Providers and ModelsDeepSeek

DeepSeek V3.2

DeepSeek V3.2
DeepSeek · Text Generation
POST /v1/chat/completions

Open-source Mixture-of-Experts LLM tuned for high-efficiency reasoning, coding, and general language tasks across long-form prompts.

This model is deprecated and will be retired on 2026-07-08. After that date, requests to this model will fail. Migrate to a successor model before then.

At a glance

FieldValue
Model iddeepseek-v3-2
Input modalitiesText
Output modalitiesText
Context window128K
Weight precision-
Max output tokens32,768
RegionSingapore
Featuresreasoning
Native inferenceNo
NewNo
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages
Deprecation date2026-07-08

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$0.57
Outputper 1M generated tokens$1.71
Web Searchper call$0.015

Example request

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

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno0.7Sampling temperature · Range: 0 – 2
top_pnumberno0.9Nucleus sampling · Range: 0 – 1
max_tokensnumberno4096Max output tokens · Range: 1 – 65536
enable_thinkingbooleannotrueEnable step-by-step reasoning before answering.
thinking_budgetnumberno32768Maximum tokens reserved for the reasoning process. Up to 393216. · Range: 1 – 393216
reasoning_effortenumno"medium"Reasoning effort level. none disables thinking. low, medium, high, and max set bounded thinking budgets sized to the selected model. Sent as an OpenAI-style reasoning_effort field, translated into enable_thinking and thinking_budget for the model service. · Allowed: none, low, medium, high, max
enable_searchbooleannofalseAllow real-time web search. Billed only when the provider reports search usage.

Notes

Web search calls cost $0.015 each — only billed when invoked. Reasoning tokens (CoT) bill as output tokens.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/deepseek-v3-2.