API pricing per million tokens
- Input
- $0.94
- per 1M, StreamLake (fp8)
- Output
- $1.88
- per 1M tokens
- Cached input
- $0.078
- no batch tier listed
- Context
- 1M
- 384K max output
Where to buy it (15)
- StreamLakefp8, fp8$0.94 / $1.88cached $0.078
- GMICloudfp8, fp8$0.957 / $1.91cached $0.08
DigitalOceandefault region$1.04 / $2.09cached $0.209
Cloudflare Workers AIdefault region$1.15 / $2.55cached $0.2
DeepInfrafp8, fp8$1.3 / $2.6cached $0.1
Qwen (Alibaba)fp8, fp8$1.42 / $2.83cached $0.118
SiliconFlowfp8, fp8$1.5 / $3.14cached $0.135
Novita AIfp8, fp8$1.6 / $3.2cached $0.135
Venicedefault region$1.65 / $3.3cached $0.33
- AtlasCloudfp4, fp4$1.68 / $3.38cached $0.13
- Baidufp8, fp8$1.69 / $3.38cached $0.14
Basetenfp4, fp4$1.74 / $3.48cached $0.145
- NextBitfp8, fp8$1.74 / $3.48cached $0.145
Parasailfp8, fp8$1.74 / $3.48cached $0.1
Azure AI Foundryus$1.91 / $3.83cached $0.16
Through a gateway
Your own numbers100M input and 20M output tokens a month: $131.54 direct.
Helicone$131.54+0%
Kong AI Gateway$131.54+0%
LiteLLM$131.54+0%
Vercel AI Gateway$131.54+0%
AWS Bedrock$131.54+0%
Google Vertex AI$131.54+0%
Databricks Mosaic AI$131.54+0%
Hugging Face Inference$131.54+0%
Requesty$138.12+5%
Eden AI$138.78+5.5%
OpenRouter$138.78+5.5%
Snowflake Cortex AI$157.85+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
DeepSeek V4.1 FlashDeepSeek · 1M$0.15 / $0.6in / out per 1M$0.15$0.6$0.0031MSep 10, 2026
Muse Spark 1.3Meta · 1M$1.25 / $4.25in / out per 1M$1.25$4.25$0.151MSep 2, 2026
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
GLM 5.3Z.ai · via DeepInfra (fp4) · 1.31M$0.563 / $2.5in / out per 1M$0.563$2.5$0.1251.31MAug 18, 2026
About DeepSeek V4 Pro 0423
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.
Takes text in and returns text. First listed Sep 23, 2026. Blended price $1.17 per 1M tokens at 3 input to 1 output.
Questions
How much does DeepSeek V4 Pro 0423 cost?
$0.94 per million input tokens and $1.88 per million output tokens, with cached input at $0.078.
What is the context window of DeepSeek V4 Pro 0423?
1M tokens, with up to 384K tokens of output.
Where is DeepSeek V4 Pro 0423 cheapest?
Of 15 routes tracked, StreamLake is cheapest at $0.94 input and $1.88 output per million tokens.
Has DeepSeek V4 Pro 0423's price changed?
Yes. The output price went from $1.9 to $3.38, first seen Sep 24, 2026.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.