token.app โ€บ DeepSeek โ€บ DeepSeek V3

DeepSeek V3 pricing & benchmarks

DeepSeek V3 is available from DeepSeek at $0.257 per million input tokens and $1.03 per million output tokens ($0.450 blended at 3:1). It accepts up to 163,840 tokens of context. 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...

Pricing
Per million tokens ยท OpenRouter
Input$0.257
Output$1.03
Blended (3:1)$0.450
Specification
deepseek/deepseek-chat
Context window164K
Max output16K
ReleasedDec 2024
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for DeepSeek V3 yet. We show nothing rather than reprinting an unverified figure.
Where to run DeepSeek V3
3 hosts ยท 1.4ร— between cheapest and dearest. Blended at 3:1. โš  marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
HostBlended $/1MIn / OutContextWeightsUptime 24h
StreamLake
โš  128K context, not 164K
$0.450 $0.257 / $1.03 128K โ€” 99.6%
DeepInfra $0.462 $0.320 / $0.890 164K fp4 97.4%
Novita
โš  64K context, not 164K
$0.625 $0.400 / $1.30 64K fp8 99.9%
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 โ€” the score above is not host-specific.
Compare 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 on OpenRouter. At a 3:1 input:output mix that blends to $0.450 per million tokens.
What is DeepSeek V3's context window?
DeepSeek V3 accepts up to 163,840 tokens of context, and can generate up to 16,000 output tokens.