Grok 4.3
Grok 4.3 is a large language model made by SpaceXSI, added to the catalog on 30 Apr 2026. It has a context window of 1,000,000 tokens and costs $1.25 per 1M input tokens and $2.50 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: following detailed instructions, working through multi-step prompts and interpreting image inputs.
Price checked · source: OpenRouter
What Grok 4.3 is
SpaceXSI: Grok 4.3 is a reasoning model designed for agentic workflows and instruction-following tasks. It accepts text, images, and files, and produces text. Its listed output is text, while its inputs include more than text alone.
The model has a context length of 1,000,000 tokens and a maximum output of 900,000 tokens. This capacity can suit tasks involving substantial supplied material or long interactions that need context carried through the prompt and response. The listed limits describe the model’s context and output capacity; they do not guarantee that every file or interaction will fit, since that depends on the amount of material involved.
Grok 4.3 supports tools, structured outputs, response formats, and reasoning. These capabilities suit workflows that combine detailed instructions with supplied text, images, or files, or that need text returned in a structured format. Tool support can be relevant to agentic workflows, though the catalog does not identify particular tools or explain how they are configured. The model may be considered for tasks such as following complex instructions, working through multi-step prompts, interpreting image inputs, and producing structured text. Its broad input types and large context make it relevant to work where a prompt includes varied material, while its text output supports text-based results.
Key features
- Accepts text, image, and file inputs
- Produces text output
- Has a context length of 1,000,000 tokens
- Supports tools, structured outputs, response formats, and reasoning
Typical uses
- Following detailed instructions
- Working through multi-step prompts
- Interpreting image inputs
- Producing structured text
Grok 4.3 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $1.25 | $1.00 |
| Output, per 1M tokens | $2.50 | $2.00 |
| Cached input read, per 1M tokens | $0.20 | $0.16 |
| Web search, per search | $0.005 | $0.005 |
| Input above 200,000 prompt tokens, per 1M | $2.50 | $2.00 |
| Output above 200,000 prompt tokens, per 1M | $5.00 | $4.00 |
| Variant | Model id |
|---|---|
| Batch | x-ai/grok-4.3:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 30 Apr 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0014 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.033 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.043 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.191 |
Grok 4.3 specifications
| Model id | x-ai/grok-4.3 |
|---|---|
| Version | grok-4.3-20260430 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 900,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 30 Apr 2026 |
| Input types | text, image, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Grok 4.3 yet.
Compare Grok 4.3
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.