deepseek/deepseek-v4-flash-0731 model page
Use this page to compare current pricing, source history, and alternatives.
AI model changelog
deepseek/deepseek-v4-flash-0731 max output tokens update
deepseek/deepseek-v4-flash-0731 changed max output tokens from 384000 to 65536.
What changed
Max Output Change
deepseek/deepseek-v4-flash-0731 changed max output tokens from 384000 to 65536.
| Field | Previous value | Current value |
|---|---|---|
| Detected date | Not listed | 2026-08-04 |
| Provider | Not listed | OpenRouter |
| Model | Not listed | deepseek/deepseek-v4-flash-0731 |
| max_output_tokens | 384000 | 65536 |
Related models
Models from the same provider
Internal links
Continue researching this change
Continue
Pick up where you left off
Public API
Build with AI Pricing Hub data
Use static JSON endpoints for providers, models, rankings, history, market metrics, and changelog events.
Editorial information
Reviewed by AI Pricing Hub Editorial
2026-08-04
Methodology explains collection, validation, limitations, and update cadence.