← Model list
Magistral Small 1.2
mistral·mistral/mistral.magistral-small-2509·GA·Open weights·magistral series
Mistral reasoning model for transparent analysis, math, and complex decisions
At a glance
Reference price$0.50 / $1.50 per 1M
Cache read — · Amazon Bedrock
Lowest paid$0.50 / $1.50
Amazon Bedrock Cloud
Context128,000
Output limit40,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
TextImage
Knowledge cutoff—
Released / updated2025-12-02 / 2025-12-02
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence11.5
Value15
Coding14.7
Agentic1.5
Output speed143 tok/s
TTFT0.83 s
Cost per task$0.2950
Value formulaIQ 11.5 ÷ min blended $0.750 = 15
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 1 providers1 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Amazon Bedrock | Cloud | $0.50 | $1.50 | — | — | 128,000 | 40,000 |
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
1Amazon Bedrock$175.00
The cheapest paid channel is the only channel.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
Upstream provides no control info
1 / 1 providers expose no reasoning control (reasoning_options: []).
Related models
Magistral Smallsame series$0.50 / $1.50DeepSeek V4 Flashcheaper alternative$0.14 / $0.28GPT-5 Nanocheaper alternative$0.05 / $0.40GLM-4.7-Flashcheaper alternative$0 / $0MiMo-V2.5cheaper alternative$0.14 / $0.28
Price historyone sample accumulated per data sync
Input listOutput listMin blended