First-party API access to DeepSeek models through OpenAI-compatible, Anthropic-compatible, and Responses APIs.

Models tracked
3
Route-ready
3
Input from
$0.22
Output from
$0.66

Catalog Coverage

Model Endpoints

ModelRoute modelContextInput / 1MOutput / 1MRegionEvidence
DeepSeek-V4-FlashRoute-readydeepseek-v4-flash1,048,576$0.22$0.66Provider-reported
DeepSeek-V4-ProRoute-readydeepseek-v4-pro1,048,576$0.66$1.98Provider-reported
DeepSeek-V4-Flash-Vision-ExpRoute-readydeepseek-v4-flash-vision-exp1,048,576$0.22$0.66Provider-reported

Routing Contract

Modedirect
Protocolopenai
API basehttps://api.deepseek.com
Last observedSep 2, 2026
Routing Groundwork Only

These public route targets identify where and how a model can be requested. Model Markets does not hold provider keys or send inference traffic from this interface.

Provider records describe a serving surface, not the underlying model. Pricing, quantization, region, service tier, retention policy, and measured performance remain endpoint-specific.

Questions

DeepSeek Questions

Which models does DeepSeek offer?+

The current source snapshot includes 3 model endpoint for DeepSeek: DeepSeek-V4-Flash, DeepSeek-V4-Pro, DeepSeek-V4-Flash-Vision-Exp. Browse all models

How much does DeepSeek cost?+

For DeepSeek-V4-Flash, the cited source reports $0.22 input and $0.66 output per million tokens.

Is DeepSeek the fastest provider?+

Model Markets has not run approved independent probes for this delivery, so it does not make a fastest-provider claim.

How current is DeepSeek data?+

This source snapshot was observed Sep 2, 2026 and is marked non-live until production collectors are activated.

How does Model Markets verify DeepSeek?+

Catalog and price claims retain their source classification. Independent telemetry will use disclosed-region standardized probes and will be presented separately. Read the methodology

Send Feedback