Mistral AIReasoning modelNewFirst seen 30 Oct 2026 on one source; awaiting a secondCompare with another modelMistral Large 4.0.8
As of 30 Oct 2026, Mistral Large 4.0.8 by Mistral AI is not yet ranked on the BenchLeader Index (0 independent results so far; the index needs at least five across two categories). It costs $1.05 per 1M tokens blended ($0.700 in / $2.10 out). Released 6 Oct 2026.
Key facts (as of 30 Oct 2026)
- Mistral Large 4.0.8 costs $1.05 per 1M tokens blended ($0.700 in / $2.10 out) (list price, 30 Oct 2026).
- Mistral Large 4.0.8 was released on 6 Oct 2026 (Mistral AI).
In detail. Mistral Large 4.0.8 is a Mistral AI proprietary reasoning model, released 6 Oct 2026. It is not yet ranked: no independent benchmark results so far, only pricing and metadata. At $1.05 per million tokens blended it is mid-priced.
- Blended price
- $1.05/M
- $0.700 in · $2.10 out
- Output speed
- –
- First answer
- –
- Context
- 1.0M
- Full answer
- –
- Cost per task
- –
- Tokens per task
- –
- Released
- 6 Oct 2026
Versions
Mistral AI has shipped 6 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Mistral Large 4 | 6 Oct 2026 | 52.7 | #265 |
| NewMistral Large 4.0.8this page | 6 Oct 2026 | – | – |
| Mistral Large 3 | 2 Dec 2025 | 45.7 | #424 |
| Mistral Large 2.1 | 18 Nov 2024 | 42.6 | #471 |
| Mistral Large 2 | 24 Jul 2024 | 40.9 | #497 |
| Mistral Large 24.02 | 26 Feb 2024 | 40.7 | #502 |
No independent quality benchmark results yet — only pricing and metadata.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.070 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0009 | $0.0007 | – |
| Summarize a 30-page report | 12,000 / 600 | $0.0097 | $0.0040 | – |
| Code edit | 6,000 / 1,500 | $0.0074 | $0.0045 | – |
| Agentic coding session | 60,000 / 4,000 | $0.050 | $0.022 | – |
| Structured extraction | 2,000 / 200 | $0.0018 | $0.0009 | – |
More from Mistral AI
See also
Questions people ask
- Why does Mistral Large 4.0.8 have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories; as of 30 Oct 2026 Mistral Large 4.0.8 has 0 that count. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does Mistral Large 4.0.8 cost per 1M tokens?
- As of 30 Oct 2026, Mistral Large 4.0.8 costs $0.700 per 1M input tokens and $2.10 per 1M output tokens, $1.05 blended (three input tokens per output token).
- When was Mistral Large 4.0.8 released?
- Mistral AI released Mistral Large 4.0.8 on 6 Oct 2026.
Data as of 30 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Mistral Large 4.0.8: benchmarks, pricing, speed and rank”, data as of 30 Oct 2026, https://www.benchleader.com/models/mistral-large-4-0-8.