tbuy
deepseek-v4-pro API pricing & access
deepseek-v4-pro API pricing: $1.71 per 1M tokens. DeepSeek V4 Pro API for coding, reasoning and long-text analysis.
deepseek-v4-pro API access
DeepSeek V4 Pro API for coding, reasoning and long-text analysis.
Compare supported API endpoints and capabilities, then access deepseek-v4-pro through the unified API gateway.
- Category
- text
- Context length
- 1000000 tokens
- Maximum output
- 384000 tokens
- Supported APIs
- OpenAI Chat Completions API, Anthropic Messages API
- API endpoints
- POST /v1/chat/completions, POST /v1/messages
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, function calling, json mode, caching
deepseek-v4-pro API pricing
- Base input price
- $1.71 per 1M tokens
- Base output price
- $3.43 per 1M tokens
Base prices are shown in USD before group-specific adjustments. Open the live pricing page for current access-group prices.
About deepseek-v4-pro
DeepSeek V4 Pro is a text model with thinking and non-thinking modes. The official limits are a 1M-token context and up to 384K output tokens. The listed native version is DeepSeek-V4-Pro-0813; Pro does not accept vision input.
Evaluate coding, long-document analysis, and structured answers using project examples. Verify mappings, parameters, and limits for your selected provider.
Official model reference, checked 2026-10-11.
API pricing and model selection
Review the prices and endpoints on this page. Check your account discounts, quota and actual usage after signing in, then evaluate the selected endpoint on a small sample.
Compare models in this category ยท API integration documentation.
Use cases and prompting
Evaluate verifiable reasoning outcomes
Provide the problem, constraints, and expected format. Request conclusions or executable code you can check, rather than hidden reasoning traces.
Verify a default request before comparing mode settings accepted by the endpoint. Check final answers after tool results return, and evaluate successful, failed, and oversized inputs for accuracy, latency, and actual usage.
A task to evaluate
Propose an executable solution to the constraints below, with a check for each constraint. Return verifiable conclusions, steps and code.
Compare the output with your acceptance criteria. Record the model, endpoint, input size, elapsed time and actual usage; change one condition at a time.
How to call deepseek-v4-pro
deepseek-v4-pro is served through tbuy's unified gateway. Existing OpenAI or Anthropic SDK code keeps working: point base_url at https://modelsok.com and use your tbuy API key.
curl (OpenAI-compatible)
curl https://modelsok.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v4-pro", "messages": [{"role": "user", "content": "Hello"}]}'Python (openai SDK)
from openai import OpenAI
client = OpenAI(base_url="https://modelsok.com/v1", api_key="YOUR_API_KEY")
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Python (anthropic SDK)
from anthropic import Anthropic
client = Anthropic(base_url="https://modelsok.com", api_key="YOUR_API_KEY")
message = client.messages.create(
model="deepseek-v4-pro",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)Related pages
Frequently asked questions about deepseek-v4-pro
What is deepseek-v4-pro?
DeepSeek V4 Pro API for coding, reasoning and long-text analysis.
How do I call deepseek-v4-pro?
Create an API key with access to deepseek-v4-pro, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
How is deepseek-v4-pro priced?
Pricing depends on the selected provider group and the model billing unit. Refer to the current input, output, request, or media prices in the pricing section.
What is the context window of deepseek-v4-pro?
The model catalog lists a context window of 1000000 tokens. Check the selected endpoint for request limits.
What is the maximum output of deepseek-v4-pro?
The model catalog lists a maximum output of 384000 tokens. Your request settings may set a lower limit.
How should I evaluate deepseek-v4-pro for my project?
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.