EleutherAI: Llemma 7b
EleutherAIID: eleutherai/llemma_7b
Llemma 7B is a language model for mathematics. It was initialized with Code Llama 7B weights, and trained on the Proof-Pile-2 for 200B tokens. Llemma models are particularly strong at chain-of-thought mathematical reasoning and using computational tools for mathematics, such as Python and formal theorem provers.
Pricing per 1M Tokens
| Input (Prompt) | $0.80 |
| Output (Completion) | $1.20 |
| Cache Read | Free |
| Cache Write | Free |
| Image | N/A |
Specifications
| Context Length | 4K |
| Max Output Tokens | 4K |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | Other |
| Instruct Type | code-llama |
| Top Provider Context | 4K |
| Top Provider Max Output | 4K |
| Moderated | No |
Compare this model
See how EleutherAI: Llemma 7b stacks up against other models.
Last updated: March 23, 2026
First tracked: March 23, 2026