Rankings
What the router actually picks.
Aggregated across every account on this deployment. Each row is the outcome of a scored decision under the caller's constraints, shown with the vendor and model that actually answered; filter by domain to see who wins coding, legal or customer support traffic.
- requests routed
- 18
- tokens
- 212
- success rate
- 100.0%
Tokens per target over time
Daily tokens the router sent to each target, last 7 days.
Share by vendor
Who is behind the tokens the router routed
Meta100%
Share by domain
Which kinds of work reach the router
- General Chat67%
- General22%
- Data Analysis6%
- Legal6%
- Meta Llama 3.3 70B Instructllm-onprem$1.00 / 1M638.4 ms mean100% ok212100.0%
Tokens per target over time
Daily tokens the router sent to each target, last 7 days.
Share by vendor
Who is behind the tokens the router routed
- Meta100%
Share by domain
Which kinds of work reach the router
- General Chat67%
- General22%
- Data Analysis6%
- Legal6%
Rankings count decisions and executed calls made through this platform only; no prompt text is stored and no account is identifiable. Raw numbers: /api/v1/rankings.
Benchmarks
Published quality, next to published price
Independent of this deployment's traffic: the 56 catalogued models that publish Artificial Analysis indexes, ranked, with their vendor list prices. Models with a routing target here are marked.
Price against quality
Blended list price (3 input : 1 output tokens) per million against the intelligence index. Composite of reasoning, knowledge and instruction-following evaluations.
- OpenAI
- Anthropic
- DeepSeek
- Qwen
- Z.ai
- MiniMax
- Other vendors
- Pareto frontier
On the frontier: Claude Fable 5.1 (batch), Claude Opus 5 (batch), GPT-5.6 Sol (batch), Gemini 3.8 Flash (batch), GLM 5.3 Flash, DeepSeek V4 Flash 0731, Ling 3.0 Flash.
Benchmark leaders
Composite of reasoning, knowledge and instruction-following evaluations. 56 of 430 catalogued models publish it; prices are blended 3:1 list prices per million tokens.
