Loading…
Loading…
Provider comparison
Choose an exact model configuration, then compare the providers measured for it. See token prices, output speed, first-token latency and context together.
Alibaba
1 provider · 1 measured endpoint
Only one provider is covered for this configuration. This is the available measurement, not a ranking of the whole market.
One row per endpoint. USD per 1M tokens; blended price uses a 3:1 input/output mix. Missing measurements sort last.
| Provider | BlendedUSD / 1M tokens | InputUSD / 1M tokens | OutputUSD / 1M tokens | Output speedtokens / second | First tokenseconds | Contexttokens | Compare endpoint |
|---|---|---|---|---|---|---|---|
| Alibaba CloudProvider website | $3.00 | $2.00 | $6.00 | 52.6 | 3.76 s | 984K |
Prices, output speed, time to first token and context come from the same provider endpoint. We do not combine one host’s cheapest tier with another tier’s fastest result. Provider and configuration names retain the source’s labels.
Blended token price describes a fixed token mix. It is different from AA’s measured cost per evaluation task and from the cost of your workload. Add endpoints to compare your own input/output mix.
These are published measurements, not guarantees of availability or production performance. Provider websites are external destinations; measurements come from Artificial Analysis. Read the methodology.
Using saved data exported 11 Nov 2026, 10:48 UTC.