deepseek-v4-pro

Chat

by 0G Foundation

DeepSeek-V4-Pro is DeepSeek's flagship LLM, optimized for agentic coding, multi-step workflows, and complex reasoning. Features native function calling and supports a 1M token context window with up to 384K output tokens. Prompt caching is supported and reported via usage.prompt_tokens_details.cached_tokens.

TEE VerifiedTeeTLSTool CallingModalities

Context

1,000,000 tokens

Max Output

393K

393,216 tokens

Input Price

3.4200 0G

per 1M tokens

Output Price

6.8400 0G

per 1M tokens

Providers

Type

chatbot

Supported Parameters

temperaturetop_ptop_kmax_tokenspresence_penaltyrepetition_penaltyseedstopstreamtoolsresponse_formatpreserve_thinking

Providers(1)

TEE (dstack)TeeTLS

Status HealthyUptime 100%Context 1MMax Out 393KIn3.4200Out6.84000G/M

Cached: 0.2849 0G/M

View API Reference Try in Playground