DeepSeek API: Compatibility with OpenAI and Anthropic Formats and New Models

ArticleResource

DeepSeek's quick-start API documentation outlines how to access its models via OpenAI- and Anthropic-compatible endpoints. It highlights updated V4 models, an experimental vision model, and direct integration into popular coding assistants.

Key points

  1. Fully compatible with OpenAI (https://api.deepseek.com) and Anthropic (https://api.deepseek.com/anthropic) formats using standard SDKs.
  2. Model versions updated: deepseek-v4-flash points to DeepSeek-V4-Flash-0731, and deepseek-v4-pro points to DeepSeek-V4-Pro-0813, retaining existing model aliases.
  3. Introduction of deepseek-v4-flash-vision-exp, an experimental model with multimodal image input support.
  4. DeepSeek Harness is available in developer preview.
  5. Direct drop-in integration without custom code in tools such as Claude Code, GitHub Copilot, and OpenCode.
  6. Chat completions support reasoning controls via 'thinking' and 'reasoning_effort' parameters.

Why it matters

API-level compatibility with both OpenAI and Anthropic enables developers to switch or test DeepSeek as a backend provider in existing frameworks and tools without modifying application logic.

Analysis

By supporting standard base URLs for both OpenAI and Anthropic client libraries, DeepSeek eliminates migration friction for development teams. The inclusion of reasoning-specific attributes ('thinking' object and 'reasoning_effort') alongside multimodal experimental models indicates a focus on agentic workflows and advanced problem-solving.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:DeepSeek

    DeepSeek API Changelog: Launch of V4-Flash-Vision-Exp and V4-Pro GA

    DeepSeek's API changelog details the introduction of the multimodal DeepSeek-V4-Flash-Vision-Exp model alongside the GA release of DeepSeek-V4-Pro. The V4 family introduces native support for the Responses API format, granular thinking effort levels, and off-peak pricing.

    AI & LLMs· Announcement

  • Article:api-docs.deepseek.com

    DeepSeek Vision API: Image Processing with deepseek-v4-flash-vision-exp

    DeepSeek has published documentation on vision capabilities for the deepseek-v4-flash-vision-exp model, offering image ingestion via Base64, external URLs, and a dedicated Files API across OpenAI- and Anthropic-compatible endpoints.

    AI & LLMs· Resource

  • Article:DeepSeek

    DeepSeek Releases Experimental DeepSeek-V4-Flash-Vision-Exp Model

    DeepSeek has launched its multimodal DeepSeek-V4-Flash-Vision-Exp model on the DeepSeek API platform. It matches DeepSeek-V4-Flash in text and reasoning benchmarks while adding visual understanding. A free Files API was introduced simultaneously for reusable asset uploads.

    AI & LLMs· Announcement

  • Article:DeepSeek AI

    DeepSeek Launches DeepSeek-V4 Preview as Open Source with 1M Context

    DeepSeek has open-sourced the preview release of DeepSeek-V4. The line-up features DeepSeek-V4-Pro and DeepSeek-V4-Flash, standardising a 1M context window and introducing architectural innovations to cut compute and memory overhead.

    AI & LLMs· Announcement

  • Repository:deepseek-ai/awesome-deepseek-agent

    Awesome DeepSeek Agent: Integration Guides for DeepSeek Models

    This repository provides curated setup guides for integrating DeepSeek models, such as DeepSeek-V4-Pro and DeepSeek-V4-Flash, into popular AI agents and coding tools.

    6kstars

    AI & LLMs· Resource

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.