MistralaiMultimodalReleased 30 April 2026
Mistral Medium 3.5 pricing, context and benchmark
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.
262K
Input context
210K
Output context
$1.5
Official input
$7.5
Official output
5
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Mistral Medium 3.5 |
| Model ID | mistralai/mistral-medium-3-5 |
| Provider | Mistralai |
| Release date | 30 April 2026 |
| Status | Generally available |
| Input context | 262,144 tokens |
| Output context | 209,715 tokens |
| Official input pricing | $1.5 per 1M tokens |
| Official output pricing | $7.5 per 1M tokens |
| Cache read pricing | $0.15 per 1M tokens (90% off input) |
| Market input pricing | $1.5 per 1M (cheapest route) |
| Market output pricing | $7.5 per 1M (cheapest route) |
| Highest route pricing | $1.65 in, $8.25 out per 1M |
| Input modalities | text · image · file |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Mistral |
| Provider routes | 2 endpoints |
| Artificial Analysis index | 5 (#2 of 4) |
| Speed | 134 tokens/s, 25.75s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $1.5 in |
| Image | ✓ yes | no | $1.5 in |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | ✓ yes | no | $1.5 in |
02 · Overview
What is Mistral Medium 3.5?
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...
Mistral Medium 3.5 carries a 262K token window, uses the Mistral tokenizer and is served by Mistralai. On Hoodgen it sits in the Multimodal tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released30 April 2026
| Property | Mistral Small 4 | Mistral Medium 3.5 | Change |
|---|---|---|---|
| Released | 2026 | 2026 | Same release window |
| Context | 262K | 262K | Unchanged |
| Max output | 210K | 210K | Unchanged |
| Input price | $0.15 | $1.5 | Higher |
| Output price | $0.6 | $7.5 | Higher |
| Input modalities | text, image | text, image, file | Unchanged |
| AA index | 4 | 5 | Newer benchmark run |
04 · Capabilities
Features and capabilities
◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
▤
Files and PDFs
Documents go in as files rather than pasted text, keeping layout and tables intact.
⚡
Prompt caching
Cached input costs $0.15 per million instead of $1.5, so stable prefixes get cheaper.
06 · Benchmarks
Benchmark results and performance
Artificial Analysis Intelligence Index v5.0.1 blends nine evaluations. Mistral Medium 3.5 scores 5 , ranking #2 of 4.
Intelligence index
5
#2 of 4
Cost per task
$1.04
weighted average per index task
Time per task
4.9m
inference time
Output speed
134
tokens per second
Index score and cost per task
Scale: index 0 to 70, cost 0 to $20. Sub scores are not published per evaluation, so none are invented here.
07 · Use cases
What can you do with Mistral Medium 3.5?
Document understanding
Screenshots, charts, scanned pages and PDFs read in the prompt.
Mixed media briefs
One thread holding text, images and files together.
Extraction
Schema constrained JSON out of messy inputs.
Research synthesis
Several sources condensed with the figures preserved.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.15 per million instead of $1.5, a 90% discount. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
Mistral Medium 3.5 pricing
Official pricing
List price
$1.5 / 1M in
$7.5 / 1M out
- $0.15 cached input
- 262K context
- text, image, file input
Cheapest route
$1.5 / 1M in
$7.5 / 1M out
- 2 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Highest route
$1.65 / 1M in
$8.25 / 1M out
- Priority or premium tier
- Best under load
- Use for latency critical calls
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Mistral | standard | $1.5 | $7.5 | n/a | 100.0% |
| Mistral | standard | $1.65 | $8.25 | n/a | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0413 | $20.63 | 19594 |
| List price | $0.0250 | $12.53 | 11899 |
| Highest route | $0.0454 | $22.69 | 21554 |
10 · Developers
API and developer information
| Model ID | mistralai/mistral-medium-3-5 |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text+image+file->text |
| Max prompt tokens | 262,144 |
| Max completion tokens | 209,715 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/mistral-medium-3-5",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 209,715 tokens per request. Long deliverables have to be chunked. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
Mistral Medium 3.5 vs other Mistralai models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Mistral Medium 3.5 | 262K | $1.5 | $7.5 | 5 | 2026 |
| Mistral Large 4 | 1.05M | $0.7 | $2.1 | 26 | Oct 2026 |
| Ministral 3 14B 2512 | 262K | $0.2 | $0.2 | n/a | 2025 |
| Mistral Small 4 | 262K | $0.15 | $0.6 | 4 | 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Mistralai and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
Mistral Medium 3.5 questions, answered
Mistral Medium 3.5 is a multimodal model from Mistralai, released 30 April 2026. Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.
✦
Start chatting with Mistral Medium 3.5
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.