Inference Provider Metrics

Every pairing of five per-endpoint metrics:

Up to 8 highlighted · click any gray curve, dot, or table row to highlight

Pairwise charts

All providers (table view)

Models

One row per model in the competitive arena. Providers counts the providers serving the model as shown on this page — the published set the charts and provider table draw from — while Ctx served and Floor $/M are the values context fidelity and price ×floor normalize to (the largest context and cheapest blended price across all of the model's arena endpoints, before this page's provider filters). A bold below 100% under % of spec marks a model whose advertised context window no provider actually serves. Unlike the provider table, these rows are not clickable — the model and weights links are the only interactive elements, so a click never changes chart emphasis.

Reading & caveats

Price (× floor)
Blended price at an assumed 10:1 input:output mix, divided per model by the cheapest endpoint's blend. 1.0× = that provider is the floor. Log scale, clamped at 8×.
Context fidelity
Endpoint context ÷ the largest context any provider serves for that model. Low values are cut-down deployments (8K–262K of a 1M-context model). A capacity signal that complements the measured speed index. The denominator is the largest context any provider serves, not the model's advertised spec — see the for the models where those differ ( of today).
Reliability
1-day uptime per endpoint, clamped below at 80%. Medians in scatter panels; full endpoint spread in curves and ECDFs.
Speed index
Endpoint p50 throughput ÷ the fastest endpoint p50 for that model, so 100% = the fastest host of that model, comparable across models. OpenRouter-measured over a trailing 30-minute window sampled once daily at pull time — routed production traffic, not a clean-room benchmark. Raw tok/s and p90 latency appear in tooltips and the table. Provider medians are suppressed when fewer than 3 endpoints and under half the catalog carry throughput data; endpoints without throughput are omitted from speed panels only.
Curves
In endpoint-level panels each provider's endpoints are sorted by the x-metric and connected — a profile across their catalog, not a time series.
First parties
Google, Amazon Bedrock, Azure, Anthropic, Alibaba appear via their own or licensed models; their 1.0× price index reflects single-source pricing power, not cheapness.

Auto-updates daily from the OpenRouter public API (~13:10 UTC).