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 Aug 3, 2026Mistral Medium 3.5 is a 128-billion-parameter text-and-image model with a quarter-million-token request limit and broad measured coverage across coding, maths and creative tasks. Its custom licence is less permissive than Apache or MIT alternatives, and its output rate is several times its input rate.
Pick this for long-context document analysis at 262,144 tokens, or for coding-heavy workflows where its measured coding score is the relevant signal. Consider it when you want identical pricing across both tracked providers and need Mistral-direct throughput at 48 tokens per second. Skip it if you need a permissive open licence, if your workload is output-heavy, or if web-development coding is your main use case.
The case for it
- Seven distinct Arena categories measured, all evaluated on the same recent date.
- Strong general coding performance, with a measured score well above its hard-prompt and maths results.
- Identical pricing across both tracked providers eliminates shopping friction.
The case against it
- Output rate is five times the input rate, making output-heavy workloads costly.
- Creative writing lags its own coding score by a wide margin; web-development coding is lower still.
- Custom licence is less permissive than Apache or MIT alternatives; commercial use and redistribution terms are not standard.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)55th of 143 · 1427.3
CodingWriting and fixing code on its own
Arena Coding53rd of 143 · 1478.9
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Mistral Medium 3.5 for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Mistral Medium 3.5 placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model7 scoresEvery figure we hold, from 7 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?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
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.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $1.50 in / $7.50 out
- Context served
- 262K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $1.50 / $7.50 | 262K | not measured | Unknown | Unknown | Unknown |
| Mistral AI | $1.50 / $7.50 | 262K | 57 tok/s | No | Yes30 days | Unknown |
Mistral AIAcross the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Mistral AI | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
Models people weigh against Mistral Medium 3.5
When we formed this view
Dates behind this page
Prices last checked 3d ago
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 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
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
- Modality record
- text+image+file->text
- Catalogue slug
- mistralai-mistral-medium-3-5