Pricingby GlyphDeepSeek V4 Flash 0423
DeepSeek · Open weights · 1M context · released Apr 24, 2026 · checked 12h ago
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.
Ways to buy 14
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
fp8 · cached $0.018 | $0.09 | $0.18 | $0.09 / $0.18Cheapest | $0.018 | Cheapest |
Default region · cached $0.02 | $0.098 | $0.196 | $0.098 / $0.196+9% vs cheapest | $0.02 | +9% vs cheapest |
Default region · cached $0.021 | $0.105 | $0.21 | $0.105 / $0.21+17% vs cheapest | $0.021 | +17% vs cheapest |
fp8 · cached $0.028 | $0.13 | $0.28 | $0.13 / $0.28+49% vs cheapest | $0.028 | +49% vs cheapest |
Default region · cached $0.028 | $0.138 | $0.275 | $0.138 / $0.275+53% vs cheapest | $0.028 | +53% vs cheapest |
| AtlasCloud fp4 · cached $0.028 | $0.14 | $0.28 | $0.14 / $0.28+56% vs cheapest | $0.028 | +56% vs cheapest |
| Baidu fp8 · cached $0.028 | $0.14 | $0.28 | $0.14 / $0.28+56% vs cheapest | $0.028 | +56% vs cheapest |
| GMICloud fp8 · cached $0.028 | $0.14 | $0.28 | $0.14 / $0.28+56% vs cheapest | $0.028 | +56% vs cheapest |
fp8 · cached $0.07 | $0.14 | $0.28 | $0.14 / $0.28+56% vs cheapest | $0.07 | +56% vs cheapest |
| StreamLake fp8 · cached $0.028 | $0.14 | $0.28 | $0.14 / $0.28+56% vs cheapest | $0.028 | +56% vs cheapest |
| Mancer 2 fp8 · cached $0.175 | $0.175 | $0.5 | $0.175 / $0.5+128% vs cheapest | $0.175 | +128% vs cheapest |
us · cached $0.031 | $0.21 | $0.56 | $0.21 / $0.56+164% vs cheapest | $0.031 | +164% vs cheapest |
| Relace fp4 · cached $0.016 | $0.03 | $1.28 | $0.03 / $1.28+204% vs cheapest | $0.016 | +204% vs cheapest |
| Wafer mxfp4 · cached $0.013 | $0.7 | $0.17 | $0.7 / $0.17+404% vs cheapest | $0.013 | +404% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $12.60 direct.
Kong AI Gateway$12.60+0%
LiteLLM$12.60+0%
Vercel AI Gateway$12.60+0%
Eden AI$13.29+5.5%
OpenRouter$13.29+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
RequestyNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
DeepSeek · 1MCheapest: $0.081 on Particle AI (us-flex) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.081 on Particle AI (us-flex) | · | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. |
DeepSeek · 1M | $0.045 | $0.3 | $0.045 / $0.3 | $0.109 | 1M | on InferenceNet (fp8) | · | DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. |
DeepSeek · 1M | $0.44 | $1.32 | $0.44 / $1.32 | $0.66 | 1M | on DeepInfra (fp8) | · | DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabi |
DeepSeek · 1M | $0.66 | $1.98 | $0.66 / $1.98 | $0.99 | 1M | Lab list price | · | DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. |
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. |
Cohere · 128K | $0.08 | Free | $0.08 / Free | $0.06 | 128K | Lab list price | · | Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). |
Cohere · 128K | $0.12 | Free | $0.12 / Free | $0.09 | 128K | Lab list price | · | Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). |
 Titan Embeddings G1 - TextAmazon Nova · 8K | $0.1 | Free | $0.1 / Free | $0.075 | 8K | Lab list price | · | Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model. |
About DeepSeek V4 Flash 0423
Takes text in and returns text. First listed Sep 23, 2026. Up to 944K output tokens. Blended price $0.113 per 1M tokens at 3 input to 1 output. Model id deepseek-v4-flash.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does DeepSeek V4 Flash 0423 cost?
$0.09 per million input tokens and $0.18 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 944K tokens of output.
Where is DeepSeek V4 Flash 0423 cheapest?
Of 14 routes tracked, DeepInfra is cheapest at $0.09 input and $0.18 output per million tokens.
Has DeepSeek V4 Flash 0423's price changed?
Yes. The input price went from $0.19 to $0.175, first seen Nov 7, 2026.