Head-to-Head Pricing Benchmark
Side-by-side pricing and context window comparison for production model selection.
Default Recommendation (120M input + 60M output)
TheDrummer: Rocinante 12B is lower-cost for the default monthly workload scenario.
Adjust the workload in the calculator below to see a live recommendation for your usage.
| Metric | Qwen: Qwen3.5-35B-A3B | TheDrummer: Rocinante 12B |
|---|---|---|
| Developer | qwen | thedrummer |
| Context Window | 262,144 | 32,768 |
| Max Output Tokens | 65,536 | 32,768 |
| Input Cost / 1M Tokens | $0.1625 | $0.1700 |
| Output Cost / 1M Tokens | $1.30 | $0.4300 |
| Projected Monthly Cost | $98 | $46 |
| Vision | ✅ Yes | ❌ No |
| Tool Calling | ✅ Yes | ✅ Yes |
| Structured Output | ✅ Yes | ✅ Yes |
| Reasoning | ✅ Yes | ❌ No |
| Web Search | ❌ No | ❌ No |
| Tokenizer | Qwen3 | Qwen |
| MMLU Score | N/A | N/A |
Price History
Current Input / 1M
$0.1625
Current Output / 1M
$1.30
Price History
Current Input / 1M
$0.1700
Current Output / 1M
$0.4300
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
Adjust your workload to see projected monthly costs.
Qwen: Qwen3.5-35B-A3B
$98
per month
TheDrummer: Rocinante 12B
$46
per month
Lower costLive Recommendation
TheDrummer: Rocinante 12B is lower-cost at 120M input + 60M output tokens/month.
Continue evaluation with more “A vs B pricing” decision pages.