Back to models
deprecated
Meta: Llama 3.1 8B Instruct
meta/llama-3-1-8b-instructPrices
- Input
$0.05 per 1M tokens
medium- Input (cached read)
$0.025 per 1M tokens
medium- Output
$0.08 per 1M tokens
medium
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| OpenRouter · meta | Input | $0.05 per 1M tokens |
| Input (cached read) | $0.025 per 1M tokens | |
| Output | $0.08 per 1M tokens | |
| OpenRouter · meta-llama | Input | $0.05 per 1M tokens |
| Input (cached read) | $0.025 per 1M tokens | |
| Output | $0.08 per 1M tokens | |
| Other · huggingface | Input | $0.06 per 1M tokens |
| Output | $0.06 per 1M tokens | |
| Other · huggingface-cerebras | Input | $0.10 per 1M tokens |
| Output | $0.10 per 1M tokens | |
| Other · huggingface-nebius | Input | $0.03 per 1M tokens |
| Output | $0.09 per 1M tokens | |
| Other · huggingface-novita | Input | $0.02 per 1M tokens |
| Output | $0.05 per 1M tokens | |
| Other · huggingface-nscale | Input | $0.06 per 1M tokens |
| Output | $0.06 per 1M tokens | |
| Other · huggingface-ovhcloud | Input | $0.11 per 1M tokens |
| Output | $0.11 per 1M tokens | |
| Other · huggingface-sambanova | Input | $0.10 per 1M tokens |
| Output | $0.20 per 1M tokens | |
| Other · inference | Input | $0.025 per 1M tokens |
| Output | $0.025 per 1M tokens | |
| Other · kilo | Input | $0.02 per 1M tokens |
| Output | $0.04 per 1M tokens | |
| Other · merge-gateway | Input | $0.22 per 1M tokens |
| Output | $0.22 per 1M tokens | |
| Other · nano-gpt | Input | $0.0544 per 1M tokens |
| Input (cached read) | $0.0272 per 1M tokens | |
| Output | $0.085 per 1M tokens | |
| Other · novita | Input | $0.05 per 1M tokens |
| Output | $0.05 per 1M tokens | |
| Other · novita-ai | Input | $0.02 per 1M tokens |
| Output | $0.05 per 1M tokens | |
| Other · nvidia | Input | $0.00 per 1M tokens |
| Output | $0.00 per 1M tokens | |
| Other · openrouter | Input | $0.05 per 1M tokens |
| Input (cached read) | $0.025 per 1M tokens | |
| Output | $0.08 per 1M tokens | |
| Other · pioneer | Input | $0.20 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $0.20 per 1M tokens | |
| Other · wandb | Input | $0.22 per 1M tokens |
| Input (cached read) | $0.22 per 1M tokens | |
| Output | $0.22 per 1M tokens |
Specifications
- Provider
- meta
- Context window
- 131,072
- Max output tokens
- 117,964
- Open weights
- yes
- Released
- 06/30/2024
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.05 per 1M tokens, unchanged since 09/14/2026
- Output
- 0.08 per 1M tokens, unchanged since 09/14/2026
- Input (cached read)
- 0.025 per 1M tokens, unchanged since 09/14/2026