API pricing per million tokens
- Input
- $0.089
- per 1M, StreamLake (fp8)
- Output
- $0.177
- per 1M tokens
- Cached input
- $0.018
- no batch tier listed
- Context
- 1M
- 384K max output
Where to buy it (15)
- StreamLakefp8, fp8$0.089 / $0.177cached $0.018
DeepInfrafp8, fp8$0.09 / $0.18cached $0.018
- GMICloudfp8, fp8$0.091 / $0.182cached $0.018
Venicedefault region$0.097 / $0.193cached $0.02
DigitalOceandefault region$0.098 / $0.196cached $0.02
Qwen (Alibaba)fp8, fp8$0.134 / $0.268cached $0.027
SiliconFlowfp8, fp8$0.13 / $0.28cached $0.028
- AtlasCloudfp4, fp4$0.14 / $0.28cached $0.028
- Baidufp8, fp8$0.14 / $0.28cached $0.028
Novita AIfp8, fp8$0.14 / $0.28cached $0.028
Parasailfp8, fp8$0.14 / $0.28cached $0.07
- NextBitfp8, fp8$0.15 / $0.3cached $0.035
- Mancer 2fp8, fp8$0.19 / $0.5$0.268 blended
- OpenInferencefp8, fp8$0.14 / $0.7cached $0.03
Azure AI Foundryus$0.21 / $0.56cached $0.031
Through a gateway
Your own numbers100M input and 20M output tokens a month: $12.40 direct.
Helicone$12.40+0%
Kong AI Gateway$12.40+0%
LiteLLM$12.40+0%
Vercel AI Gateway$12.40+0%
AWS Bedrock$12.40+0%
Google Vertex AI$12.40+0%
Databricks Mosaic AI$12.40+0%
Hugging Face Inference$12.40+0%
Cloudflare AI Gateway$13.03+5%
Requesty$13.03+5%
Eden AI$13.09+5.5%
OpenRouter$13.09+5.5%
Snowflake Cortex AI$14.89+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
GPT-6 LunaOpenAI · 1.05M$0.1 / $0.5in / out per 1M$0.1$0.5$0.011.05MSep 22, 2026
Muse Spark 1.3 ContributorMeta · 1M$0.1 / $0.2in / out per 1M$0.1$0.2$0.0021MSep 2, 2026
About DeepSeek V4 Flash 0423
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.111 per 1M tokens at 3 input to 1 output.
Questions
How much does DeepSeek V4 Flash 0423 cost?
$0.089 per million input tokens and $0.177 per million output tokens, with cached input at $0.018.
What is the context window of DeepSeek V4 Flash 0423?
1M tokens, with up to 384K tokens of output.
Where is DeepSeek V4 Flash 0423 cheapest?
Of 15 routes tracked, StreamLake is cheapest at $0.089 input and $0.177 output per million tokens.
Has DeepSeek V4 Flash 0423's price changed?
Yes. The output price went from $0.168 to $0.28, 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.