Mistral Small 3.1
mistral/small-2503By Mistral · family: mistral-small · released 2025-03-01 · knowledge: 2024-09
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capabilities
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding46
- Tool calling40/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)2/20
- Provider availability4/10
Agents54
- Tool calling35/35
- Structured output0/25
- Reasoning0/15
- Output token limit15/15
- Provider availability4/10
JSON / structured output49
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume19/20
Cost efficiency72
- Headline price (log-scaled)72/95
- Has prompt-cache pricing0/5
Long context45
- Context window (100K → 2M)35/90
- Has published price for full window10/10
Vision81
- Accepts image input50/50
- Context window (10K → 1M)17/30
- Has published price10/10
- Provider availability4/10
Production-readiness76
- Number of independent providers20/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $0.65 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $1.30 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.35 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $1.10 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $1.38 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Pricing detail
Recommended pricing from azure · mistral-small-2503
Cheapest provider: github-models · Unknown input + Unknown output
Available on 4 providers
| Provider | Provider model id | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|---|
| Azure azure | mistral-small-2503 | $0.100 | $0.300 | 128K | 2025-03-01 |
| GitHub Models github-models | mistral-ai/mistral-small-2503 | Unknown | Unknown | 128K | 2025-03-01 |
| Azure Cognitive Services azure-cognitive-services | mistral-small-2503 | $0.100 | $0.300 | 128K | 2025-03-01 |
| routing.run routing-run | route/mistral-small-2503 | $0.150 | $0.600 | 128K | 2026-03-16 |
Data inconsistencies across providers
- release_date varies (span 380d): 2025-03-01, 2026-03-16
- modalities varies across offerings
Different providers report different values for this model. Quick facts above use the representative provider; consult the table for per-provider truth.
Frequently asked questions
How much does Mistral Small 3.1 cost?
Mistral Small 3.1 costs $0.100 per 1M input tokens and $0.300 per 1M output tokens, sourced from azure. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Mistral Small 3.1?
Mistral Small 3.1 has a context window of 128K tokens, with a max output of 33K tokens per reply. This is the total combined size of prompt + completion.
Does Mistral Small 3.1 support tool calling?
Yes. Mistral Small 3.1 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Mistral Small 3.1 support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Mistral Small 3.1 in our data source. Verify with Mistral's official documentation before relying on it in production.
Can Mistral Small 3.1 accept image input?
Yes. Mistral Small 3.1 accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check Mistral's docs for the exact rule.
Is Mistral Small 3.1 open-weight?
No. Mistral Small 3.1 is a proprietary model — only Mistral (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to Mistral Small 3.1?
If Mistral Small 3.1 doesn't fit, consider Mistral Nemo, Mistral Large 3, Devstral 2. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Mistral models
- Mistral Nemo$0.15 in / $0.15 out
- Mistral Large 3$0.50 in / $1.50 out
- Devstral 2$0.40 in / $2.00 out
- Mistral Large 2.1$2.00 in / $6.00 out
- Mistral Nemo$0.02 in / $0.04 out
Capability lists this model is in
Last updated:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.