Mistral Medium 3.5 128B
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
Cheapest input
$1.50
$/MTok · models.dev
Cheapest output
$7.50
$/MTok
Context
262K
tokens
Offers
6
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (1 omitted). Show free/$0 offers.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestmistral-medium-3.5-128b | Scaleway | $1.50 | $7.50 | $0.15 | 256K |
| LiteLLMmistralai/mistral-medium-3.5-128b | — | $1.50 | $7.50 | $0.15 | — |
| LiteLLMmistral-medium-3.5-128b | — | $1.50 | $7.50 | $0.15 | — |
| models.devmistralai/Mistral-Medium-3.5-128B | Berget.AI | $1.65 | $5.50 | $0 | 262K |
| models.devmistralai/Mistral-Medium-3.5-128B | Evroc | $1.73 | $6.90 | $0 | 262K |
| models.devmistral-medium-3.5-128b | GreenPT | $2.05 | $10.26 | $0 | 262K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: image
- In: text
- Out: text
Knowledge cutoff: 2026-04Released: 2026-04-29Family: mistral-medium
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence29.9
- AA coding46.9
- AA agentic19
Sources: Arena AI, Artificial Analysis. See /benchmarks.