Skip to content
LLMs
DeepSeek logo

DeepSeek: DeepSeek V3

by DeepSeek

DeepSeek: DeepSeek V3 is a large language model from DeepSeek. It costs $0.257 per million input tokens and $1.03 per million output tokens. Its context window is 164K tokens.

Tool callingStructured outputOpen weights
Input / 1M tokens
$0.257
Output / 1M tokens
$1.03
Cached input / 1M
-

Not supported

Context window
164K

tokens

Who serves it cheapest

2 hosts serve DeepSeek V3. Same weights, same API - the price difference is pure margin and routing.

Providers serving DeepSeek: DeepSeek V3, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
StreamLakeCheapest$0.257$1.03128K-98.7%
DeepInfrafp4$0.320$0.890164K-94.8%

The spread between StreamLake and DeepInfra is about the same for identical weights. Quantization and context limits differ, so check both columns before switching.

About DeepSeek V3

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

Specifications

DeepSeek: DeepSeek V3 specifications
Model IDdeepseek/deepseek-chat
ProviderDeepSeek
Context window164K tokens
Max output16K tokens
Input modalitiestext
Output modalitiestext
Knowledge cutoff2024-07-31
Open weightsYes - deepseek-ai/DeepSeek-V3
ReleasedDecember 26, 2024

Cheaper alternatives

Models that cost less than DeepSeek V3 while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does DeepSeek: DeepSeek V3 cost?

$0.257 per million input tokens and $1.03 per million output tokens.

What is the context window of DeepSeek: DeepSeek V3?

164K tokens, with up to 16K tokens of output per request.

Which provider serves DeepSeek: DeepSeek V3 cheapest?

StreamLake at $0.257 per million input tokens - about the same cheaper than DeepInfra, the most expensive of the 2 hosts serving it.

Confirm against the source: DeepSeek official pricing.