0.04Context 262,144Output limit 209,715
  • Eden AIGateway
    $0.40 / $2.00
    Cache read $0.04Context 262,144Output limit 262,144
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
InferX
Devstral-2-123B-Instruct-2512-int4-AutoRound
GatewayFree——128,000 ⚠128,000
NanoGPT
mistralai/devstral-2-123b-instruct-2512
Gateway$0.40$1.40$0.20—262,14465,536
MistralOfficialFirst-party$0.40$2.00——262,144262,144deprecated
MistralOfficial
devstral-latest
First-party$0.40$2.00——262,144262,144deprecated
LLM GatewayGateway$0.40$2.00——262,144262,144
Amazon Bedrock
mistral.devstral-2-123b
Cloud$0.40$2.00——262,1448,192deprecated
DevPass (LLM Gateway)Gateway$0.40$2.00——262,144262,144deprecated
Merge GatewayGateway$0.40$2.00$0.04—256,000 ⚠256,000
OpenRouterGateway$0.40$2.00$0.04—262,144209,715
Eden AIGateway$0.40$2.00$0.04—262,144262,144

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

Common scenarios
1NanoGPT$126.00
2Merge Gateway$136.80
3OpenRouter$136.80
4Eden AI$136.80
5Kilo Gateway$136.80
6Eden AI$150.48
9Mistral · Official$180.00

1 more channels offer $0 (InferX); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to NanoGPT to save $54.00/mo (30%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.00$02026-08-052026-10-21
2026-10-21Input list $0.40Output list $2.00Min blended $0.65

Benchmark3 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index—23.7indexSource ↗
SciCode—33.1percent correctSource ↗
Terminal-Bench Hard—18.9success rateSource ↗

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

Related models

devstral-latestsame series—devstral-latest@eusame series—Devstral Small 2505same series—Codestral 25.08cheaper alternative$0.30 / $0.90Nova Litecheaper alternative$0.06 / $0.24Ministral 3 14Bcheaper alternative$0.20 / $0.20Codestral (latest)cheaper alternative$0.30 / $0.90Devstral 2 (latest)same lab$0.40 / $2.00
Data partly from models.dev (MIT) · Mistral official docs ↗