Llama 2 Chat 7B is a text-based AI model by Meta. It features 116 tok/s output speed, $0.05/1M input tokens pricing. It scores 9.7 on the intelligence index.
Output Speed
116 tok/s
Latency (TTFT)
0.54s
Blended Price
$0.10/M
| Input (Prompt) | $0.05 |
| Output (Completion) | $0.25 |
| Cache Read | Free |
| Cache Write | Free |
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Llama 2 Chat 7B costs $0.05/1M input tokens and $0.25/1M output tokens.
Llama 2 Chat 7B generates output at 116 tok/s. Time to first token is 0.54s.
No, Llama 2 Chat 7B is a paid model. Check the free models page for zero-cost alternatives.
See the alternatives section above for models with similar capabilities. You can also compare Llama 2 Chat 7B head-to-head with any model on our comparison page.
Last updated: