DeepSeek V3 (Dec '24)
AI model by DeepSeek. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. DeepSeek V3 (Dec '24) is a budget-tier option from DeepSeek at $0.89/M output tokens. Despite the low price, it scores competitively on Coding Index (23.0) and Intelligence Index (14.2) — 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 (Dec '24) costs $0.45 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 (Dec '24)Current | $0.36 | $0.89 | — |
| GLM-4.6V (Non-reasoning) | $0.30 | $0.90 | 72 tok/s |
| Agnes 2.5 Pro Alpha | $0.45 | $0.90 | 202 tok/s |
| Trinity Large Thinking | $0.25 | $0.90 | 314 tok/s |
| GLM-4.6V (Reasoning) | $0.30 | $0.90 | 55 tok/s |
| MiMo-V2.5-Pro | $0.43 | $0.87 | 35 tok/s |