Grok 4.3 (batch)
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.
x-ai/grok-4.3:batch
- Context
- 1M tokens
- Completion cap
- 900,000
- Tools
- Yes
- JSON
- Yes
- Released
- 2026-04-30
Call it from Geek Hub
Same OpenAI SDK. Change the base URL and the model id.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "x-ai/grok-4.3:batch",
"messages": [{"role": "user", "content": "Hola"}]
}'Get an API keyFrequently asked questions
- What is Grok 4.3 (batch)?
- 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. Grok 4.3 (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: x-ai/grok-4.3:batch.
- Is Grok 4.3 (batch) free?
- No. Input is $1.0901 per 1M tokens and output is $2.1801 per 1M tokens on Geek Hub (markup included).
- What is the context length of Grok 4.3 (batch)?
- Grok 4.3 (batch) has a 1M tokens context window. It supports up to 900,000 completion tokens.
- Does Grok 4.3 (batch) support tool calling and structured outputs?
- Grok 4.3 (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
- When was Grok 4.3 (batch) released?
- Grok 4.3 (batch) was released on 2026-04-30.
More models from xAI
Grok 4.20Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict
Grok 4.20 Multi-AgentGrok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordina
Grok 4.3Grok 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 r
Grok 4.5Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
Grok 4.6Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).
Grok 4.7Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, veri