Grok API

grok-voice-3.0 is available with speech-to-speech at the same price as Grok Voice 2.0, and grok-voice-latest now points to grok-voice-3.0. Grok Voice 2.0 is deprecated.

The grok-voice-2.0 model is deprecated. Callers should set model to grok-voice-3.0 or grok-voice-latest, which are available at the same price.

grok-voice-transcribe-1.0 is deprecated and reaches end of life on October 2, 2026. Until then all requests to that slug route to grok-voice-transcribe-2.0 at the same price, with higher accuracy.

A new safety_identifier request field accepts an opaque end-user identifier assigned by your application, letting SpaceXAI attribute a policy violation to one of your end users rather than your API key. It is supported on Chat Completions, the Responses API, deferred chat completions, the Batch API, and the gRPC GetCompletionsRequest, and the legacy user field is still accepted.

Video generation now accepts a last frame and keyframes. The rest of the release is changelog and release-workflow housekeeping.

Grok 4.7 is available on the xAI API as grok-4.7 with a 500k context window, low through xhigh reasoning effort (default high), and pricing of $2/$0.50/$6 per 1M tokens (input/cached input/output) below 200k prompt tokens and $4/$1/$12 above. On the Responses API it always returns reasoning.encrypted_content even when include does not list it.

grok-voice-transcribe-2.0 is now available for speech to text alongside grok-voice-transcribe-1.0, which remains the default.

On November 2, 2026, grok-imagine-image-quality is retired, with requests to the slug served by grok-imagine-image-2.0 with quality set to low at a lower per-image price and no change to the request or response shape. grok-imagine-image (1.0) is unaffected.

The grok-imagine-image-2.0 quality parameter now accepts auto, with the default moving from medium to auto, which uses low for generation and medium for editing. Image editing accepts up to 5 source images per request instead of 3, and both generation and editing add 21:9 and 5:2 aspect ratios.

The SDK now supports reference audio for video generation, a generate_audio option, and 1080p resolution. Also added a quality parameter for image generation, an image_generation server-side tool, and automatic tool_call_id assignment when replaying tool outputs via chat.append(response).

Accept xhigh reasoning_effort and add grok-4.6 to ChatModel.

Grok 4.6 is available on the xAI API with a 500k context window, text and image inputs with text-only output, and no text output limit. Pricing is $2 / $0.50 / $6 per 1M tokens (input / cached input / output) below 200k prompt tokens and $4 / $1 / $12 above, with reasoning effort supporting low, medium, high (default), and xhigh.

Grok Bot is now available, offering durable AI teammates that work on a persistent cloud computer with messaging, approvals, connectors, and routines.

Grok 4.5 is now available in the API console for EU users.

Speech to Text now accepts a vad_threshold parameter as a streaming query param and batch multipart field to tune the voice-activity gate that skips non-speech audio. Lower values transcribe quieter or noisier speech for narrowband telephony, and 0 disables the gate.

grok-imagine-video-1.5 now supports text-to-video, image-to-video, and reference-to-video with optional preset voices, with native 1080p for text-to-video and image-to-video. Text-to-video on this model runs as text-to-image then image-to-video.

grok-voice-think-fast-2.0 is now available with speech to speech, and grok-voice-latest will route to this model starting August 5, 2026.

Grok 4.5, aimed at coding, agentic tasks, and knowledge work, is now available on the xAI API at $2 per 1M input tokens and $6 per 1M output tokens. Reasoning effort is configurable across low, medium, and high, defaulting to high.

Added service tier support for priority processing.

Imagine file storage is now available, and image and video generation endpoints accept file-ID inputs. The files client now supports public file URLs and list filtering.