SpaceXAI: Grok 4.3 (batch)
by xAItext+image+file->text1 endpoint
Overview
Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning can be configured between none/low/medium/high (default low) effort levels.
It supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.
Capabilities
Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Top-P sampling
Deterministic seed
Log probabilities
Modalities
Input
TextImageFile
Output
Text
Technical Specifications
Context Window
1M tokens
Max Output
900K tokens
Tokenizer
Grok
Supported Parameters
include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetool_choicetoolstop_logprobstop_p
Pricing
Per 1M tokens
Input$1.00
Output$2.00
Cache read$0.16
Added
April 30, 2026
Last synced 9/21/2026