LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Devstral Small 2505

mistral·mistral/devstral-small-2505·GA·Closed·devstral series
Mistral coding agent model for repository tasks and software engineering workflows

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·NanoGPTGateway
$0.06 / $0.06
Blended $0.06 · 1.2× spread
Context
128,000
Output limit
4,096
Knowledge cutoff
2024-12
Released / updated
2025-05-01 / 2025-08-02
Capabilities
Reasoning✓ Tool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

Available at 2 providers2 with public prices

  • ProviderInput / Output
  • NanoGPTGateway
    $0.06 / $0.06
    Cache read $0.03Context 32,768 ⚠Output limit 8,192
  • IO.NETCloud
    mistralai/Devstral-Small-2505
    $0.05 / $0.22
    Cache read $0.025Context 128,000Output limit 4,096deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPTGateway$0.06$0.06$0.03—32,768 ⚠8,192
IO.NET
mistralai/Devstral-Small-2505
Cloud$0.05$0.22$0.025$0.10128,0004,096deprecated

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$11.40
2IO.NET$18.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.30$02026-08-052026-10-23
2026-10-23Input list —Output list —Min blended $0.06

Related models

devstral-latestsame series—devstral-latest@eusame series—
Data partly from models.dev (MIT)