All AI models
Hosted API with published model ecosystemVerified August 11, 2026

DeepSeek

DeepSeek V4

DeepSeek V4 is a high-value API option for teams that need a one-million-token context window, tool support, and unusually low published Flash pricing. It belongs in an open-model research workflow, but its precise self-hosting and licensing claims should be verified against an official V4 weight release before you build a product dependency around them.

License
Verify current weight terms
Context
1M tokens
Modalities
Text
Parameters
Provider API documentation does not list a parameter count for the current V4 API variants

What the license means

DeepSeek publishes current V4 API documentation and prices. This page does not label V4 as a permissive open-source release until the provider publishes a primary weight and license source for the exact V4 variant being considered.

Open-weight, open source, and no-cost API access mean different things. Always review the linked terms and your own data, hosting, and compliance requirements before shipping.

API and operating cost

Input / 1M
$0.14
Output / 1M
$0.28

Flash cache-miss input and output price per 1M tokens. Pro and cache-hit pricing differ. The provider notes that a price change is planned.

Check current provider price

Where it fits

  • Cost-sensitive API workflows
  • Long-context text agents
  • Tool-call and structured-output integrations

Where it does not fit

  • Planning a self-hosted deployment without a current official V4 weight source
  • Assuming Flash pricing applies to Pro or long-lived cached workloads

Local deployment reality

Treat the exact V4 deployment path as a provider-specific verification item. The current official source cited here is the hosted API documentation, not a self-hosting instruction set.

Practical setup notes

  • Choose Flash when the Responses API matters and Pro only after benchmarking the task quality.
  • Model cache-hit and cache-miss input separately in cost estimates.

Capability notes

Reasoning
Thinking and non-thinking modes
Tools and output
Tool calls, JSON output, Anthropic compatibility, and Responses API on Flash

Limitations to plan around

  • Published API pricing is volatile and DeepSeek has warned of a planned increase.
  • The public API page is not a substitute for exact deployment and license terms.

Continue comparing

Related model decisions

See all reviewed models
Open source

GLM-5.2

Long-horizon coding agents

Open-weight

MiniMax M3

Agentic coding

Open source

Mistral Small 4

Multimodal document analysis

Editorial note: This is a dated decision page, not a benchmark leaderboard or a substitute for legal, security, or infrastructure review. Model and pricing facts can change after August 11, 2026; use the linked primary sources before committing budget or customer data.