DeepSeek: DeepSeek V3
deepseek/deepseek-chat
ToolsJSON
Intelligence
—
Design Elo
1145
Website
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.257
123rd cheapest
Context
164K
16K max out
How it compares
Cheaper than63%
of all ranked models
Overview
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...
Benchmarks
independent · Artificial Analysis & Design ArenaDesign Arena · Elo14,733 tournaments
Website
1145
3D
1144
Data Viz
1127
svg
1024
Providers & pricing (3)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| StreamLake | $0.257 | $1.03 | 128K | 99.9% |
| DeepInfrafp4 | $0.320 | $0.890 | 164K | 95% |
| Novitafp8 | $0.400 | $1.30 | 64K | 99.7% |
Specifications
Context window164K
Max output16K
Knowledge cutoffJul 2024
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price—
ModeratedNo
Open weightsdeepseek-ai/DeepSeek-V3 ↗
DeepSeek V3 FAQ
How much does DeepSeek V3 cost?
DeepSeek V3 costs $0.257 per million input tokens and $1.03 per million output tokens via OpenRouter, making it 123rd cheapest of 332 paid models.
What is DeepSeek V3's context window?
DeepSeek V3 supports a 164K-token context window and can output up to 16K tokens. It accepts text input.
More from deepseek
All DeepSeek V3 alternatives →Compare head-to-head
DeepSeek: DeepSeek V3 vs DeepSeek: DeepSeek V4 ProDeepSeek: DeepSeek V3 vs DeepSeek: DeepSeek V4 FlashDeepSeek: DeepSeek V3 vs DeepSeek: DeepSeek V3.2DeepSeek: DeepSeek V3 vs DeepSeek: DeepSeek V3.2 ExpDeepSeek: DeepSeek V3 vs DeepSeek: DeepSeek V3.1 TerminusDeepSeek: DeepSeek V3 vs DeepSeek: DeepSeek V3.1