deepseek-r1-0528 — API, Pricing & Context Window | Vivgrid
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
| Provider | DeepSeek |
| Model ID | deepseek-r1-0528 |
| Best for | General-purpose |
| Available on | Chat Completions |
| Context window | 163,840 tokens |
| Modalities | Text |
| Tool / function calling | Yes |
| Knowledge cutoff | 2024-07 |
| Acceleration | 🌐 Global (Centralized) |
Pricing
Pricing in USD per 1M tokens.
| Input | Cached input | Output |
|---|---|---|
| $1.35 | — | $5.40 |
What one request costs
The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.
| Request | Cost |
|---|---|
| Cold prompt, nothing cached | $0.0378 |
API surfaces
The Vivgrid Console catalogs deepseek-r1-0528 on one surface, all behind the same API key. The endpoint shown is the one the Console previews for that surface.
| Surface | Primary endpoint | Use it for |
|---|---|---|
| Chat Completions | /chat/completions | Agent projects, where Vivgrid injects the model, system prompt and tools server-side, and Model API calls that name the model per request. |
Quick start
Get an API key from the Vivgrid Console, then call deepseek-r1-0528 directly.
curl https://api.vivgrid.com/v1/chat/completions \
-H "Authorization: Bearer $VIVGRID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-r1-0528",
"messages": [
{ "role": "user", "content": "Say hello in English, Chinese and Spanish." }
],
"stream": true
}'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
- gpt-6-astra — OpenAI's frontier gpt-6 coding model
- deepseek-v4-flash — general-purpose DeepSeek model
- deepseek-v4-pro — flagship coding model