Open multimodal Llama model for long-context analysis and efficient agents
Specification
most-agreed values
Context
328K
Max output
66K
Released
2025-09-05
Knowledge cutoff
2025-01
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.085
Output
$0.46
Cache read
$0.0425
Quality
5 benchmarks · 2 sources
Composite
20th
percentile of 334 scored models
Rank
268 / 334
±0.05 sd
Evidence
5 × 2
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
coding2nd1/3 bench
reasoning36th1/4 bench
math29th3/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 62.3 ±1.2 | default | Epoch AI | 2025-04-08 |
| GPQA diamond | 51.8 ±3.2 | default | Epoch AI | 2025-04-08 |
| FrontierMath-v1 | 0.0 ±0.0 | default · 2 runs | Epoch AI | 2025-04-08 |
| OTIS Mock AIME 2024-2025 | 7.8 ±3.0 | default | Epoch AI | 2025-04-08 |
| SWE-Bench verified | 9.1 | default · mini-SWE-agent | SWE-bench | — |
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 |
|---|---|---|---|---|---|---|---|
| vercel | free | free | — | — | 128K | 4K | — |
| helicone | $0.08 | $0.30 | — | — | 131K | 8K | — |
| nano-gpt · meta-llama | $0.085 | $0.46 | $0.0425 | — | 328K | 66K | — |
| kilo · meta-llama | $0.10 | $0.30 | — | — | 328K | 16K | — |
| openrouter | $0.10 | $0.30 | — | — | 1.3M | 16K | — |
| openrouter · meta-llama | $0.10 | $0.30 | — | — | 1.3M | 16K | — |
| vercel_ai_gateway · vercel-ai-gateway | $0.10 | $0.30 | — | — | 131K | 8K | — |
More from Meta
most-hosted first