Get started

Grok 4.3 (batch)

Sold by 4 sellers, timed at 74.8 tok/s, scored 42.2 on the Coding Index, on 25 Design Arena boards, and with results on 2 openly licensed boards.

retrieved sha256 · 0bb53a77713f

Models/SpaceXAI/Grok 4.3 (batch)USD per 1M tokens · as OpenRouter routes it
x-ai/grok-4.3:batchSpaceXAI · batch variant · Grok tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$1.00per 1M tokens
Output$2.00per 1M tokens
Cached input$0.16per 1M tokens
Context1M1,000,000 tokens
The other meters · every further rate the list publishes for this id, in the unit it states1 meter
Web search$0.005per search
Over the base window · the rate the list gives once a prompt is longer than a thresholdin / out per 1M tokens
Prompts over 200K tokens$2.00 / $4.00cached $0.32
What the list says · the fields OpenRouter publishes for this id11 fields
AuthorSpaceXAI
Listed
Canonical idx-ai/grok-4.3-20260430
Context1,000,000 tokens
Max output900,000 tokens
Modalitiestext, image, file → text
TokenizerGrok
Reasoningoptional, on by default · effort high, medium, low, none, low by default
Moderationnot moderated by OpenRouter
Variantbatch
Other listingbase listing

What sellers charge

4 sellers · 2x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $1.25 at xAI to $2.50 at xAI. The $1.00 listed is the cheapest on offer; 4 sellers are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

12,801 requests · 3 endpoints · 30-minute window
Throughput74.8 tok/sMedian output rate, weighted across the 3 endpoints serving it by the requests each answered.the speed board
First token1.09sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread65 to 75The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

4 priced · 3 timed · cheapest first
  1. xAIxai$1.25$2.50$0.20not declared900knot matchednonenonenot matched98.88%
  2. xAIxai/zdr$1.25$2.50$0.20not declared900knot matchednonenonenot matched99.58%
  3. xAIxai/priority$2.50$5.00$0.40not declared900knot matchednonenonenot matchedno reading
  4. xAIxai/zdr/priority$2.50$5.00$0.40not declared900knot matchednonenonenot matched100%
  5. xAInot matchednot matchednot matchednot matchedno offer75 tok/s381.13s9,868 reqno offer
  6. xAInot matchednot matchednot matchednot matchedno offer74 tok/s34955ms2,931 reqno offer
  7. xAInot matchednot matchednot matchednot matchedno offer65 tok/s43971ms2 reqno offer

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 2 of the 3 timed routes are slower than it, and the middle route runs at 74 tok/s. The widest median-to-p90 gap is xAI's, 2.18x.

xAI publishes 4 offers and had 3 routes timed. The two documents share no route id, so those offers and routes are printed apart rather than paired.

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 2 of the 4 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: xAI (xai/zdr) at 93.56% on 3 Nov 2026 and xAI (xai) at 94.51% on 3 Nov 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

13 parameters · 4 sellers
  1. include_reasoningevery seller
  2. logprobsevery seller
  3. max_tokensevery seller
  4. reasoningevery seller
  5. reasoning_effortevery seller
  6. response_formatevery seller
  7. seedevery seller
  8. structured_outputsevery seller
  9. temperatureevery seller
  10. tool_choiceevery seller
  11. toolsevery seller
  12. top_logprobsevery seller
  13. top_pevery seller

All 13 are accepted by every one of the 4 sellers that publish a list. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $1.25 per million tokens, 3 in to 1 out: cheaper than 129 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board

Each mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.

