🔥 gpt-6-astra is Now Live – First Release! Try Now
Sign in
Product
ModelsToolsPlaygroundCompute
Resource
BlogsRankingDocumentationUse CasesStatus
CLIPricing
Language
Back to ModelsGet startedView API

deepseek-v4-pro API

deepseek-v4-pro

DeepSeek V4 Pro is the documented model ID for Flatkey's compatible chat and messages routes. DeepSeek documents a 1M-token context and up to 384K output tokens; Flatkey's current catalog applies UTC time-tiered rates below.

Chat and codingLong contextTool workflows
Input /M
Reference price: $1.32
$1.056-20%
Cache /M
Reference price: $0.044
$0.0352-20%
Output /M
Reference price: $3.96
$3.168-20%
Provider
DeepSeek

Performance

DeepSeek V4 Pro API performance and availability

Live Flatkey request telemetry appears here when enough DeepSeek V4 Pro traffic is available; no coding benchmark is inferred.

Avg. provider uptime
98.7%
last 30 days
Latency
5.13s
last 30 days
Requests
157K
30-day window
Successful inference trend
#7 · 1.3T

Activity

DeepSeek V4 Pro API usage and request activity

This chart uses live Flatkey request data for DeepSeek V4 Pro and stays unreported until enough traffic is collected.

Requests
157K
30-day window
Latency
5.13s
last 30 days
Uptime
98.7%
last 30 days
Successful inference trendActivity

Pricing

DeepSeek V4 Pro API pricing by UTC tier

Prices below are calculated from Flatkey pricing data for this model and the visible groups currently returned by our pricing API.

Flatkey price

Input /M

Live catalog model
$1.056
Input /M
$1.056$1.32
Cache /M
$0.0352$0.044
Output /M
$3.168$3.96
View API
Shared balance

Add credits

Add credits

Use the same Flatkey balance and API key across image, video, audio, and text models.

$10Open wallet$20Open wallet$50Open wallet
Model catalog
Model Type
Text
API
/v1/chat/completions
Billing basis
1M tokens
Context
1,048,576 tokens

DeepSeek V4 Pro capabilities for reasoning and coding

These cards describe practical workflows; exact route, context, and billing fields remain in the API and comparison sections.

Long-context reasoning

Plan, compare, and transform large technical materials within the documented context available to the model route.

Text and file workflows

Use the verified text and file inputs for coding, document analysis, and research tasks on the hosted route.

Engineering and coding assistance

Turn technical prompts into explanations, implementation drafts, reviews, and structured next steps.

Compatible application integration

Connect the model to OpenAI-shaped or Anthropic-shaped clients while keeping routing and account controls in Flatkey.

Compare

DeepSeek V4 Pro vs V4 Flash: API and context fields

No quality or coding-performance ranking is asserted.

CapabilityDeepSeek V4 FlashDeepSeek V4 Pro
Model IDdeepseek-v4-flashdeepseek-v4-pro
Endpoint pathsVerify before publishing/v1/chat/completions, /v1/messages
ContextUnknown1M tokens; up to 384K output
ModalitiesVerify the selected V4 Flash routeText/file fields verified for Flatkey
Benchmark/coding rankingNot assertedNot asserted

Why use Flatkey for DeepSeek V4 Pro?

A clear DeepSeek V4 Pro API workflow for coding

The page makes the time tier, endpoint choice, context field, and deployment boundaries explicit for production planning.

UTC-aware billing

Keep peak and off-peak expressions together; do not replace the catalog rule with one blended rate.

OpenAI or Anthropic route

Use /v1/chat/completions or /v1/messages with the exact deepseek-v4-pro model ID.

Text and file boundary

The verified catalog lists text and file modalities; vision and other inputs are not inferred.

Model facts over rankings

Compare integration fields and context data without publishing an unsupported benchmark or coding-superiority claim.

API

Use the DeepSeek V4 Pro API with compatible clients

Set the exact model ID and choose the compatible path selected by your client.

deepseek-v4-pro
POST /v1/chat/completions
POST /v1/messages
Text and file fields for this Flatkey route; provider vision/file support is endpoint-specific.
curl https://router.flatkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-..." \
  -d '{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Compare two API gateway designs for reliability, cost control, and failover in three concise bullets."
    }
  ]
}'
Docs

FAQ

DeepSeek V4 Pro API
pricing and local-use questions

Answers about DeepSeek V4 Pro API paths, UTC peak and off-peak pricing, context, verified inputs, and deployment boundaries.

What is DeepSeek V4 Pro?
DeepSeek V4 Pro is documented with a 1M-token context and up to 384K output tokens. The Flatkey page exposes its compatible API routes and catalog pricing.
How do I use DeepSeek V4 Pro?
Send a request to /v1/chat/completions or /v1/messages with model ID deepseek-v4-pro.
What is the DeepSeek V4 Pro API model name?
The verified model ID is deepseek-v4-pro.
How is DeepSeek V4 Pro priced?
Use the pricing section above for current Flatkey prices from our pricing API.
Does DeepSeek V4 Pro support local download or open-source use?
DeepSeek has documented an open-source V4 Preview upstream. This Flatkey page provides hosted API routing; local packaging and hardware requirements are not promised here.
Does DeepSeek V4 Pro support vision or multimodal input?
Text and file fields are verified for this Flatkey route. Do not infer native V4 Pro vision support from the separate V4 Flash Vision Files API documentation.
Is DeepSeek V4 Pro better for coding than V4 Flash?
This page does not publish a benchmark or quality ranking.