Mistral Medium 3.5
Mistral AI · released Mar 31, 2026 · mistralai/Mistral-Medium-3.5-128B
- Type
- Open weightsCustom licence
- Params
- 128B
- Context
- 262K
about 197K words of context · download allowed, licence restricts use
Our take
Written Sep 2, 2026Mistral Medium 3.5 is a 128-billion-parameter text model that accepts images and files alongside text. Its coding score is its strongest measured skill, and it offers a 262,144-token request limit, but its agent-task performance is weak across every dimension we track.
Pick this for coding workloads where its Arena Coding score of 1479.1 is well above its general text rating, or for long-document work needing a quarter-million-token context. Use the 127 tps tier if you need high throughput at the same price point as the slower tier. Skip it if you need agentic tool use, web-development coding specifically, or a permissive open licence.
The case for it
- Coding is its standout skill: 52 points above its own general text score on the Arena leaderboard.
- 262,144-token request limit suits long-document analysis.
- Premium throughput available at no extra cost: 127 tps tier priced the same as 4 tps.
The case against it
- Agent tasks are weak across all measured dimensions, with negative scores on task outcome, tool use and recovery.
- Web development coding lags its general coding ability by 214 points.
- Custom restricted licence and steep output pricing on every tracked offer, with no cheaper tier available.
How good is it?
A text model for drafting and everyday questions, though it trails most models at multi-step tasks and tool use.
- carrying out multi-step tasks for youArena Agent · 48th of 55
- calling tools to carry out requestsArena Agent · Tool use · 52nd of 55
- changing course when you give new instructionsArena Agent · Steerability · 46th of 55
- getting back on track after a step failsArena Agent · Recovery · 47th of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)73rd of 168 · 1426
CodingWriting and fixing code on its own
Arena Coding71st of 168 · 1478
AgenticPlanning, calling tools, staying on task
Arena Agent48th of 55 · −0.116
Arena Agent is the only board that has scored it for this.
WritingDrafting and rewriting prose
Arena Creative Writing71st of 168 · 1398
Arena Creative Writing is the only board that has scored it for this.
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model12 scoresEvery figure we hold, from 12 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M1 Ultra (64-core GPU) · 128 GB
Room to spare. 11.1 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 1 hour ago — each listing carries its own date.
- per 1M tokens
- $1.50 in / $7.50 out
- Context served
- 262K
- Throughput
- ~76 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $1.50 / $7.50checked 1 hour ago | 262K | not measured | Unknown | Unknown | Unknown |
| Mistral AIThrough OpenRouter | $1.50 / $7.50checked 1 hour ago | 262K210K max reply | 76 tok/s | No | Yes30 days | Confirmed |
| Mistral AIeuThrough OpenRouter | $1.65 / $8.25checked 1 hour ago | 262K210K max reply | 114 tok/s | No | Yes30 days | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Mistral AIThrough OpenRouter | ✓ | ✓ | ✓ |
| Mistral AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
Models people weigh against Mistral Medium 3.5
When we formed this view
Recent changes
Each date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts.
- We hold no cached-input rate for any of its listings.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Custom licence
This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.
Identifiers
- Hugging Face
- mistralai/Mistral-Medium-3.5-128B
- Architecture
- Dense
- Takes in, gives back
- Text, images and documents in, text out
- Catalogue slug
- mistralai-mistral-medium-3-5