mistralai
Mistral: Mistral Medium 3.5 (batch)
mistralai/mistral-medium-3-5:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter lists mistralai/mistral-medium-3-5:batch as the batch variant of Mistral Medium 3.5, a dense 128B model. The catalog describes text, image, and file inputs with text output, a 256K-token context window, tool controls, and optional high-effort reasoning. The underlying model card presents Medium 3.5 as a unified instruction-following, reasoning, coding, vision, multilingual, and agentic model. Those capabilities are source-reported; no independent tests of the :batch endpoint were supplied, so validate quality, latency, file handling, and tool behavior on representative workloads before adoption.[1][2]
Strengths
- A single set of weights is described as covering instruction following, reasoning, and coding, while the catalog exposes function calling, structured output, and per-request reasoning controls.[1][2]
- The catalog lists a 256K-token context window and text, image, and file inputs; the model card specifically describes text-and-image input and a vision encoder built for varied sizes and aspect ratios.[1][2]
- The model card reports broad multilingual coverage, strong system-prompt adherence, native function calling, and JSON output; OpenRouter exposes related tools and structured-output parameters.[1][2]
Limitations
- The only evidence specific to :batch is the OpenRouter catalog; the supplied model card documents the underlying canonical model, so endpoint behavior should be validated.[1][2]
- Available benchmark information is reported by the vendor and catalog fields rather than an independent workload test; treat it as directional, not proof for a production use case.[1][2]
- Text is the only listed output. Knowledge cutoff is unspecified, file input is listed only by OpenRouter, and the documentation warns that an outdated Transformers configuration can impair long-context behavior.[1][2]
Where to use it
- Consider for non-interactive batch pipelines that transform text, image, or file inputs into text, after confirming the provider's batch semantics and file support.[1]
- Evaluate for coding assistants and agentic workflows that need configurable reasoning, function calling, structured outputs, and a long context window.[1][2]
- Potential fit for multilingual document or visual-analysis applications where text output is sufficient; pilot image and file handling before rollout.[1][2]
Sources
- [1] OpenRouter catalog · Mistral: Mistral Medium 3.5 (batch)Sources checked: Nov 13, 2026
- [2] Model documentation · Mistral: Mistral Medium 3.5 (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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...
Specifications
- Model ID
- mistralai/mistral-medium-3-5:batch
- Canonical ID
- mistralai/mistral-medium-3.5-20260430
- Creator
- mistralai
- Added to OpenRouter
- 30.04.2026
- Context length
- 262,144
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.750 / out $3.75
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | CC — below the B band | reasoning: optional · default high · efforts: high, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | BB — next 30% of the cohort | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: high, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 4.6 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 46.9 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 7 | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Mistral | 262,144 | $0.750 | $3.75 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.