Loading
Loading
Model record / DeepSeek
deepseek-v4-pro
Access deepseek-v4-pro from DeepSeek through one OpenAI-compatible API with live market-linked pricing and usage-based billing.
Text generationText inputReasoningStreaming30% below list
What you pay
Current catalog rates.
Input / 1M tokens$0.66 list$0.462
Output / 1M tokens$1.98 list$1.386
Cached input / 1M tokens$0.038981
Current discount30%
Observed reliability
99.14
Successful provider-reaching requests
Output speed
93
Median tokens per second over sustained generations
p95 first token (ms)
11,839
p50 4769 ms · total p95 59796 ms
Evidence strength
—
established
At a glance
- Provider
- DeepSeek
- Model ID
- deepseek-v4-pro
- Type
- Text generation
- Endpoint
- /v1/chat/completions
- Vision input
- Not supported
- Image editing
- Not supported
- Video input
- Not supported
- Reasoning
- Supported
- Streaming
- Supported
- Context window
- 1,000,000 tokens
- Maximum output
- 128,000 tokens
Send a request
Pricing history
See how much this model saves and when its recorded price has been lowest.
Time zone
deepseek-v4-pro
Growing confidenceThis model averaged 31.2% below comparable direct provider prices across the selected range. Its strongest observed window was 5:00 PM in UTC.
Last 24 hours
Average saved
31.2%
Last 24 hours
Cheapest time
5:00 PM
38.0% average savings
Hourly coverage
24/24
24 total observations
Signal quality
Growing
Ready for planning
Typical unit savings$0.20 / 1M input tokens$0.63 / 1M output tokens
When this model is cheapest
Each bar is the average discount for that hour in UTC (UTC). Missing bars mean no observation was recorded.
ObservedCheapestNo data
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#10
of 64 ranked models
Last 7 days
#11
of 65 ranked models
Last 30 days
#2
of 65 ranked models
Ready when you are
Stop paying list price for tokens.
Marketplace pricing, capped at list, optimized further.
