For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
WebsiteModelsPricingGet Started
DocumentationAPI Reference
DocumentationAPI Reference
  • Overview
    • Welcome
    • Getting Started
    • Authentication
    • Concepts
  • Platform
    • Models and Pricing
    • Billing and Credits
    • Rate Limits and API Keys
    • OpenAI and Anthropic Compatibility
  • Providers and Models
    • All providers
      • DeepSeek overview
      • DeepSeek-Prover-V2
      • DeepSeek-V3.2
      • DeepSeek-V4-Flash
      • DeepSeek-V4-Pro
      • Janus-Pro-DeepSeek
  • Reference
    • API Reference Overview
    • AI Agent Access
    • Support
    • Changelog
On this page
  • Models from DeepSeek
Providers and ModelsDeepSeek

DeepSeek

Models from DeepSeek

DeepSeek-Prover-V2
Open-source LLM specialized in formal theorem proving in Lean 4, built on a recursive theorem-proving pipeline powered by DeepSeek-V3.
DeepSeek-V3.2
Open-source Mixture-of-Experts LLM tuned for high-efficiency reasoning, coding, and general language tasks across long-form prompts.
DeepSeek-V4-Flash
Lightweight MoE model with 284B total / 13B active parameters and native 1M context, tuned for low-latency, cost-effective high-concurrency use.
DeepSeek-V4-Pro
Flagship MoE LLM with 1.6T total / 49B active parameters and native 1M context for advanced math, logical inference, and specialized coding.
Janus-Pro-DeepSeek
Autoregressive framework on the Janus Pro 7B model that unifies multimodal understanding and image generation in one architecture.
Was this page helpful?
Previous

DeepSeek-Prover-V2

Next
Built with

Logo
WebsiteModelsPricingGet Started