Intelligence Index
0140.3
> 89% OF MODELS
DeepSeek
DeepSeek V4 Flash
Updated: July 2026
DeepSeek's efficient 1M-context MoE model for fast inference, strong reasoning, and agent workflows.
Specifications
- Context
- 1M
- Input
- $0.14/M
- Output
- $0.28/M
Capabilities
THINKINGCODINGWEB
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Qwen3 235B A22B Thinking 2507 | Qwen | 262K | $0.1495/M | $1.495/M |
| Qwen3.6 35B A3B | Qwen | 262K | $0.15/M | $1/M |
| Mistral Small 4 | MistralAI | 262K | $0.15/M | $0.6/M |
| Ministral 3 8B 2512 | MistralAI | 262K | $0.15/M | $0.15/M |
| DeepSeek Chat v3.1 | DeepSeek | 33K | $0.15/M | $0.75/M |
Performance Metrics
Coding Index
0256.2
> 83% OF MODELS
Agentic Index
0331.1
> 88% OF MODELS
Average Response Performance
- Output Speed
- 112.1 tok/s
- Time To First Token
- 1.25s
- Time To First Answer Token
- 51.35s
- End To End Response Time
- 55.81s
DATA SOURCE: Artificial Analysis