Pricingby GlyphDeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.
Ways to buy 3
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
fp4-flex, fp4 | $0.256 | $0.712 | $0.256 / $0.712Cheapest | n/a | Cheapest |
fp4 | $0.32 | $0.89 | $0.32 / $0.89+25% vs cheapest | n/a | +25% vs cheapest |
| StreamLake Default region | $0.286 | $1.14 | $0.286 / $1.14+35% vs cheapest | n/a | +35% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $39.84 direct.
Kong AI Gateway$39.84+0%
LiteLLM$39.84+0%
Requesty$41.83+5%
Eden AI$42.03+5.5%
OpenRouter$42.03+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
Vercel 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. |
Z.ai · 1M | $0.179 | $1.4 | $0.179 / $1.4 | $0.484 | 1M | on Wafer (fp4) | · | GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. |
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. |
Z.ai · 1M | $0.37 | $1.25 | $0.37 / $1.25 | $0.59 | 1M | Lab list price | · | GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. |
 Titan Multimodal Embeddings G1Amazon Nova · 0K | $0.8 | Free | $0.8 / Free | $0.6 | 0K | Lab list price | · | Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. |
About DeepSeek V3
Takes text in and returns text. First listed Sep 23, 2026. Up to 16K output tokens. Blended price $0.37 per 1M tokens at 3 input to 1 output. Model id deepseek-chat.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does DeepSeek V3 cost?
$0.256 per million input tokens and $0.712 per million output tokens.
What is the context window of DeepSeek V3?
164K tokens, with up to 16K tokens of output.
Where is DeepSeek V3 cheapest?
Of 3 routes tracked, DeepInfra is cheapest at $0.256 input and $0.712 output per million tokens.