Mistral Small 4

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from Magistral, multimodal understanding from Pixtral, and agentic coding capabilities from Devstral, enabling one model to handle complex analysis, software development, and visual tasks within the same workflow.

mistral/mistral-small-2603
Organization
Mistral
Providers
14
Context
256,000
Output limit
256,000
Knowledge
2025-06
Release
2026-03-16
Updated
2026-03-16
Weights
Open
Input
text, image
Output
text
Capabilities
Tools, Reasoning, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

18 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
AKI.IO
mistral4-119b
262,14481,920$0.20 / $0.60YesYes—
View
Cortecs
mistral-small-2603
262,144256,000$0.156 / $0.625YesYesYes
View
DevPass (LLM Gateway)
mistral-small-2603
262,144256,000$0.15 / $0.60YesYes—
View
Eden AI
mistral/mistral-small-2603
262,144256,000$0.15 / $0.60YesYesYes
View
EmpirioLabs AI
mistral-small-4
256,00065,536$0.15 / $0.60NoYesYes
View
Infomaniak
mistralai/Mistral-Small-4-119B-2603
256,000256,000$0.25 / $0.93YesYes—
View
Kilo Gateway
mistralai/mistral-small-2603
262,144209,715$0.15 / $0.60YesYesYes
View
LLM Gateway
mistral/mistral-small-2603
262,144256,000$0.15 / $0.60NoYesYes
View
Mistralvia OpenRouter
mistralai/mistral-small-2603
unknown
262,144209,715$0.15 / $0.60YesYesYes
View
Mistralvia OpenRouter
mistralai/mistral-small-2603
unknown
262,144209,715$0.165 / $0.66YesYesYes
View
Mistralvia OpenRouter
mistralai/mistral-small-2603
unknown
262,144209,715$0.165 / $0.66YesYesYes
View
Mistralvia OpenRouter
mistralai/mistral-small-2603
unknown
262,144209,715$0.15 / $0.60YesYesYes
View
Opper
mistral-small-2603
256,0008,192$0.5811 / $2.44062YesYesNo
View
Pioneer
mistralai/Mistral-Small-4-119B-2603
32,00032,000$0.15 / $0.60YesYes—
View
Requesty
mistral-small-2603
256,000256,000$0.165 / $0.66YesYesYes
View
Requesty
mistral-small-2603@eu
256,000256,000$0.165 / $0.66YesYesYes
View
SAP AI Core
mistralai--mistral-small
128,000128,000$0.07 / $0.28YesYes—
View
Tempr Gateway
mistral/mistral-small-2603
256,000256,000$0.15 / $0.60YesYes—
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.07Per 1M input tokens
Output from$0.28Per 1M output tokens
Available offers18Across 14 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 4 lowest-priced configurations
InputOutput
Mistralmistral/zdr
$0.15$0.60
Mistralmistral
$0.15$0.60
Mistralmistral/us
$0.165$0.66
Mistralmistral/eu
$0.165$0.66
mistralai/mistral-small-2603Observed
Input
$0.15
Output
$0.60
Cache read
$0.015
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
Mistralmistral/zdr$0.15$0.60$0.015—
Mistralmistral/us$0.165$0.66$0.0165—
Mistralmistral/eu$0.165$0.66$0.0165—
Mistralmistral$0.15$0.60$0.015—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 3 endpoints
P50P75P90P99
Mistralmistral/zdr
296–2,662.54 ms
Mistralmistral/eu
459–1,622.36 ms
Mistralmistral
288.5–1,335.91 ms
All latency percentiles 3 endpoints
EndpointP50P75P90P99
Mistralmistral/zdr296 ms394 ms610 ms2,662.54 ms
Mistralmistral/eu459 ms581 ms825.8 ms1,622.36 ms
Mistralmistral288.5 ms367 ms579 ms1,335.91 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 3 endpoints
P50P75P90P99
Mistralmistral/zdr
116–203.58 t/s
Mistralmistral/eu
92–170.24 t/s
Mistralmistral
91–207.9 t/s
All throughput percentiles 3 endpoints
EndpointP50P75P90P99
Mistralmistral/zdr116 t/s144 t/s167 t/s203.58 t/s
Mistralmistral/eu92 t/s101 t/s106 t/s170.24 t/s
Mistralmistral91 t/s114 t/s150 t/s207.9 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 4 endpoints
Endpoint5 minutes30 minutes24 hours
Mistralmistral/zdr
Mistralmistral/us
Mistralmistral/eu
Mistralmistral

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations
mistralai/mistral-small-2603Observed
Benchmark profileArtificial Analysis · shared source scale from 0 to 30
Coding26.6
Agentic0.8
Intelligence11.3

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondMistral: Mistral Small 4
75.758%
tau bench verified airlineMistral: Mistral Small 4
43.667%
EvaluationConfigurationSourceResultsDetails
gpqa diamondMistral: Mistral Small 4mistralai/mistral-small-2603OpenRouter75.758%
Details
Composite indicesMistral Small 4 (Reasoning)mistralai/mistral-small-2603Artificial AnalysisIntelligence 11.3 · Coding 26.6 · Agentic 0.8
Details
tau bench verified airlineMistral: Mistral Small 4mistralai/mistral-small-2603OpenRouter43.667%
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026
ApplicationModel routeTurnsMedian cost / sessionDetails
Hermes Agentmistralai/mistral-small-26032–9 turns
$0.00355
Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
mistralai/mistral-small-2603Observed
Context
262,144
Maximum output
209,715
Tokenizer
Mistral
Input
text, image
Output
text
Moderation
No
Added to OpenRouter
2026-03-16
Base URLhttps://openrouter.ai/api/v1
Model IDmistralai/mistral-small-2603
Version IDmistralai/mistral-small-2603
Weights IDmistralai/Mistral-Small-4-119B-2603

Reasoning

Required
No
Enabled by default
No
Default effort
high
Supported efforts
high, none

Supported parameters

  • frequency_penalty
  • include_reasoning
  • max_tokens
  • presence_penalty
  • reasoning
  • reasoning_effort
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Mistral Small 4 cost?

Listed rates start at $0.07 per million input tokens and $0.28 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Mistral Small 4?

There are 18 cataloged offers across 14 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 256,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 9f9b57ec6bc3
  • · dd7aa4e83ea7