Loading
Loading
Model record / DeepSeek
deepseek-v4-flash-0731
Access deepseek-v4-flash-0731 from DeepSeek through one OpenAI-compatible API with live market-linked pricing and usage-based billing.
Text generationText inputReasoningStreaming40% below list
What you pay
Current catalog rates.
Input / 1M tokens$0.076 list$0.0456
Output / 1M tokens$0.153 list$0.0918
Cached input / 1M tokens$0.014 list$0.0084
Current discount40%
Observed reliability
99.51
Successful provider-reaching requests
Output speed
162.7
Median tokens per second over sustained generations
p95 first token (ms)
20,256
p50 5747 ms · total p95 29272 ms
Evidence strength
—
established
At a glance
- Provider
- DeepSeek
- Model ID
- deepseek-v4-flash-0731
- 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
- 1,048,576 tokens
- Maximum output
- 65,536 tokens
Send a request
Pricing history
See how much this model saves and when its recorded price has been lowest.
Time zone
deepseek-v4-flash-0731
High confidenceThis model averaged 48.5% below comparable direct provider prices across the selected range. Its strongest observed window was 3:00 PM in UTC.
Last 24 hours
Average saved
48.5%
Last 24 hours
Cheapest time
3:00 PM
52.5% average savings
Hourly coverage
24/24
308 total observations
Signal quality
High
Ready for planning
Typical unit savings$0.06 / 1M input tokens$0.05 / 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
#4
of 69 ranked models
Last 7 days
#4
of 71 ranked models
Last 30 days
#4
of 71 ranked models
Ready when you are
Stop paying list price for tokens.
Marketplace pricing, capped at list, optimized further.
