Mistral AI

Mistral Small 4

Tool callingStructured outputReasoningImage input
Mistral Small 4 launch post cover

Fast Mistral production model for chat, extraction, and cost-sensitive agents

Context
262K
Released
7mo ago
Parameters
—
Input / 1M tokens
$0.15
Output / 1M tokens
$0.60
Cached input / 1M tokens
$0.02

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer
Mistral AI
Model family
Mistral Small
Type
Language model
Predecessor
—
Successor
—
Released
March 16, 2026
Model ID
mistralai/mistral-small-2603
Openness
Open weights
License
—
Parameters
—
Input modalities
text, image
Output modalities
text
Modality
text+image->text
Tokenizer
Mistral
Max output tokens
210K
Knowledge cutoff
2025-06
Source freshness
Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
Source model
mistral/mistral-small-2603
Source family
mistral-small
Last updated
2026-03-16
Knowledge cutoff
2025-06
Model context
256K
Model output limit
256K
Open weights
Yes
File attachments
Yes
Reasoning
Yes
Tool calling
Yes
Temperature control
Yes

Downloadable weights

Published benchmarks

BenchmarkScoreEvaluation detailsEvidence
Artificial Analysis Coding Index24.3 · index2026-06-01Source
SciCode38 · percent correct2026-06-01Source
Terminal-Bench Hard17.4 · success rate2026-06-01Source
Complete source record (JSON)
{
  "id": "mistral/mistral-small-2603",
  "name": "Mistral Small 4",
  "description": "Fast Mistral production model for chat, extraction, and cost-sensitive agents",
  "family": "mistral-small",
  "last_updated": "2026-03-16",
  "knowledge": "2025-06",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 256000,
    "output": 256000
  },
  "benchmarks": [
    {
      "name": "Artificial Analysis Coding Index",
      "score": 24.3,
      "source": "https://openrouter.ai/mistralai/mistral-small-2603/benchmarks",
      "metric": "index",
      "date": "2026-06-01"
    },
    {
      "name": "SciCode",
      "score": 38,
      "source": "https://openrouter.ai/mistralai/mistral-small-2603/benchmarks",
      "metric": "percent correct",
      "date": "2026-06-01"
    },
    {
      "name": "Terminal-Bench Hard",
      "score": 17.4,
      "source": "https://openrouter.ai/mistralai/mistral-small-2603/benchmarks",
      "metric": "success rate",
      "date": "2026-06-01"
    }
  ],
  "release_date": "2026-03-16",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/mistralai/Mistral-Small-4-119B-2603"
    }
  ]
}

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
Mistralmistral/zdr262K$0.15$0.60$0.02—99.93%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Mistralmistral262K$0.15$0.60$0.02—99.93%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Mistralmistral/zdrBatch pricing262K$0.15$0.60$0.02—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

MistralmistralBatch pricing262K$0.15$0.60$0.02—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Mistralmistral/eu262K$0.17$0.66$0.02—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Mistralmistral/us262K$0.17$0.66$0.02—100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Mistralmistral/euBatch pricing262K$0.17$0.66$0.02—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Mistralmistral/usBatch pricing262K$0.17$0.66$0.02—100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware