LLM Reference
Fireworks AI

DeepSeek Coder V2 on Fireworks AI

DeepSeek Coder V2 · DeepSeek

ServerlessProvisioned

Pricing

TypePrice (per 1M)
Input tokens$1.20
Output tokens$1.20

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

About DeepSeek Coder V2

DeepSeek Coder V2 is an open-source Mixture-of-Experts code language model tailored for code intelligence and software development. It rivals closed-source models like GPT-4 Turbo in code-specific tasks by undergoing extensive pre-training on 6 trillion tokens beyond its DeepSeek-V2 base. This training enhances its coding and mathematical reasoning capabilities while preserving strong general language skills. The model supports over 338 programming languages and accommodates a context length of 128K tokens, making it capable of handling extensive codebases and complex tasks. DeepSeek Coder V2 is accessible via Hugging Face, DeepSeek's official website, and an OpenAI-compatible API. Its architecture features Multi-head Latent Attention and employs the DeepSeekMoE framework for efficient inference and cost-effective training.

Get Started

Model Specs

Released2024-06-17
Parameters236B
Context128K
ArchitectureMixture of Experts