Open Llama instruction model for multilingual chat, reasoning, and coding
Specification
most-agreed values
Context
128K
Max output
8K
Released
2024-07-23
Knowledge cutoff
2023-12
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.22
Output
$0.22
Quality
3 benchmarks · 1 source
Composite
11th
percentile of 344 scored models
Rank
307 / 344
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning5th1/4 bench
math11th2/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 22.9 ±0.9 | default | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 1.7 ±0.9 | default | Epoch AI | 2026-08-27 |
| GPQA diamond | 27.0 ±1.9 | default | Epoch AI | 2026-08-27 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 4 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| llamagate · llamagate | $0.03 | $0.05 | — | — | 131K | 8K | — |
| vercel_ai_gateway · vercel-ai-gateway | $0.05 | $0.08 | — | — | 131K | 131K | — |
| cerebras | $0.10 | $0.10 | — | — | 128K | 128K | — |
| vercel | $0.22 | $0.22 | — | — | 128K | 8K | — |
Other listings of this model
this page is one of them
The corpus files Llama 3.1 8B Instruct under several keys. This page is the llama-3-1-8b listing. The full record — every host, every price and every benchmark score — is on the main Llama 3.1 8B Instruct page.
More from Meta
most-hosted first