Grok 4.3
xAI · released Apr 30, 2026
- Type
- Proprietary
- Input
- $1.25
- Output
- $2.50
- Cached
- Not published
List price · per 1M tokens · xAI at 1M context · source ↗
Our take
Written Aug 2, 2026Grok 4.3 is xAI's proprietary flagship that handles text, images and files with a one-million-token request limit. It scores highest on coding tasks among its measured categories, though its agentic performance is poor and it comes with a narrow, expensive offer set.
Choose this for long-context workflows needing one million tokens, or for coding-heavy tasks where its measured coding score is its strongest result. Use it if you are already committed to xAI's ecosystem. Skip it if you need reliable agentic task performance, want to self-host, or need a budget tier.
The case for it
- One-million-token request limit, among the largest available and several times the size of most mid-tier models.
- Strong measured coding performance relative to its own text score, with a 44-point spread between the two categories.
- Broad benchmark coverage: eight distinct Arena categories measured in recent July–August 2026 runs.
The case against it
- Agentic task performance is poor and possibly its worst-measured category, with the only negative scores in its entire benchmark set.
- Premium pricing with no budget tier, and the expensive tracked offer doubles the cheaper one for both input and output.
- Proprietary weights with no open licence or download option.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)42nd of 143 · 1442.4
CodingWriting and fixing code on its own
Arena Coding46th of 143 · 1488.1
AgenticPlanning, calling tools, staying on task
Arena Agent (IPS)35th of 36 · −0.144
Also on this board: −0.08 via High (Jul 28, 2026). Read the pair, not the higher one.
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Grok 4.3 placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model16 scoresEvery figure we hold, from 16 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Why this differs from the header. The strip above quotes xAI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $1.25 / $2.50 | 1M | not measured | Unknown | Unknown | Unknown |
| xAI | $1.25 / $2.50 | 1M1M out | not measured | Unknown | Unknown | Unknown |
| xAI | $1.25 / $2.50 | 1M | 90 tok/s | No | Yes30 days | Confirmed |
| xAIpriority tier | $2.50 / $5.00 | 1M | 24 tok/s | No | Yes30 days | Unknown |
xAIAcross the 4 listings we hold: 2 say they do not train on prompts, 0 say they do and 2 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| xAI | |||
| xAI | ✓ | ✓ | ✓ |
| xAIpriority | ✓ | ✓ | ✓ |
Tool calling: 3 of 4 listings say yes, 1 publishes no parameter list. JSON output: 3 of 4 listings say yes, 1 publishes no parameter list. Strict schema: 3 of 4 listings say yes, 1 publishes no parameter list.
Models people weigh against Grok 4.3
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 1 of 4 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 4 listings do not say whether they train on prompts.
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
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file->text
- Catalogue slug
- x-ai-grok-4-3