deepseek-r1-0528 — API, Pricing & Context Window

deepseek-r1-0528 on Vivgrid: DeepSeek's reasoning-focused R1 model with a 164K context window, available through one unified API.

deepseek-r1-0528 is a reasoning-focused release from DeepSeek's R1 line, tuned to think through multi-step problems with explicit chains of reasoning. It offers a 164K-token context window for long, complex tasks.

Vivgrid serves deepseek-r1-0528 through its unified, OpenAI-compatible API, so you can mix DeepSeek's reasoning model into agent pipelines alongside other providers using one key.

Specifications

Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

Quick start

Call deepseek-r1-0528 through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the Vivgrid Console.

curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{\n    "model": "deepseek-r1-0528",\n    "messages": [\
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }\
    ],\n    "stream": true\n  }'\n```

## Ideal use cases

- Multi-step reasoning and problem solving
- Math, logic, and analytical tasks
- Workflows that benefit from explicit reasoning traces
- Cost-effective alternative to frontier reasoning models

## Related models

- [deepseek-v3.2](/content/docs/models/deepseek-v3.2) — general-purpose DeepSeek model
- [deepseek-v4-pro](/content/docs/models/deepseek-v4-pro/index.html) — flagship coding model
- [deepseek-v3.1](/content/docs/models/deepseek-v3.1) — earlier general-purpose model