Models
deepseek-v3.2 — API, Pricing & Context Window | Vivgrid
deepseek-v3.2 on Vivgrid: DeepSeek's efficient general-purpose model with a 128K context window and very low token pricing.
deepseek-v3.2 is an efficient general-purpose model from DeepSeek, offering solid reasoning and a 128K-token context window at very low cost. It's a practical choice for teams that need dependable quality on a tight budget.
On Vivgrid, deepseek-v3.2 is reachable through the unified, OpenAI-compatible endpoint, so it slots directly into existing agent stacks with one API key.
Specifications
| Provider | DeepSeek |
| Model ID | deepseek-v3.2 |
| Best for | General-purpose |
| Context window | 128,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text |
| Tool / function calling | Yes |
| Knowledge cutoff | 2024-07 |
| Acceleration | 🌐 Global (Centralized) |
Pricing
Pricing in USD per 1M tokens, matching the provider's rates.
| Input | Cached input | Output |
|---|---|---|
| $0.28 | $0.03 | $0.42 |
Quick start
Call deepseek-v3.2 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 '{
"model": "deepseek-v3.2",
"messages": [
{ "role": "user", "content": "Say hello in English, Chinese and Spanish." }
],
"stream": true
}'Ideal use cases
- Budget-conscious general-purpose agents
- Classification, extraction, and summarization
- High-volume text workloads
- Cost-efficient reasoning where context fits in 128K tokens
Related models
- deepseek-v4-pro — the flagship next generation
- deepseek-v3.1 — the prior 3.x release
- deepseek-r1-0528 — reasoning-focused DeepSeek model