Skip to content
NewTry RouterPlus with free creditsTry playground →

DeepSeek V3.2 API

  • 131KContext
  • 65.5KMax output
  • $1.00/ $1.00From, per 1M in / out
  • 1Provider
Providers
  • Chutes

Pricing

ProviderInput / 1MCached / 1MOutput / 1M
Chutes$1.00$0.10$1.00

USD, as of October 28, 2026. Live prices

Cost

WorkloadChutes
1,000 chat replies2K in, 500 out each$2.50
1,000 agent tasks50K in, 5K out each$55.00
Monthly batch job500M in, 50M out$550.00

Quickstart

OpenAI-compatible
curl https://api.routerplus.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v3.2",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

FAQ

How much does the DeepSeek V3.2 API cost?

On RouterPlus, DeepSeek V3.2 costs $1.00 per million input tokens and $1.00 per million output tokens at Chutes, the lowest listed prices and the provider where routing starts. Prices as of October 28, 2026.

Which providers serve DeepSeek V3.2?

Chutes serves DeepSeek V3.2 on RouterPlus today.

What is the DeepSeek V3.2 model ID?

Use "deepseek/deepseek-v3.2" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.

What is the DeepSeek V3.2 context window?

131K tokens of context and up to 65.5K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.

Is DeepSeek V3.2 open weights?

Yes. DeepSeek publishes DeepSeek V3.2 as an open-weight model, which is why several independent providers can host it.

Do any DeepSeek V3.2 providers retain prompts?

None of the 1 providers serving DeepSeek V3.2 on RouterPlus list prompt retention.

Can I reserve capacity for DeepSeek V3.2?

Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.

Need DeepSeek V3.2 at volume?