DeepSeek: DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-exp
DeepSeek V4 Flash Vision Exp is a DeepSeek model that isn't ranked on the TryAii Score yet — only 2 benchmarks on file so far. It lists at $0.216/$0.647 per million input/output tokens with a 1.05M-token context. It's among the fastest models we track, at roughly 84-104 tokens/sec.
Prompt $/1M
$0.216
Completion $/1M
$0.647
Context
1,048,576 tok
Best provider
150 tok/s · Fireworks
Specs
- Model id
- deepseek/deepseek-v4-flash-vision-exp
- Display name
- DeepSeek: DeepSeek V4 Flash Vision Exp
- Modality
- text+image->text
- Tokenizer
- DeepSeek
- Instruct type
- —
- Context length
- 1,048,576
- Max completion
- 262,144
- Prompt $/1M
- $0.216
- Completion $/1M
- $0.647
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Fireworksfastest | 150 |
| DeepSeek | 89 |
| Novita | 86 |
| DeepInfra | 77 |
| deepseekfastest | — |