Analysis
OpenAPI Breaking-Change Detection
Given two OpenAPI specifications, identify removed operations, required-field changes, narrowed enums, response changes, and other client-breaking differences.
Engineering & ProductPer spec
Not benchmarked
No result on this tier
Token profile pending
— /100K
Run this tier to add it
—
Gemma 4 E4B IT
E4B · Off-the-shelf
1,002 in · 1,198 out · 19.34s p50
$14.75 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
61%
Cheapest
Qwen3 235B A22B
235B (22B active) · Off-the-shelf
908 in · 1,403 out · 19.90s p50
$297 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $0.4550 input · $1.82 output /1M
TrustedRouter · $0.6330 input · $2.11 output /1M
80%
GPT-5.4
Hosted · Off-the-shelf
899 in · 1,609 out · 13.06s p50
$2638 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $2.50 input · $15.00 output /1M
TrustedRouter · $2.64 input · $15.82 output /1M
88%
Best accuracy
All 12 model results and methodology
Generated 100/100 examples
| Model | Tier | Quality | Judged | Scenario cost |
|---|---|---|---|---|
| Nemotron Nano 9B v2 | small | 25% | 100/100 | $45.25 |
| Qwen3 235B A22B | mid | 80% | 100/100 | $297 |
| DeepSeek V3 | mid | 72% | 100/100 | $124 |
| Mistral Large 2407 | mid | 71% | 100/100 | $204 |
| Arcee Trinity Large Thinking | mid | 20% | 100/100 | $166 |
| GPT-5.4 | frontier | 88% | 100/100 | $2638 |
| Claude Opus 4.7 | frontier | 65% | 100/100 | $5530 |
| Gemini 3.1 Pro Preview | frontier | 15% | 100/100 | $2524 |
| Gemma 4 E4B IT | small | 61% | 100/100 | $14.75 |
| Granite 4.1 8B | small | 31% | 100/100 | $14.88 |
| Ministral 8B Instruct 2410 | small | 9% | 100/100 | $25.18 |
| Qwen3 4B Instruct 2507 | small | 20% | 100/100 | $114 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T08:57:02.487Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock