Meta
Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instruct
Input
$0.10
per 1M tokens
Output
$0.32
per 1M tokens
Cached input
—
per 1M tokens
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
- Released
- Context window
- 131K tokens
- Max output
- 16K tokens
- Input
- text
- Output
- text
- Reasoning
- No
Price history
No price changes since we started tracking on .
Providers on OpenRouter
10 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 |
|---|---|---|---|---|---|
| DeepInfraturbo | $0.10 | $0.32 | 131K | 100% | 99.21% |
| Novitabf16 | $0.135 | $0.40 | 12K | 100% | 98.6% |
| Parasailfp8 | $0.22 | $0.50 | 131K | 100% | 99.93% |
| AkashMLfp8 | $0.20 | $0.52 | 131K | 100% | 100% |
| CoreWeavefp16 | $0.71 | $0.71 | 128K | 100% | 100% |
| $0.72 | $0.72 | 128K | — | — | |
| Googleus-central1 | $0.72 | $0.72 | 128K | — | — |
| Groq | $0.59 | $0.79 | 131K | 100% | 100% |
| SambaNova | $0.45 | $0.90 | 131K | 80.0% | 97.3% |
| Cloudflarefp8 | $0.293 | $2.25 | 24K | 100% | 100% |