Primary use stated or inferred cautiously from official documentation.
M
MISTRAL AI / mistral-medium-3-5
Mistral Medium 3.5
Multimodal coding and self-controlled deployment.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | mistral-medium-3-5 |
|---|---|
| Model type | Text and reasoning |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 28 APR 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image · Document |
| Exit | Text |
| Context window | 256.000 tokens |
| maximum output | Not published |
| Reasoning | Configurable effort |
| Published tools | Features · Agents API · Document Q&A |
| Structured Outings | Supported |
| Batch processing | Supported |
| Prompt cache | Supported |
| Fine-tuning | Open weights · modified MIT license |
| Verified platforms | Mistral API · Le Chat · Mistral Vibe |
Multimodal coding and self-controlled deployment.
Pricing depends on the inference provider or your own hardware.
03 / CAPABILITIES
What it can do
Orientation
Multimodal coding and self-controlled deployment.
Context
256.000 tokens · Not published
Tools and integration
Features · Agents API · Document Q&A
Access
Mistral API · open weights
Input modalities
TextImageDocument
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 1,50 USD / 1 M tokens | Standard API rate |
| Cached input | 0,15 USD / 1 M tokens | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | 7,50 USD / 1 M tokens | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Consult the primary source before budgeting for a deployment.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| SWE-bench Verified | 77,6 % | Resolved | View source ↗ |
| τ³-Telecom | 91,4 | Score | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Mistral Medium 3.5
Version added to Inferama's verified catalog.
07 / SOURCES