mattshumer

Reflection Llama-3.1 70B

mattshumer/reflection-70b

Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

Community

Open Source

Context Window

128,000

Max Output Tokens

4,096

ProviderInput Token PriceOutput Token Price
DeepInfra$0.35/Million Tokens$0.4/Million Tokens
Hyperbolic$0.40/Million Tokens$0.4/Million Tokens