Grok 4.20 is xAI's latest multimodal reasoning model with strong tool use, structured output support, and a 2M-token context window.
Private|2M context|$1.42/M input|$2.83/M output
xAI
x-ai/ · 16 models
Access 16 xAI models through AnonRouter's privacy-first gateway, including Grok 4.20, Grok 4.20 Multi-Agent, and Grok 4.3. Compare pricing, context windows, and capabilities across xAI's text, video, image, audio routes — every request anonymized, with no payload logging.
Models
16
Modalities
4
Text, Video, Image, Audio
From (input)
$1.00
per 1M tokens
Max context
2M
Private routes
14 / 16
not anonymous-only
Catalog by modality
16 routesText5Video5Image4Audio2
xAI models16
Grok 4.20 Multi-Agent is a variant of xAI Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.
Private|2M context|$1.42/M input|$2.83/M output
Grok 4.3 is xAI's most intelligent and fastest reasoning model with function calling, structured outputs, and a 1M-token context window. Suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy.
Private|1M context|$1.42/M input|$2.83/M output
Grok 4.5 is xAI's intelligent coding model for agentic software engineering and workflow tasks, with function calling, structured outputs, and a 500K-token context window.
Private|500K context|$2.27/M input|$6.80/M output
xAI's fast coding model trained specifically for agentic coding, currently in early access.
Private|256K context|$1.00/M input|$2.00/M output
Image generation model served through Venice.
Private|Unknown context|–|from $0.03/image
Image-to-video generation, served through Venice partner routing.
Private|Unknown context|–|Varies
Image inpainting and editing model served through Venice.
Private|Unknown context|–|from $0.03/edit
Image inpainting and editing model served through Venice.
Private|Unknown context|–|from $0.06/edit
Image generation model served through Venice.
Private|Unknown context|–|from $0.06/image
Image-to-video generation, served through Venice partner routing.
Private|Unknown context|–|Varies
Text-to-video generation, served through Venice partner routing.
Private|Unknown context|–|Varies
Video generation, served through Venice partner routing.
Private|Unknown context|–|Varies
Image-to-video generation, served through Venice partner routing.
Private|Unknown context|–|Varies
Speech-to-text transcription model served through Venice.
Anonymous|Unknown context|$0.00186/min|–
Text-to-speech model with 5 voices served through Venice.
Anonymous|Unknown context|$18.75/1M chars|–