Mistral Medium 3.5
| Maker | Mistral |
|---|---|
| Released | 2026-04-28 |
| Context | 256K |
| Max output | 262.1K |
| Open weights | Modified MIT |
|---|---|
| Modalities | text, image, pdf → text |
| Input / 1M | $1.50 |
| Output / 1M | $7.50 |
| Review call | $0.0574 |
|---|---|
| Reasoning efforts | none, high |
| Hosts | Mistral, OpenRouter |
| Model id | mistral-medium-3-5 |
CodePanel's benchmark has not run Mistral Medium 3.5 as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
No Mistral model is in the run yet. The ranked model closest to it in list price is GLM-5.3 (Workers AI) from Z.ai, which caught 61% [50%–72%] of the known bugs at rank 3 of 17, with a measured review cost of $0.0311. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0574 on Mistral Medium 3.5 and $0.0473 on GLM-5.3 (Workers AI), so this model's call is 21% more than that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| Mistral | mistral-medium-3-5 | $1.50 | $7.50 |
Source: Mistral pricing, Oct 17, 2026
| Model | Maker | Input / 1M | Output / 1M | Review call | Context |
|---|---|---|---|---|---|
| Gemini 2.5 Pro | $1.25 | $10.00 | $0.0569 | 1M | |
| GPT-5 | OpenAI | $1.25 | $10.00 | $0.0569 | 400K |
| Qwen3.7 Max | Qwen | $1.475 | $4.425 | $0.0494 | 1M |
| Grok 4.7 | xAI | $2.00 | $6.00 | $0.0669 | 500K |
Updated Oct 23, 2026