Llama 4 Maverick is a text-based AI model by Meta. It features 127 tok/s output speed, $0.31/1M input tokens pricing. It scores 18.4 on the intelligence index.
Output Speed
127 tok/s
Latency (TTFT)
0.47s
Blended Price
$0.49/M
| Input (Prompt) | $0.31 |
| Output (Completion) | $0.91 |
| 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 4 Maverick costs $0.31/1M input tokens and $0.91/1M output tokens.
Llama 4 Maverick has a lower coding score of 15.6. For demanding coding tasks, consider a model with a higher coding benchmark.
Llama 4 Maverick generates output at 127 tok/s. Time to first token is 0.47s.
No, Llama 4 Maverick is a paid model. Check the free models page for zero-cost alternatives.
Last updated:
See the alternatives section above for models with similar capabilities. You can also compare Llama 4 Maverick head-to-head with any model on our comparison page.