Mistral Medium 3.5
- Context
- 262K
- Released
- —
- Parameters
- 128B
- Input / 1M tokens
- $1.50
- Output / 1M tokens
- $7.50
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Mistral AI
- Model family
- Mistral Medium
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- —
- Model ID
mistralai/mistral-medium-3-5- Openness
- Open weights
- License
- Modified MIT
- Parameters
- 128B
- Input modalities
- text, image, file
- Output modalities
- text
- Modality
- text+image+file->text
- Native context
- 256K
- Tokenizer
- Mistral
- Max output tokens
- 210K
- Hugging Face
- —
- Source freshness
- Endpoints synced Oct 15, 2026, 10:24 AM UTC
Open-weight builds
Ollama variants
Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.
| Variant | Parameters | Type | Quantization | Size | Context | Input |
|---|---|---|---|---|---|---|
| mistral-medium-3.5:128b-bf16 | 128B | — | BF16 | 255 GB | 256K | text + image |
| mistral-medium-3.5:latest | 128B | — | Q4_K_M | 80 GB | 256K | text + image |
| mistral-medium-3.5:128b-q8_0 | 128B | — | Q8_0 | 138 GB | 256K | text + image |
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| mistral/zdr | 262K | $1.50 | $7.50 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral | 262K | $1.50 | $7.50 | — | — | 99.91% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/zdrBatch pricing | 262K | $1.50 | $7.50 | — | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistralBatch pricing | 262K | $1.50 | $7.50 | — | — | 99.91% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/eu | 262K | $1.65 | $8.25 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/euBatch pricing | 262K | $1.65 | $8.25 | — | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.