Skip to content

Highest Output-Speed Command R+ (08-2024) Inference Providers

Ranks providers by their recent typical output speed in tokens per second. Providers without enough recent data remain visible after ranked rows.

Cohere currently ranks first at 42.0 tok/s via cohere.

Provider options:
1
Ranked:
1
Metric:
Output speed

Highest output speed endpoint ranking

Highest Output-Speed Command R+ (08-2024) Inference Providers
RankProvider / routeOutput speedSpeed measurementsEndpoint details
#1Provider / route
Coherecohere
Output speed42.0 tok/sSpeed measurements
500-token response
12.05 s
Response starts
0.15 s
Output speed
42.0 tok/s
Endpoint details
Input price
$2.5 / 1M tokens
Output price
$10 / 1M tokens
Uptime (30 min)
Insufficient recent data
Context
128K

Endpoint data fetched .

Command R+ (08-2024) endpoint guide

How to interpret the Highest Output-Speed Command R+ (08-2024) Inference Providers

1 of 1 Command R+ (08-2024) endpoint currently have the published data required for this ranking. Cohere leads at 42.0 tok/s via cohere. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.

How generation throughput is ranked

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.

Compare Cohere with the next option

Only 1 route currently qualifies, so the rank alone provides limited choice. Review every visible endpoint for price, speed, uptime, context length, and route-specific configuration.

Use the route, not only the provider name

Command R+ (08-2024) has 1 published provider option, 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.