LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Magistral Small

mistral·mistral/magistral-small-2506·Deprecated·Open weights·magistral series
Open Mistral reasoning model for transparent step-by-step problem solving

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·IO.NETCloud
$0.50 / $1.50
Blended $0.75
1 more $0 channels
Context
128,000
Output limit
4,096
Knowledge cutoff
2025-01
Released / updated
2025-06-10 / 2025-06-10
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
License
Apache-2.0
Weights
Hugging Face

Available at 2 providers1 with public prices · 1 free

  • ProviderInput / Output
  • NvidiaCloud
    Free
    Context 32,768 ⚠Output limit 32,768deprecated
  • IO.NETCloud
    mistralai/Magistral-Small-2506
    $0.50 / $1.50
    Cache read $0.25Context 128,000Output limit 4,096deprecated
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaCloudFree——32,768 ⚠32,768deprecated
IO.NET
mistralai/Magistral-Small-2506
Cloud$0.50$1.50$0.25$1.00128,0004,096deprecated

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.

Reasoning control

Upstream provides no control info

Your usage cost

Common scenarios
1IO.NET$145.00

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

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.50$02026-08-052026-09-29
2026-09-29Input list —Output list —Min blended $0.75

Related models

Magistral Small 1.2same series—
Data partly from models.dev (MIT)