Open Llama instruction model for multilingual chat, reasoning, and coding
Specification
most-agreed values
Context
128K
Max output
8K
Released
2024-12-06
Knowledge cutoff
2023-12
Retires
2026-02-16
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.72
Output
$0.72
Quality
3 benchmarks · 1 source
Composite
22nd
percentile of 344 scored models
Rank
268 / 344
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning25th1/4 bench
math20th2/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 41.6 ±1.2 | default | Epoch AI | 2025-01-27 |
| GPQA diamond | 47.4 ±2.9 | default | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 5.1 ±2.4 | default | Epoch AI | 2025-02-25 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 7 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| kyma · kyma | $0.135 | $0.432 | — | — | 128K | 8K | — |
| inferenceapis · inferenceapis | $0.20 | $0.50 | — | — | 131K | 131K | — |
| venice | $0.70 | $2.80 | — | — | 128K | 4K | — |
| snowflake | $0.72 | $0.72 | — | — | 128K | 16K | — |
| vercel | $0.72 | $0.72 | — | — | 128K | 8K | — |
| vercel_ai_gateway · vercel-ai-gateway | $0.72 | $0.72 | — | — | 128K | 8K | — |
| cerebras | $0.85 | $1.20 | — | — | 128K | 128K | 2026-02-16 |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | vercel | Input | free |
| 2026-10-22 | vercel | Input | $0.72 |
| 2026-09-02 | vercel | Output | free |
| 2026-10-22 | vercel | Output | $0.72 |
Other listings of this model
same model, different key
More from Meta
most-hosted first