MODEL PROFILE

Mistral Medium 3.5 (batch)

Mistral AI · mistral-medium-3-5:batch

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Text generationreasoningstructured_outputstools
Context window262,144 Token
Input → OutputText、Image、File → Text
Model weightsNot verified
Profile updated2026/11/8 12:07:08
OVERVIEW

Model overview

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

The summary below is compiled from sources by an AI model, not our own testing. Verify selection decisions against original sources and your workload.

Key features

  • Supports multimodal inputs including text, image, and file
  • Designed for agentic workflows, coding, and complex reasoning tasks
  • Features long context window of up to 262,144 tokens

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
OpenRouter · mistralai/mistral-medium-3-5:batch ↗USD 0.75USD 3.75Per million tokens2026/11/2 06:25:23

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

Does Mistral Medium 3.5 support image understanding?

Yes, it accepts image inputs and produces text output, indicating image understanding capability.

What is the maximum context length for Mistral Medium 3.5?

The context length is 262,144 tokens.

Is Mistral Medium 3.5 optimized for tool use or structured output generation?

Yes, it is tagged with 'tools' and 'structured_outputs', suggesting explicit support for these capabilities.

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:来源未披露,须进一步核验。模型介绍与第三方评测均以原来源的具体版本和方法为准。