← Compare models
Open all in the calculator — adjust volume and token counts →
Claude Sonnet 4.5 (batch) vs DeepSeek V3.2
List-price comparison ·Claude Sonnet 4.5 (batch) details ·DeepSeek V3.2 details
For a typical workload (100,000 requests / mo), DeepSeek V3.2 is the cheapest — 90% less than the priciest here ($48.28/mo vs $480.00/mo).
| Claude Sonnet 4.5 (batch) | DeepSeek V3.2 | |
|---|---|---|
| Input / 1M tokens | $1.50 | $0.269 |
| Output / 1M tokens | $7.50 | $0.400 |
| Typical request (1,200 in + 400 out) | $0.0048 | $0.0005 |
| Context window | 1M tokens | 163,840 tokens |
| Max output | 64k tokens | 65,536 tokens |
| Quality score | 90/100 | 79/100 |
| Tier | Balanced | Balanced |
| Provider | Anthropic | DeepSeek |
Projected monthly cost
| Requests / mo | Claude Sonnet 4.5 (batch) | DeepSeek V3.2 |
|---|---|---|
| 1,000 | $4.80 | $0.4828 |
| 10,000 | $48.00 | $4.83 |
| 100,000 | $480.00 | $48.28 |
Claude Sonnet 4.5 (batch)
Auto-synced from OpenRouter — no editorial write-up yet.
DeepSeek V3.2
Extremely competitive coding and reasoning benchmarks at a fraction of commercial-API pricing — strong default for cost-sensitive batch workloads.
Open-weight hosting means latency and uptime vary by inference provider (DeepInfra, Fireworks, etc.) — pin a provider or add fallbacks for production SLAs.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.