Efficient Mistral model for fast chat, extraction, and production assistants
Specification
most-agreed values
Context
33K
Max output
16K
Released
2025-01-30
Knowledge cutoff
2023-10-31
Retires
2026-04-02
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.05
Output
$0.08
Quality
3 benchmarks · 1 source
Composite
23rd
percentile of 344 scored models
Rank
264 / 344
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning25th1/4 bench
math23rd2/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 44.8 ±1.1 | default | Epoch AI | 2025-01-30 |
| GPQA diamond | 46.3 ±2.8 | default · 2 runs | Epoch AI | 2026-08-30 |
| OTIS Mock AIME 2024-2025 | 6.0 ±2.7 | default · 2 runs | Epoch AI | 2026-08-30 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 8 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| deepinfra | $0.05 | $0.08 | — | — | 33K | 16K 33K | — |
| edenai | $0.05 | $0.08 | — | — | 33K | 16K | — |
| kilo | $0.05 | $0.08 | — | — | 33K | 16K | — |
| openrouter | $0.05 | $0.08 | — | — | 33K | 16K | — |
| aimlapi | $0.0529 | $0.0846 | — | — | 33K | 16K | — |
| together_ai | $0.10 | $0.30 | — | — | 33K | 33K | 2026-04-02 |
| nano-gpt | $0.1155 | $0.3465 | — | — | 33K | 8K | — |
| fireworks_ai | $0.90 | $0.90 | — | — | 33K | 33K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | deepinfra | Input | $0.05 |
| 2026-10-14 | deepinfra | Input | $0.05 |
| 2026-09-02 | openrouter | Input | $0.05 |
| 2026-09-06 | openrouter | Input | $0.05 |
| 2026-10-10 | openrouter | Input | $0.05 |
| 2026-09-02 | deepinfra | Output | $0.08 |
| 2026-10-14 | deepinfra | Output | $0.08 |
| 2026-09-02 | openrouter | Output | $0.08 |
| 2026-09-06 | openrouter | Output | $0.08 |
| 2026-10-10 | openrouter | Output | $0.08 |
| 2026-09-13 | together_ai | Input | $0.10 |
| 2026-09-24 | together_ai | Input | $0.10 |
| 2026-09-13 | together_ai | Output | $0.30 |
| 2026-09-24 | together_ai | Output | $0.30 |
| 2026-10-13 | aimlapi | Input | $0.0688 |
| 2026-10-23 | aimlapi | Input | $0.0529 |
| 2026-10-13 | aimlapi | Output | $0.11 |
| 2026-10-23 | aimlapi | Output | $0.0846 |
More from Mistral
most-hosted first