Meta
Llama 3.1 8B Instruct
meta-llama/llama-3.1-8b-instruct
Input
$0.05
per 1M tokens
Output
$0.08
per 1M tokens
Cached input
$0.025
per 1M tokens
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...
- Released
- Context window
- 131K tokens
- Max output
- 118K tokens
- Input
- text
- Output
- text
- Reasoning
- No
Price history
- input $0.02 → $0.05 +150% · output $0.04 → $0.08 +100%
- input $0.05 → $0.02 -60% · output $0.08 → $0.04 -50%
Providers on OpenRouter
5 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| DeepInfrafp8 | $0.02 | $0.04 | 131K | 100% | 100% |
| Novitafp8 | $0.02 | $0.05 | 16K | 100% | 99.72% |
| Groq | $0.05 | $0.08 | 131K | 100% | 100% |
| CoreWeavebf16 | $0.22 | $0.22 | 131K | 100% | 100% |
| Cloudflarefp8 | $0.152 | $0.287 | 32K | 100% | 99.66% |