DeepSeek

DeepSeek V4 PRO

Built for reasoning, coding, and agentic tool use, with stronger long-context, thinking-mode, and complex-task execution than DeepSeek V3.2. Compared with Chinese peers such as Qwen, GLM, and Kimi, it is especially competitive for math, programming, and logical reasoning tasks.

  • Long context
  • Tool use
  • Reasoning
  • Structured output

AI Chat

Send a prompt and see the response here.

deepseek-v4-pro
Current conversation
How can I help you?

Start a conversation with this model and ask follow-up questions.

Uses your account balance at the model’s current rates.

Insufficient balance

Your account balance is insufficient for this generation. Top up, then return here to try again.

Top up balance

USD /1M tokens

Pricing

GroupInputOutputCache Read
default$1.71$3.429918$0.009918
deepseek-0.9$1.539$3.086926$0.008926
default
Input$1.71Output$3.429918Cache Read$0.009918
deepseek-0.9
Input$1.539Output$3.086926Cache Read$0.008926

Public list prices are shown in USD. Final charges may vary by account group and usage tier.

API

Code examples

curl --location --request POST 'https://api.tokenhot.ai/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "deepseek-v4-pro",
    "messages": [
        {
            "role": "user",
            "content": "What model are you"
        }
    ]
}'

DeepSeek

Related models

DeepSeekDeepSeekDeepSeek V4 Flash Vision EXP

An experimental multimodal variant of DeepSeek-V4-Flash for image understanding alongside text. A practical choice for visual Q&A, screenshot and document analysis, while its experimental status makes it better suited to evaluation and flexible workflows than strict production-critical paths.

$0.149/1M tokensDeepSeekDeepSeekDeepSeek V4 Flash

Built for reasoning, coding, and agentic tool use, with stronger long-context, thinking-mode, and complex-task execution than DeepSeek V3.2. Compared with Chinese peers such as Qwen, GLM, and Kimi, it is especially competitive for math, programming, and logical reasoning tasks.

$0.1278/1M tokensDeepSeekDeepSeekDeepSeek V4.1 Flash

A strong high-throughput, lower-cost default for general and agentic work: it natively understands images and supports a 1M-token context, optional thinking and non-thinking modes, tool calls, and JSON output. Compared with the higher-tier V4 Pro, it is positioned around speed, throughput, and cost efficiency, making it practical for long documents, coding/agents, and image-text analysis; enable thinking when deeper reasoning is needed.

$0.3/1M tokensOpenAIOpenAIGPT 5.6 SOL

The flagship GPT-5.6 tier for complex professional work and quality-first delivery. It supports image input, function calling, structured outputs, and an exceptionally large context window; consider Terra or Luna when latency or unit cost is the primary constraint.

$1/1M tokens

Blog

Related Articles

DeepSeek V4 Pro 0813: Pricing, Benchmarks, and Open Weights

A developer guide to DeepSeek V4 Pro 0813, covering its 1.6T MoE design, 1M context, official agent benchmarks, API pricing, and realistic hosting needs.

2026-08-19How to Use the DeepSeek API Outside China: Setup and Checks

Use the DeepSeek API outside China through direct or gateway access. Configure Python, verify model IDs, diagnose errors, and measure latency and cost.

2026-08-17DeepSeek Harness (dsh) in 2026: Architecture, Modes, Releases, and Safe Evaluation

A practical guide to DeepSeek Harness architecture, current modes and release status, with safe setup and upgrade checks for developers.

2026-08-17

FAQ

Frequently asked questions

What is DeepSeek V4 PRO best suited for?

DeepSeek V4 PRO is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.

How is DeepSeek V4 PRO priced?

Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.

How can I call DeepSeek V4 PRO?

Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.

Get started

Build with DeepSeek V4 PRO

Use in Console