DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
AI model by DeepSeek. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. DeepSeek V4 Flash 0731 (Reasoning, Max Effort) is a budget-tier option from DeepSeek at $1.32/M output tokens. Despite the low price, it scores competitively on Coding Index (69.1) and Intelligence Index (34.5) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, DeepSeek V4 Flash 0731 (Reasoning, Max Effort) reports 214 tok/s output speed and 1430ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, DeepSeek V4 Flash 0731 (Reasoning, Max Effort) costs $0.57 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-10-08.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
DeepSeek V4 Flash 0731 (Reasoning, Max Effort)Current | $0.44 | $1.32 | 214 tok/s |
| Claude 3 Haiku | $0.25 | $1.25 | — |
| GPT-5.4 nano (medium) | $0.20 | $1.25 | 171 tok/s |
| GPT-5.4 nano (Non-Reasoning) | $0.20 | $1.25 | 171 tok/s |
| GPT-5.4 nano (xhigh) | $0.20 | $1.25 | 170 tok/s |
| Qwen3 14B (Non-reasoning) | $0.35 | $1.40 | 63 tok/s |