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 ReadFree
Cache WriteFree
ImageN/A

Specifications

Context Length4K
Max Output Tokens4K
Input ModalitiesText
Output ModalitiesText
TokenizerOther
Instruct Typecode-llama
Top Provider Context4K
Top Provider Max Output4K
ModeratedNo

Compare this model

See how EleutherAI: Llemma 7b stacks up against other models.

Last updated: March 23, 2026

First tracked: March 23, 2026