xAI

Mutable alias for xAI's newest speech-to-speech voice agent model; since October 14, 2026 it points to Grok Voice 3.0, after earlier tracking Voice 1.0 and 2.0. Runs over a realtime, OpenAI Realtime-compatible WebSocket in 20+ languages.

Lowest-cost Imagine video tier, added in October 2026, for 1-15 second text- or image-to-video with lip-synced audio. Reaches 1080p by upscaling 720p and lacks the reference, voice and keyframe controls of Video 1.5.

xAI's flagship model as of October 2026, released September 21, 2026 for coding, agents and knowledge work. Offers a 500k-token context, no text output limit and reasoning effort up to xhigh.

August 2026 successor to Grok 4.5, tuned for long-running agents and interactive work, with a 500k-token context. Grok 4.7 replaced it as xAI's top model in September 2026 at the same token prices.

xAI's current image model, released August 7, 2026 and recommended in its docs for image work. Adds a quality setting (low, medium, auto), editing with up to five source images, 1k or 2k output and 21:9 and 5:2 ratios.

xAI's July 2026 model for coding, agentic tasks and knowledge work, with a 500k-token context and reasoning effort up to xhigh. Superseded by Grok 4.6 and then Grok 4.7; the grok-build-latest alias still points here.

xAI's current recommended video model, generally available since June 16, 2026, for text-, image- and reference-to-video. Renders native 1080p clips up to 15 seconds with lip-synced audio, plus first, last and keyframe pinning and up to three preset voices.

Preview slug for Grok Imagine Video 1.5, announced June 3, 2026 as an image-to-video model up to 720p. The model left preview on June 16, and this name now resolves as an alias of grok-imagine-video-1.5.

Dated May 30, 2026 slug from the Grok Imagine Video 1.5 preview, which xAI now lists as an alias of grok-imagine-video-1.5. That preview build was image-to-video only at up to 720p; text-to-video and native 1080p came later.

xAI's low-cost agentic coding model, in public API beta since May 2026, running at 100+ tokens per second with a 256k-token context. It first powered the Grok Build coding agent, which now defaults to Grok 4.7; retired grok-code-fast-1 routes here.

xAI's lower-cost 1M-token-context model from April 2026, with reasoning effort adjustable from none to xhigh (default low) and Batch API support. Retired Grok 4 and 4.1 Fast slugs redirect to it; Grok 4.5 through 4.7 now sit above it.

Grok Voice 1.0, xAI's April 2026 speech-to-speech agent model with background reasoning, tool calling and 25+ languages. Superseded by Grok Voice 2.0 in July and Grok Voice 3.0 in October 2026; no longer in xAI's voice model table.

Higher-quality Imagine image tier above Image 1.0, resolving to the 20260403 build. xAI retires it on November 2, 2026, after which requests are served by Grok Imagine Image 2.0 at low quality.

Dated April 3, 2026 build of Grok Imagine Image Quality, which xAI lists as an alias of that model for pinned output. The model behind it retires on November 2, 2026, with Grok Imagine Image 2.0 as the replacement.

Mutable alias that tracks the newest Grok Imagine Image Quality build, still the 20260403 version as of October 2026. Its target retires on November 2, 2026; xAI points users to Grok Imagine Image 2.0 instead.

xAI's speech-to-text service at /v1/stt (GA April 2026) for batch uploads and WebSocket streaming. It now defaults to grok-voice-transcribe-2.0, covering 38+ languages with diarization, word timestamps, multichannel input and up to 100 keyterms.

Dated March 2, 2026 snapshot of Grok Imagine Image 1.0, the build the grok-imagine-image base name currently points to; pin it to keep output unchanged. Superseded by Grok Imagine Image 2.0.

Non-reasoning variant of xAI's March 2026 Grok 4.20 snapshot, answering directly with a 1M-token context, image input and Batch API support. Superseded by Grok 4.3 and later releases; Grok 4.7 is xAI's flagship as of October 2026.

Reasoning variant of the Grok 4.20 0309 snapshot, which the plain grok-4.20 alias resolves to, with a 1M-token context, tool calling and structured outputs. A previous-generation model, superseded by Grok 4.3 and now by Grok 4.7.

xAI's text-to-speech service at /v1/tts, generally available since March 2026, with no model selector. Covers 20 languages plus auto-detect, built-in voices (eve by default) or cloned custom voices, inline speech tags and WebSocket streaming.