API ManyNew models: Qwen 3.8 Max, Claude Haiku 5.5, Claude Opus 5.5, Claude Sonnet 5.5

DeepSeek · Text & reasoning · Tool use · Reasoning

Deepseek V3.2 API

Call Deepseek V3.2 with the same key and request shape as every other model in the catalog.

Test it onlineIntegration docs$0.363 in · $0.54 out per 1M tokens
Deepseek V3.2 example

WHY IT FITS

Inside the gateway

Deepseek V3.2 is an OpenAI-compatible chat model with a 164K token context window, priced per million input and output tokens. Point any OpenAI SDK at this endpoint, send the model id with a messages array, and the response carries token usage you can reconcile against the published rate.

OpenAI-compatible

Call Deepseek V3.2 with the standard chat completions request shape.

Per-token pricing

$0.3631 per million input tokens and $0.5400 per million output tokens.

Long context

164K tokens of context for large prompts and documents.

Tool use

Tool use is supported for Deepseek V3.2.

Reasoning

Reasoning is supported for Deepseek V3.2.

INTEGRATION

Wire it in four steps

  1. Create a key

    Open the dashboard, mint a server-side API key and top up a small balance.

  2. Discover

    Call GET /v1/models to confirm deepseek/deepseek-v3.2, its live specification and the per-token rate.

  3. Send

    POST /v1/chat/completions with the model id and your messages, using any OpenAI-compatible client.

  4. Read

    The reply comes back in the same response (or as a stream), with token usage and the USD cost.

CALLING

Make your first call

# OpenAI-compatible chat completions
curl https://apimany.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v3.2","messages":[{"role":"user","content":"Hello!"}],"max_tokens":512}'

ONLINE TEST

Send a real message from this page

The request runs against this site's own /v1/chat/completions using your signed-in balance, or an API key if you are not signed in. A pasted key stays in this browser tab and is never stored; the result is charged at the quoted USD price.

Or sign in to chat with your account balance.

GOOD TO KNOW

Integration questions

Is Deepseek V3.2 OpenAI-compatible?
Yes. Send model deepseek/deepseek-v3.2 to POST /v1/chat/completions with a messages array, exactly like the OpenAI SDK.
How is Deepseek V3.2 billed?
Per token: $0.3631 per million input tokens and $0.5400 per million output tokens. Usage is returned on every response.
What context window does Deepseek V3.2 have?
164K tokens of context, with the output limit published by GET /v1/models.
Which parameters does Deepseek V3.2 support?
Tool use, Reasoning; recognised fields are validated before dispatch.
Can I use my existing API key?
Yes — the same account key works. Confirm the live id and rate with GET /v1/models before wiring it in.

KEEP EXPLORING

Nearby models