← Compare models
Open all in the calculator — adjust volume and token counts →
Claude Sonnet 4.6 vs gpt-oss-120b
List-price comparison ·Claude Sonnet 4.6 details ·gpt-oss-120b details
For a typical workload (100,000 requests / mo), gpt-oss-120b is the cheapest — 99% less than the priciest here ($11.24/mo vs $960.00/mo).
| Claude Sonnet 4.6 | gpt-oss-120b | |
|---|---|---|
| Input / 1M tokens | $3.00 | $0.037 |
| Output / 1M tokens | $15.00 | $0.170 |
| Typical request (1,200 in + 400 out) | $0.0096 | $0.0001 |
| Context window | 1M tokens | 131,072 tokens |
| Max output | 128k tokens | 131,072 tokens |
| Quality score | 88/100 | 78/100 |
| Tier | Balanced | Balanced |
| Provider | Anthropic | OpenAI |
Projected monthly cost
| Requests / mo | Claude Sonnet 4.6 | gpt-oss-120b |
|---|---|---|
| 1,000 | $9.60 | $0.1124 |
| 10,000 | $96.00 | $1.12 |
| 100,000 | $960.00 | $11.24 |
Claude Sonnet 4.6
Strong price-to-performance for production agents: reliable tool use, structured JSON output, and solid coding ability at roughly a fifth of Opus's cost.
Can still misstep on the hardest multi-step reasoning chains where Opus would succeed — budget for occasional escalation to a flagship model.
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.