DeepSeek V4 Pro (Reasoning, Max Effort)
AI model by DeepSeek. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. DeepSeek V4 Pro (Reasoning, Max Effort) is a budget-tier option from DeepSeek at $0.87/M output tokens. Despite the low price, it scores competitively on GPQA Diamond (88.8%) and IFBench (76.5%) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, DeepSeek V4 Pro (Reasoning, Max Effort) reports 71 tok/s output speed and 1021ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, DeepSeek V4 Pro (Reasoning, Max Effort) costs $0.52 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 2026-07-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
DeepSeek V4 Pro (Reasoning, Max Effort)Current | $0.43 | $0.87 | 71 tok/s |
| MiMo-V2.5-Pro | $0.43 | $0.87 | 63 tok/s |
| Trinity Large Thinking | $0.23 | $0.88 | 142 tok/s |
| Llama 4 Maverick | $0.31 | $0.85 | 102 tok/s |
| Agnes 2.5 Pro Alpha | $0.45 | $0.90 | 134 tok/s |
| GLM-4.6V (Reasoning) | $0.30 | $0.90 | 0 tok/s |