Grok 4.3

SpaceXAI· released 30 Apr 2026

x-ai/grok-4.3
Input / 1M tokens
$1.25
Output / 1M tokens
$2.5
Context window1M tokens

Longest answer: 900K tokens

reads textreads imagereads filetool callingvisionreasoning

About

Grok 4.3 is a reasoning model from SpaceXAI for agentic workflows, instruction-following tasks, and applications requiring high factual performance. It accepts text, image, and file inputs and produces text. The model supports tools and reasoning, with a context window of 1,000,000 tokens and a maximum output of 900,000 tokens. It was released on 2026-04-30. Input costs 1.25 USD per 1M tokens; output costs 2.5 USD per 1M tokens. For builders, the combination of file and image input, tool support, and long context provides the key integration characteristics. Teams can assess the model against text-oriented applications that need multimodal input and reasoning, while considering its distinct input and output prices.

Who it is for

It suits teams building agentic or instruction-following applications that need text, image, or file input. It may fit tasks where high factual performance is a stated requirement.

What is good

  • Accepts text, image, and file inputs.
  • Supports tools and reasoning.
  • Context window is 1,000,000 tokens.
  • Maximum output is 900,000 tokens.

What to know first

  • Input costs 1.25 USD per 1M tokens.
  • Output costs 2.5 USD per 1M tokens.

Verdict

Grok 4.3 combines reasoning and tool support with image and file input. Its large context and output limits may matter for longer tasks, alongside its token pricing.

Details

Lab
SpaceXAIopenrouter.ai · 3 Oct 2026
Context
1,000Kopenrouter.ai · 3 Oct 2026
Input price
$1.25 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$2.5 / 1Mopenrouter.ai · 3 Oct 2026
Max output
900,000 tokensopenrouter.ai · 3 Oct 2026
Inputs
text, image, fileopenrouter.ai · 3 Oct 2026
Open weights
Noopenrouter.ai · 3 Oct 2026

More newest models

See the list