- Context
- 1M tokens
- Max output
- 384K tokens
- Input / 1M
- —
- Output / 1M
- —
Model Family
DeepSeek V4
DeepSeek V4 is a DeepSeek model family represented in iilib by DeepSeek V4 Pro and DeepSeek V4.1 Flash.
Official documentationVerified Oct 18, 2026
Models
2
Provider
DeepSeek
API access
DeepSeek API
Context range
1M tokens
Input price range
—
Output price range
—
Overview
Both indexed variants support a one-million-token context and agent-oriented APIs. V4.1 Flash has been updated to the 1017 revision, accepts images, and has downloadable MIT-licensed weights; DeepSeek V4 Pro has not been marked open-weight.
Models in this family
Current indexed models and their documented specifications.
DeepSeek V4.1 Flash
Open weightsSep 10, 2026
1 mapped API
DeepSeek V4 Pro
Aug 13, 2026
- Context
- 1M tokens
- Max output
- 384K tokens
- Input / 1M
- —
- Output / 1M
- —
1 mapped API
| Model | Released | Context | Max output | Input | Output | API |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash Open weights | Sep 10, 2026 | 1M tokens | 384K tokens | — | — | DeepSeek API |
| DeepSeek V4 Pro | Aug 13, 2026 | 1M tokens | 384K tokens | — | — | DeepSeek API |