Intelligence Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Index42.2Position 72 of 118, above 39% of the models scored.the coding leaderboard
Agentic Index15.5Position 52 of 94, above 45% of the models scored.the agentic leaderboard
  1. Agentic game development · Agents954 Elowin rate 28.7% · source rank 25the board, 25 ranked
  2. Agentic HTML slides · Agents1066 Elowin rate 31.8% · source rank 9the board, 9 ranked
  3. Agentic slides · Agents1072 Elowin rate 31.9% · source rank 9the board, 9 ranked
  4. Agentic slides, HTML · Agents1066 Elowin rate 31.7% · source rank 9the board, 9 ranked
  5. Agentic slides, python-pptx · Agents1068 Elowin rate 32.4% · source rank 9the board, 9 ranked
  6. Android native · Agents956 Elowin rate 23.0% · source rank 43the board, 41 ranked
  7. blender3d · Agents807 Elowin rate 15.5% · source rank 25the board, 25 ranked
  8. codetovideo · Agents898 Elowin rate 17.9% · source rank 26the board, 26 ranked
  9. Full stack · Agents981 Elowin rate 28.0% · source rank 43the board, 44 ranked
  10. Godot game development · Agents924 Elowin rate 23.5% · source rank 36the board, 34 ranked
  11. HTML slides · Agents906 Elowin rate 28.6% · source rank 25the board, 25 ranked
  12. Mobile apps · Agents1050 Elowin rate 33.0% · source rank 50the board, 49 ranked
  13. pdf · Agents943 Elowin rate 20.2% · source rank 37the board, 36 ranked
  14. PPTX slides · Agents1071 Elowin rate 32.5% · source rank 8the board, 8 ranked
  15. python-pptx slides · Agents1072 Elowin rate 30.8% · source rank 27the board, 29 ranked
  16. spreadsheet · Agents932 Elowin rate 30.5% · source rank 32the board, 32 ranked
  17. Web apps · Agents1106 Elowin rate 42.5% · source rank 37the board, 47 ranked
  18. 3D scenes · Models1104 Elowin rate 40.6% · source rank 92the board, 113 ranked
  19. ASCII art · Models1109 Elowin rate 42.1% · source rank 58the board, 67 ranked
  20. Code · Models1174 Elowin rate 43.5% · source rank 70the board, 120 ranked
  21. Data visualisation · Models1176 Elowin rate 45.1% · source rank 67the board, 110 ranked
  22. Game development · Models1160 Elowin rate 42.5% · source rank 73the board, 120 ranked
  23. SVG · Models1070 Elowin rate 36.5% · source rank 76the board, 83 ranked
  24. UI components · Models1184 Elowin rate 45.2% · source rank 70the board, 116 ranked
  25. Websites · Models1185 Elowin rate 44.0% · source rank 73the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals

Epoch AI has not placed Grok 4.3 (batch) on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.

Benchmark results

2 of 6 boards · 29 results
Epoch AI Benchmarking Hub · publisher-run, CC-BY-4.06 of 22 tasks · at high effort

Mean accuracy, 0 to 1, on the task the row names, as Epoch AI runs it and averaged over repeated runs. All eighteen of their tasks, including the held-out FrontierMath tiers, named as they name them. The model id carries the effort setting the run used. Epoch AI Benchmarking Hub names this run grok-4.3_high. All runs is how many runs the publisher scored on the task, every model's. Read from epoch.ai ↗, which dates its own data . Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.

LiveBench · publisher-run, Apache-2.023 of 23 tasks · 71 runs scored on each task · effort unstated

Percent correct on the task the row names, higher is better. All 23 published columns; there is no average to carry, because the site computes its headline in the browser from a weighting this does not reimplement. LiveBench names this run grok-4.3, with no effort setting written on it. Read from livebench.ai ↗, which dates its own data . LiveBench, Apache-2.0. Results produced by the LiveBench maintainers on questions refreshed monthly.

2 of the 6 openly licensed boards Vitna mirrors carry a result for Grok 4.3 (batch), each printed as its publisher published it and none added to another. MTEB, HELM, Vectara hallucination leaderboard and Aider polyglot have not published one under a name that matches its listing, and names are matched to the catalog exactly and never guessed. A task that is a link opens its column on /capability, with every run scored on it; an effort that is a link opens its run's row there, where the run is ranked on Vitna's scale. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Vitna ran none of these evaluations and adjusted none of these figures.