SpyBara
Go Premium

Documentation 2026-07-23 16:58 UTC to 2026-07-25 10:59 UTC

3 files changed +7 −19. View all changes and history on the product overview
2026
Sat 25 10:59 Thu 23 16:58 Wed 22 21:00 Tue 21 20:58 Sat 18 00:00 Thu 16 09:01 Tue 14 21:01 Sun 12 00:02 Thu 9 13:03 Wed 8 18:58 Mon 6 22:58 Sat 4 20:00 Thu 2 16:59 Wed 1 19:00
Details

131const url = `wss://api.x.ai/v1/realtime?model=${MODEL}`;131const url = `wss://api.x.ai/v1/realtime?model=${MODEL}`;

132```132```

133 133 

134| Model | Description | |134| Model | Description |

135|-------|-------------|---|135|-------|-------------|

136| `grok-voice-think-fast-1.0` | Flagship voice model | |136| `grok-voice-latest` | Alias that tracks the newest voice model |

137| `grok-voice-fast-1.0` | Legacy voice model | deprecated |137| `grok-voice-think-fast-1.0` | Flagship voice model |

138 

139> [!NOTE]

140>

141> `grok-voice-latest` always points to the newest model (currently `grok-voice-think-fast-1.0`).

142 138 

143## Session Parameters139## Session Parameters

144 140 


1631* **Remove workaround prompting.** Prompt hacks and edge-case fixes needed for GPT models are unnecessary. Strip out instructions added solely to patch bugs or limitations of the previous model.1627* **Remove workaround prompting.** Prompt hacks and edge-case fixes needed for GPT models are unnecessary. Strip out instructions added solely to patch bugs or limitations of the previous model.

1632* **Reasoning is enabled by default.** The default `reasoning.effort` is `"high"` for complex multi-step instructions, nuanced tone, and ambiguous queries. Set it to `"none"` to disable reasoning.1628* **Reasoning is enabled by default.** The default `reasoning.effort` is `"high"` for complex multi-step instructions, nuanced tone, and ambiguous queries. Set it to `"none"` to disable reasoning.

1633 1629 

1634#### Deprecated model

1635 

1636This model remains available for existing integrations, but new applications should use `grok-voice-latest`.

1637 

1638* `grok-voice-fast-1.0`: Legacy voice model with similar prompting characteristics to GPT realtime models.

1639 

1640The deprecated model follows the same client and server event flow as `grok-voice-latest`, so existing integrations can pin to it while migrating.

1641 

1642> [!NOTE]1630> [!NOTE]

1643>1631>

1644> `grok-voice-latest` always points to the newest model (currently `grok-voice-think-fast-1.0`). Pin to a versioned model name in production for stability.1632> `grok-voice-latest` always points to the newest model (currently `grok-voice-think-fast-1.0`). Pin to a versioned model name in production for stability.

rate-limits.md +2 −2

Details

39| grok-4.20-0309-non-reasoning | T0: 37, T1: 50, T2: 75, T3: 125, T4: 208 | T0: 10M, T1: 15M, T2: 25M, T3: 45M, T4: 85M |39| grok-4.20-0309-non-reasoning | T0: 37, T1: 50, T2: 75, T3: 125, T4: 208 | T0: 10M, T1: 15M, T2: 25M, T3: 45M, T4: 85M |

40| grok-build-0.1 | T0: 37, T1: 50, T2: 75, T3: 125, T4: 208 | T0: 10M, T1: 15M, T2: 25M, T3: 45M, T4: 85M |40| grok-build-0.1 | T0: 37, T1: 50, T2: 75, T3: 125, T4: 208 | T0: 10M, T1: 15M, T2: 25M, T3: 45M, T4: 85M |

41| grok-4.20-multi-agent-0309 | T0: 9, T1: 12, T2: 18, T3: 31, T4: 56 | T0: 2.5M, T1: 3.7M, T2: 6.2M, T3: 11M, T4: 21M |41| grok-4.20-multi-agent-0309 | T0: 9, T1: 12, T2: 18, T3: 31, T4: 56 | T0: 2.5M, T1: 3.7M, T2: 6.2M, T3: 11M, T4: 21M |

42| grok-imagine-image | 5 | — |

43| grok-imagine-image-quality | 5 | — |42| grok-imagine-image-quality | 5 | — |

44| grok-imagine-video | 10 | — |43| grok-imagine-image | 5 | — |

45| grok-imagine-video-1.5 | 10 | — |44| grok-imagine-video-1.5 | 10 | — |

45| grok-imagine-video | 10 | — |

46 46 

47### What counts toward TPM47### What counts toward TPM

48 48 

Details

14 14 

15* `session` (object | null) — Optional initial session configuration to bind to the client secret. This JSON value is stored alongside the secret and applied when the WebSocket connection opens.15* `session` (object | null) — Optional initial session configuration to bind to the client secret. This JSON value is stored alongside the secret and applied when the WebSocket connection opens.

16 16 

17 * `model` ("grok-voice-latest" | "grok-voice-think-fast-1.0" | "grok-voice-fast-1.0") — Model to use for the session. Use grok-voice-latest for the best experience.17 * `model` ("grok-voice-latest" | "grok-voice-think-fast-1.0") — Model to use for the session. Use grok-voice-latest for the best experience.

18 18 

19 * `reasoning` (object) — Reasoning settings for models that support them.19 * `reasoning` (object) — Reasoning settings for models that support them.

20 20