fireworks/models/kimi-k2-instruct-0905

DeepSeek V3.1 Terminus

DeepSeek-V3.1-Terminus is an updated version of DeepSeek-V3.1 with enhanced language consistency, reduced mixed Chinese-English text, and optimized Code Agent and Search Agent performance.

DeepSeek V3.1

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.

Qwen3 Coder 480B A35B Instruct

Qwen3's most agentic code model to date

Kimi K2 Instruct

Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.