Home / Models / DeepSeek / DeepSeek V3

DeepSeek V3 pricing and routing profile

DeepSeek V3 from DeepSeek lists at $0.257 per million input tokens and $1.03 per million output tokens, with a 163,840-token context window. Prices from OpenRouter's catalogue on 2026-09-28.

Input, per 1M tokens$0.257
Output, per 1M tokens$1.03
Context window164K
Confidence signalNot exposed

Tool callingStructured output

Cost per 1,000 requests

Request shapeList cost
Classification or routing (600 tokens in, 10 out)$0.165
Chat reply (2,000 in, 400 out)$0.926
Retrieval-augmented answer (8,000 in, 500 out)$2.57

Before prompt caching. Try your own shape in the cost calculator.

Can Gimbix route to it first?

Not as a first-answer model through OpenRouter: no host returns token log probabilities for DeepSeek V3. It can still be the model Gimbix falls back to when a cheaper model is unsure.

Cheaper models that can answer first

Models priced below DeepSeek V3 that expose a confidence signal. Whether they answer your traffic as well is what a Gimbix pilot measures.

ModelInput / output per 1MCheaper on a chat reply
DeepSeek V3.1$0.25 / $0.955%
Qwen3 Coder Flash$0.195 / $0.97516%
Qwen3.6 35B A3B$0.15 / $1.0024%
Llama 4 Maverick$0.188 / $0.65231%
Qwen3 Coder Next$0.12 / $0.8040%
Qwen3 VL 30B A3B Instruct$0.15 / $0.6042%

Questions

How much does DeepSeek V3 cost?

DeepSeek V3 lists at $0.257 per million input tokens and $1.03 per million output tokens on OpenRouter as of 2026-09-28. A typical chat reply of 2,000 input and 400 output tokens costs about $0.926 per 1,000 requests.

What is the context window of DeepSeek V3?

163,840 tokens.

Can a cheaper model replace DeepSeek V3?

Sometimes. Gimbix proves it on your own traffic before routing: the cheaper model must match DeepSeek V3 on one half of your requests and make at most three answers worse on the other.