Start typing to search.
Ranks providers by their recent typical output speed in tokens per second. Providers without enough recent data remain visible after ranked rows.
| Rank | Provider / route | Pricing | Benchmarks | API support |
|---|---|---|---|---|
| #1 | Provider / route 1M contextunknown128K max output | Pricing
| Benchmarks
| API support
|
| #2 | Provider / route 1M contextunknown128K max output | Pricing
| Benchmarks
| API support
|
| #3 | Provider / route 1M contextunknown128K max output | Pricing
| Benchmarks
| API support
|
| #4 | Provider / route 1M contextunknown128K max output | Pricing
| Benchmarks
| API support
|
| #5 | Provider / route 1M contextunknown128K max output | Pricing
| Benchmarks
| API support
|
| — | Provider / route 1M contextunknown128K max output | Pricing
| Benchmarks
| API support
|
Endpoint data fetched .
Claude Opus 5 endpoint guide
5 of 6 Claude Opus 5 endpoints currently have the published data required for this ranking. Azure leads at 67.5 tok/s via azure/us-east-2. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.
The output-speed ranking compares recent median generated tokens per second. It favors routes that complete long generations quickly, while first-token latency remains a separate measure of how responsive the endpoint feels at the beginning.
Anthropic currently ranks second at 66.0 tok/s. Compare that gap with input and output price, response-start time, output speed, 30-minute uptime, context length, and the exact route before deciding whether first place is meaningful for your workload.
Claude Opus 5 has 6 published provider options, and performance data is matched to each exact OpenRouter routing tag. Different quantization, context, regional deployment, or provider configuration can change price and behavior even when the underlying model name is identical.
