DeepSeek V3

DeepSeek-V3 · DeepSeek

It has been automatically upgraded to the latest released version, 250324. Automatically upgraded to the latest released version 250324.

API Pricing

Input$0.272 / 1M tokens
Output$1.088 / 1M tokens

Specifications

Context1.64M tokens
Modalitiestext
Featurestool calling, function calling, structured outputs

Frequently asked questions

What is DeepSeek V3?

It has been automatically upgraded to the latest released version, 250324. Automatically upgraded to the latest released version 250324.

What is the context length of DeepSeek V3?

DeepSeek V3 has a 1,638,000 token context window.

How much does DeepSeek V3 cost?

On AIHubMix, DeepSeek V3 costs $0.272 per million input tokens and $1.088 per million output tokens.

What modalities does DeepSeek V3 support?

DeepSeek V3 accepts text input.

What capabilities does DeepSeek V3 support?

DeepSeek V3 supports tool calling, function calling and structured outputs. Per-protocol parameter support is listed in the capability table on this page.

How do I call DeepSeek V3 via API?

DeepSeek V3 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to DeepSeek-V3 — no other code changes needed.

Who created DeepSeek V3?

DeepSeek V3 is developed by DeepSeek. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More models from DeepSeek

See all DeepSeek models →

DeepSeek V4 Flash 0731

by DeepSeek

DeepSeek-V4-Flash-0731(deepseek-v4-flash-0731) is an open-source MoE large language model…

$0.142/1M in · $0.284/1M out
1,000,000 tokens context

DeepSeek V4 Flash Vision Exp

by DeepSeek

DeepSeek’s officially released new multimodal visual-understanding model…

$0.142/1M in · $0.284/1M out
1,000,000 tokens context

DeepSeek V4 Pro 0813

by DeepSeek

DeepSeek V4 Pro 0813 is DeepSeek’s high-performance general-purpose reasoning and agent…

$0.692/1M in · $2.075/1M out
1,000,000 tokens context

DeepSeek V4 Flash 0731 Fast

by DeepSeek

DeepSeek V4 Flash 0731 Fast is a high-speed deployment of DeepSeek’s agentic model…

$0.28/1M in · $0.56/1M out
1,000,000 tokens context

DeepSeek V4 Flash

by DeepSeek

(This model currently points to the older 0423 version; if you need to request the latest…

$0.142/1M in · $0.284/1M out
1,000,000 tokens context

DeepSeek V4 Pro

by DeepSeek

(This model currently points to the older 0423 version; if you need to request the latest…

$1.69/1M in · $3.38/1M out
1,000,000 tokens context

Use DeepSeek V3 via the AIHubMix unified API — one interface for every major LLM.