DeepSeek V3.1 (Non-reasoning)
AI model by DeepSeek. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. DeepSeek V3.1 (Non-reasoning) is a budget-tier option from DeepSeek at $1.68/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Cost model. For a workload of 1M input tokens + 100K output tokens, DeepSeek V3.1 (Non-reasoning) costs $0.74 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 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
DeepSeek V3.1 (Non-reasoning)Current | $0.57 | $1.68 | — |
| GPT-4.1 mini | $0.40 | $1.60 | 79 tok/s |
| Qwen3.7 Plus | $0.40 | $1.60 | 56 tok/s |
| Qwen3 VL 235B A22B Instruct | $0.40 | $1.60 | 51 tok/s |
| GLM-4.5V (Non-reasoning) | $0.60 | $1.80 | 70 tok/s |
| GLM-4.5V (Reasoning) | $0.60 | $1.80 | 72 tok/s |