Choose a model to open its comparison page.
Grok 4.6 benchmark, API pricing, and provider data cover 1 API provider, with prices starting at $0.375/M. The page also shows measured API speed and first-token latency.
Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
26 metrics
2 metrics
2 metrics
10 metrics · Rated
14 metrics · Estimated
4 metrics · Estimated
6 metrics · Provisional
0 metrics · No data
0 metrics · No data
1 metric · No data
0 metrics · No data
Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
xAI xai/zdr | $2/M | $6/M | 99.9% | — | — | 500K tokens / — |
xAI xai/zdr/priority | $4/M | $12/M | 99.9% | — | — | 500K tokens / — |
xAI xai | $2/M | $6/M | 99.8% | — | — | 500K tokens / — |
xAI xai/priority | $4/M | $12/M | 99.8% | — | — | 500K tokens / — |
Grok 4.6 API pricing starts at $0.375/M from 无限智能.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 99% | grok-4.6 | GROK-反代4.6🀄️-x0.15-对话 | -81%$0.375/M Cache read$0.037/M | -62%$2.25/M | — | — | — |
