Grok 4.3
xAI · released Apr 30, 2026
- Type
- Closed
- Input
- $1.25
- Output
- $2.50
- Cached
- None held
List price · per 1M tokens · xAI at 1M context · machine-readable source ↗
Our take
Written Sep 30, 2026Grok 4.3 is a hosted-only model: we list no download for it, so using it means choosing a host. Its one standout result is tool use, where it places 7th of 55 on Arena Agent · Tool use as of 25 Sep 2026, while its other agentic and reasoning standings sit near the bottom of their fields.
Reach for it when the job is tool calling — picking the right tool and not inventing one — which is the one board where it places well. It also takes text, images and files in a single request, so a long document need not be split up first, though reliable recall across all of it is unverified in our data. Skip it if you need measured coding, reasoning or agentic task completion, where it sits near the bottom of every field we hold.
The case for it
- 7th of 55 on Arena Agent · Tool use as of 25 Sep 2026, a board that records whether the model calls the right tool and does not invent one.
- The request capacity is large enough for long documents to be handled in one go, though reliable recall across all of it is unverified in our data.
- Text, image and file input with written output, so a document or screenshot does not have to be described in words first.
The case against it
- 58th of 58 on LiveBench as of 25 Jun 2026 and 58th of 58 on LiveBench Agentic Coding as of 25 Jun 2026 — last in both fields.
- 54th of 55 on Arena Agent (interactive problem solving) as of 25 Sep 2026, so agentic task completion is weak despite the tool-use result.
- 58th of 168 on Arena Text (overall) as of 25 Sep 2026 and 49th of 168 on Arena Creative Writing as of 25 Sep 2026, boards that record which answer people preferred rather than whether it was correct.
How good is it?
A chat model for answering questions and calling tools, though it struggles with long multi-step tasks and changing course mid-way.
- calling tools to carry out requestsArena Agent · Tool use · 7th of 55
- multi-step work it carries out for youArena Agent · 54th of 55
- changing course when you give new instructionsArena Agent · Steerability · 52nd of 55
- getting back on track after a step failsArena Agent · Recovery · 54th of 55
EverydayGeneral questions and everyday reasoning
Arena Text (overall)58th of 168 · 1442
CodingWriting and fixing code on its own
Arena Coding63rd of 168 · 1488
AgenticPlanning, calling tools, staying on task
Arena Agent54th of 55 · −0.203
Also on this board: −0.116 (Sep 5, 2026). Read the pair, not the higher one.
WritingDrafting and rewriting prose
Arena Creative Writing49th of 168 · 1423
Placings on Arena's agent boards, from live sessions people ran themselves. A model can lead on one of these and sit mid-field on the others.
Boards this model appears on that none of the ratings above are built on.
Every published score for this model20 scoresEvery figure we hold, from 20 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Where to rent it
Prices checked between 59 min and 1 hour ago — each listing carries its own date.
xAI, direct and through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts xAI on 1M of context.
- per 1M tokens
- $1.25 in / $2.50 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $1.25 / $2.50checked 1 hour ago | 1M | not measured | Unknown | Unknown | Unknown |
| xAIDirect and through OpenRouter | $1.25 / $2.50checked 59 min ago directchecked 1 hour ago through OpenRouter | 1M1M max reply direct900K max reply through OpenRouter | 88 tok/sthrough OpenRouter | DirectUnknownThrough OpenRouterNo | DirectUnknownThrough OpenRouterYes30 days | DirectUnknownThrough OpenRouterConfirmed |
| xAIpriority tierThrough OpenRouter | $2.50 / $5.00checked 1 hour ago | 1M900K max reply | 75 tok/s | No | Yes30 days | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts (1 of them only through OpenRouter), 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check (1 of them only through OpenRouter); the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| xAIDirect and through OpenRouter | ✓ | ✓ | ✓ |
| xAIpriorityThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
Models people weigh against Grok 4.3
When we formed this view
Recent changes
Each date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts, and 1 answers only through OpenRouter, not for its own listing.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text, images and documents in, text out
- Catalogue slug
- x-ai-grok-4-3