← Compare models
Open all in the calculator — adjust volume and token counts →
DeepSeek V3.2 vs gpt-oss-120b
List-price comparison ·DeepSeek V3.2 details ·gpt-oss-120b details
For a typical workload (100,000 requests / mo), gpt-oss-120b is the cheapest — 77% less than the priciest here ($11.24/mo vs $48.28/mo).
| DeepSeek V3.2 | gpt-oss-120b | |
|---|---|---|
| Input / 1M tokens | $0.269 | $0.037 |
| Output / 1M tokens | $0.400 | $0.170 |
| Typical request (1,200 in + 400 out) | $0.0005 | $0.0001 |
| Context window | 163,840 tokens | 131,072 tokens |
| Max output | 65,536 tokens | 131,072 tokens |
| Quality score | 79/100 | 78/100 |
| Tier | Balanced | Balanced |
| Provider | DeepSeek | OpenAI |
Projected monthly cost
| Requests / mo | DeepSeek V3.2 | gpt-oss-120b |
|---|---|---|
| 1,000 | $0.4828 | $0.1124 |
| 10,000 | $4.83 | $1.12 |
| 100,000 | $48.28 | $11.24 |
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.
gpt-oss-120b
Auto-synced from OpenRouter — no editorial write-up yet.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.