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.
MARA currently ranks first at 236.0 tok/s via mara.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route MARA mara | Output speed236.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Friendli friendli | Output speed138.5 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route Parasail parasail/fp8 | Output speed126.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route StreamLake streamlake | Output speed125.5 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Weights & Biases wandb/fp8 | Output speed84.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route DigitalOcean digitalocean | Output speed65.0 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route Inceptron inceptron/fp8 | Output speed58.0 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route MiniMax minimax/fp8 | Output speed57.0 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route DeepInfra deepinfra/fp8 | Output speed55.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Venice venice | Output speed51.5 tok/s | Speed measurements
| Endpoint details
|
| #11 | Provider / route SiliconFlow siliconflow/fp8 | Output speed50.0 tok/s | Speed measurements
| Endpoint details
|
| #12 | Provider / route MiniMax minimax/highspeed | Output speed48.0 tok/s | Speed measurements
| Endpoint details
|
| #13 | Provider / route Chutes chutes/fp8 | Output speed37.0 tok/s | Speed measurements
| Endpoint details
|
| #14 | Provider / route Phala phala | Output speed36.0 tok/s | Speed measurements
| Endpoint details
|
| #15 | Provider / route NovitaAI novita/fp8 | Output speed9.0 tok/s | Speed measurements
| Endpoint details
|
| #16 | Provider / route AtlasCloud atlas-cloud/fp8 | Output speed8.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
MiniMax M2.5 endpoint guide
16 of 16 MiniMax M2.5 endpoints currently have the published data required for this ranking. MARA leads at 236.0 tok/s via mara. 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.
Friendli currently ranks second at 138.5 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.
MiniMax M2.5 has 16 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.
