fireworks/models/deepseek-v3-0324

Display Name: Deepseek V3 03-24

Fireworks

text-onlyReleased on Oct 16 12:00 AM

CompareTry in Chat

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek. Updated checkpoint.

Similar Models

text-only

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.

In: $0.62 / Out: $1.85

In: text / Out: text, json

Context: 160K

text-only

Kimi K2 Instruct 0905

Kimi K2 0905 is an updated version of Kimi K2, a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Kimi K2 0905 has improved coding abilities, a longer context window, and agentic tool use, and a longer (262K) context window.

In: $0.66 / Out: $2.75

In: text / Out: text, json

Context: 256K

text-only

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.

In: $0.62 / Out: $1.85

In: text / Out: text, json

Context: 160K

text-only

Qwen3 Coder 480B A35B Instruct

Qwen3's most agentic code model to date

In: $0.50 / Out: $1.98

In: text / Out: text, json

Context: 256K