Model Details
Released
Jul 31, 2026
Context Length
1,048,576
Where is DeepSeek v4 Flash-0731 a perfect fit?
DeepSeek-V4-Flash-0731 is DeepSeek's post-trained production version of V4 Flash, optimized particularly for coding agents, tool use, reasoning, and long-running agentic workflows. It retains the same architecture and parameter scale as the preview version but receives substantially improved post-training.
- Coding agents and software engineering
- Repository-scale code generation and modification
- Autonomous tool-using agents
- Complex reasoning and planning
- Long-context document and code analysis
- RAG and knowledge-intensive applications
- High-volume inference where cost is critical
- Codex-compatible coding workflows
- Coding agents and software engineering
- Repository-scale code generation and modification
- Autonomous tool-using agents
- Complex reasoning and planning
- Long-context document and code analysis
- RAG and knowledge-intensive applications
- High-volume inference where cost is critical
- Codex-compatible coding workflows
Quick Model Estimate
Your DeepSeek v4 Flash-0731 Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
📥 Input (1000 × $0.130000)
—
📤 Output (1000 × $0.260000)
—
Cost Breakdown
📥 Input
📤 Output
Prices are watched for changes and checked against the provider's own page.
Pricing
|
Provider
↕
|
Modality
↕
|
Service Tier
↕
|
Input Price
(per 1M tokens) ↕ |
Output Price
(per 1M tokens) ↕ |
Cached Input
(per 1M tokens) ↕ |
Context Size
↕
|
View
|
|---|---|---|---|---|---|---|---|
 Perplexity | Text | Standard | $0.1300 | $0.2600 | $0.0280 | 1,048,576 tokens | → |
FAQs about DeepSeek v4 Flash-0731
How much does DeepSeek v4 Flash-0731 cost per 1M tokens?
DeepSeek v4 Flash-0731 costs $0.13 per million input tokens, and $0.26 per million output tokens.
What does a typical workload cost with DeepSeek v4 Flash-0731?
1,000 requests of 2,000 input and 500 output tokens each — 2,000,000 input and 500,000 output tokens in total — costs $0.39 with DeepSeek v4 Flash-0731 at its lowest rates. Use the calculator on this page for your own volumes.
Where can I use DeepSeek v4 Flash-0731?
DeepSeek v4 Flash-0731 is available through Perplexity, from $0.13 per million input tokens.
What is DeepSeek v4 Flash-0731's context window?
DeepSeek v4 Flash-0731 has a context window of 1,048,576 tokens.