
DeepSeek V4 Pro
toolsdeepseek-v4-proThe latest DeepSeek model DeepSeek V4 Pro
Input / 1M tokens
$0.9483
$0.0000009483 / token
Output / 1M tokens
$1.897
$0.0000018966 / token
Cached input / 1M
$0.07902
Uptime · 24h
—
No traffic yet
Details
- Type
- Chat
- Input
- text
- Output
- text
- Context
- 1,048,576 tokens
Supported parameters
max_tokenstemperaturetop_pstopseedpresence_penaltyfrequency_penaltyresponse_formatpluginstoolstool_choiceparallel_tool_callsLast 24 hours
Requests per hour; red = provider errors.
- Avg latency
- —
- Avg first token
- —
- Throughput
- —
Endpoints
Requests go to these routes in order and fail over between them. Pick or exclude them by label with provider.order / only / ignore, or reorder with provider.sort.
| Label | Input / output per 1M | First token | Throughput | Status |
|---|---|---|---|---|
primary | $0.9483 / $1.897 | — | — | Available |
relay | $0.9483 / $1.897 | — | — | Available |
backup | $0.9 / $1.5 | — | — | Available |
Use it
curl https://api.ultragpt.pro/v1/chat/completions \
-H "Authorization: Bearer $ULTRAGPT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Anthropic SDK / Claude Code
curl https://api.ultragpt.pro/v1/messages \
-H "x-api-key: $ULTRAGPT_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"max_tokens": 1024,
"messages": [{ "role": "user", "content": "Hello!" }]
}'More DeepSeek models
DeepSeek V4.1 Flashdeepseek-v4.1-flash
DeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017
Deepseek V4 Flashdeepseek-v4-flash
DeepSeek V4 Flash Vision Expdeepseek-v4-flash-vision-exp
DeepSeek V3.2deepseek-v3.2Compare DeepSeek V4 Pro
FAQ
How much does the DeepSeek V4 Pro API cost?
$0.9483 input / $1.897 output per 1M tokens; cached input $0.07902 per 1M tokens. You pay per use from a prepaid balance - no subscription, and every response reports its exact cost in usage.cost.
How do I call DeepSeek V4 Pro through the API?
Create an UltraGPT API key, point the official OpenAI SDK (or any OpenAI-compatible client) at https://api.ultragpt.pro/v1 and pass "deepseek-v4-pro" as the model. Anthropic SDKs and Claude Code work too, through /v1/messages.
What is the context window of DeepSeek V4 Pro?
DeepSeek V4 Pro accepts up to 1,048,576 tokens of context on UltraGPT.
Does DeepSeek V4 Pro support tools, vision and reasoning?
Tool / function calling: yes. Image input (vision): no. Reasoning: no. Input: text; output: text.