DeepSeek V3

Large-scale Chinese AI model with strong multilingual capabilities.

deepseek-v3
STABLEModel DeactivatedGet StartedView uptime
64,000 context
Released December 26, 2024
Starting at $0.50/M input tokens
Starting at $1.50/M output tokens
Streaming
No ratings yetSign in to rate

Select Provider

All Providers for DeepSeek V3

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

Nebius AI
Context: 64k
Deactivated since Nov 3, 2025
Input
$0.5
/M tokens
Cache Read
/M tokens
Output
$1.5
/M tokens
Get Started

Frequently asked questions

What is DeepSeek V3?

Large-scale Chinese AI model with strong multilingual capabilities. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does DeepSeek V3 cost?

Pricing for DeepSeek V3 on LLM Gateway starts at $0.50 per million input tokens and $1.50 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of DeepSeek V3?

DeepSeek V3 supports a context window of up to 64,000 tokens on its largest provider deployment.

Which providers serve DeepSeek V3?

DeepSeek V3 is served by Nebius AI through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does DeepSeek V3 support tool calling and structured outputs?

No. DeepSeek V3 does not currently support tool calling or structured JSON outputs through LLM Gateway.

When was DeepSeek V3 released?

DeepSeek V3 was released on December 26, 2024.