Compute research · pulled 2026-07-07 · openrouter.ai public API
OpenRouter provider landscape — pairwise view
Every pairing of price (blended $/M as a multiple of the model's cheapest endpoint),
context fidelity (share of the model's maximum context this provider actually serves),
reliability (1-day uptime), and model support (models served).
Scope: the competitive arena — 88 models with ≥3 endpoints; 47 providers, 572 endpoints.
Diagonals show each provider's distribution (ECDF) across its endpoints.
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). Proxy for serving capability — OpenRouter does not expose per-endpoint throughput publicly.
- Reliability
- 1-day uptime per endpoint, clamped below at 80%. Medians in scatter panels; full endpoint spread in curves and ECDFs.
- 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.
All providers (table view)