Context
164K
Max output
164K
Serving providers
9
Cheapest input
$0.20 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.20 to $1.45 per 1M tokens across 9 providers, so the dearest route costs 625% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
HyperbolicCheapest$0.20$0.201
ComponentUnitStandardBatchCached
Text input/1M tok$0.2000
Text output/1M tok$0.2000
DeepSeek$0.27$1.101
DeepInfra$0.38$0.891
Nebius$0.50$1.501
Fireworks AI$0.90$0.901
Vercel AI Gateway$0.90$0.901
Azure$1.14$4.561
Together AI$1.25$1.251
Replicate is dearest at $1.45 / $1.45

Price history

input + output $/1M since we started tracking
Input Output
Input down 78% since first tracked
$0.000$0.500$1.00Jan 5Jun 28Aug 22Jun 22$0.200$0.200

Cost calculator

estimate your monthly spend on this model
$56
estimated / month

Model IDs

copy the exact identifier for your platform
hyperbolic/deepseek-ai/DeepSeek-V3deepseek/deepseek-v3deepinfra/deepseek-ai/DeepSeek-V3nebius/deepseek-ai/DeepSeek-V3fireworks_ai/accounts/fireworks/models/deepseek-v3vercel_ai_gateway/deepseek/deepseek-v3azure_ai/deepseek-v3together_ai/deepseek-ai/DeepSeek-V3replicate/deepseek-ai/deepseek-v3

Frequently asked questions

DeepSeek pricing, context and availability

How much does DeepSeek cost?

DeepSeek costs $0.20 per 1M input tokens and $0.20 per 1M output tokens at its cheapest provider via Hyperbolic. Across 9 serving providers, input prices range from $0.20 to $1.45 per 1M tokens.

What is the context window of DeepSeek?

DeepSeek accepts up to 164K tokens of context and can return up to 164K output tokens.

Which providers serve DeepSeek?

DeepSeek is available from 9 serving providers, each with its own pricing and model ID. Hyperbolic is currently the cheapest.

What can DeepSeek do?

DeepSeek supports tool use, prompt caching and structured output.

Other DeepSeek models

compare pricing across the DeepSeek lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI