What is deepseek-ai/DeepSeek-V3's context window?

deepseek-ai/DeepSeek-V3 accepts up to 163,840 tokens in a single request.

Is there a cheaper DeepInfra model than deepseek-ai/DeepSeek-V3?

Yes. deepseek-ai/DeepSeek-V4-Flash is $0.090 per 1M input tokens versus $0.320 for deepseek-ai/DeepSeek-V3, with a 1,048,576 token context window.

Where does this deepseek-ai/DeepSeek-V3 price come from?

From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.

deepseek-ai/DeepSeek-V3 pricing

DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2. deepseek-ai/DeepSeek-V3 from DeepInfra costs $0.320 per 1M input tokens and $0.890 per 1M output tokens. Context window 163,840 tokens.

API id deepseek-ai/DeepSeek-V3 · DeepInfra · source · updated 2026-09-25 · general-purpose

$0.320

Input / 1M tokens

$0.890

Output / 1M tokens

—

Cached input / 1M

164K

Context window

deepseek-ai/DeepSeek-V3 specifications

Provider: DeepInfra
API id: deepseek-ai/DeepSeek-V3
Model type: general-purpose
Context window: 164K tokens
Max output: not published
Currency: USD
Price source: Provider API
Last checked: 2026-09-25

What deepseek-ai/DeepSeek-V3 costs in practice

Estimated cost at common usage volumes
Workload	Input tokens	Output tokens	Estimated cost
Short chat turn	1,000	500	$0.0008
Document summary	50,000	2,000	$0.02
1M tokens in, 200K out	1,000,000	200,000	$0.50

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does deepseek-ai/DeepSeek-V3 cost per 1M tokens?: deepseek-ai/DeepSeek-V3 costs $0.320 per 1M input tokens and $0.890 per 1M output tokens on the standard tier.
What is deepseek-ai/DeepSeek-V3's context window?: deepseek-ai/DeepSeek-V3 accepts up to 163,840 tokens in a single request.
Is there a cheaper DeepInfra model than deepseek-ai/DeepSeek-V3?: Yes. deepseek-ai/DeepSeek-V4-Flash is $0.090 per 1M input tokens versus $0.320 for deepseek-ai/DeepSeek-V3, with a 1,048,576 token context window.
Where does this deepseek-ai/DeepSeek-V3 price come from?: From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.

Head-to-head comparisons

Compare deepseek-ai/DeepSeek-V3 with another model →

Other DeepInfra models

See all DeepInfra pricing →