Grok 4.7
Sold by 5 sellers, timed at 77.4 tok/s, scored 35.5 on the Intelligence Index, on 12 Design Arena boards, and with results on 2 openly licensed boards.
retrieved sha256 · 0bb53a77713f
The same model sold by 2 providers, each at its own list price. OpenRouter's rate is its routed rate across whichever of them it uses, and it need not match any one of them.
What sellers charge
5 sellers · 2x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $2.00 at Amazon Bedrock to $4.00 at xAI. The $2.00 listed is the cheapest on offer; 2 sellers are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
11,559 requests · 6 endpoints · 30-minute windowOpenRouter'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
5 priced · 6 timed · cheapest first- Amazon Bedrockamazon-bedrock/global · listed$2.00$6.00$0.50not declared450k13 tok/s59.84s590 req97.77%
- xAIxai · listed$2.00$6.00$0.50not declared450knot matchednonenonenot matched98.88%
- xAIxai/zdr · listed$2.00$6.00$0.50not declared450knot matchednonenonenot matched98.22%
- xAIxai/priority$4.00$12.00$1.00not declared450knot matchednonenonenot matched99.68%
- xAIxai/zdr/priority$4.00$12.00$1.00not declared450knot matchednonenonenot matched100%
- xAInot matchednot matchednot matchednot matchedno offer84 tok/s391.7s3,214 reqno offer
- xAInot matchednot matchednot matchednot matchedno offer89 tok/s571.37s240 reqno offer
- xAInot matchednot matchednot matchednot matchedno offer84 tok/s661.12s9 reqno offer
- xAInot matchednot matchednot matchednot matchedno offer96 tok/s681.3s145 reqno offer
- xAInot matchednot matchednot matchednot matchedno offer79 tok/s491.52s7,361 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: 1 of the 6 timed routes are slower than it, and the middle route runs at 84 tok/s. The widest median-to-p90 gap is Amazon Bedrock's, 2.6x.
xAI publishes 4 offers and had 5 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 . 6 of the 6 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/priority) at 0.00% on 24 Oct 2026, xAI (xai/zdr/priority) at 33.33% on 24 Oct 2026, Amazon Bedrock at 57.83% on 3 Nov 2026, xAI (xai/zdr/us) at 71.66% on 25 Oct 2026, and 2 more. 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
15 parameters · 5 sellers- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- reasoning_effortevery seller
- response_formatevery seller
- structured_outputsevery seller
- temperatureevery seller
- tool_choiceevery seller
- toolsevery seller
- top_pevery seller
- logprobs4 of 5not Amazon Bedrock
- seed4 of 5not Amazon Bedrock
- top_logprobs4 of 5not Amazon Bedrock
- stop1 of 5only Amazon Bedrock
- top_k1 of 5only Amazon Bedrock
10 of these 15 are accepted by every one of the 5 sellers that publish a list; the other 5 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.
Price position
342 priced modelsBlended $3.00 per million tokens, 3 in to 1 out: cheaper than 81 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 boardEach 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.
- blender3d · Agents1163 Elowin rate 60.0% · source rank 6the board, 25 ranked
- codetovideo · Agents1114 Elowin rate 41.6% · source rank 24the board, 26 ranked
- Mobile apps · Agents1242 Elowin rate 53.5% · source rank 11the board, 49 ranked
- pdf · Agents1197 Elowin rate 51.2% · source rank 20the board, 36 ranked
- spreadsheet · Agents1420 Elowin rate 74.3% · source rank 2the board, 32 ranked
- 3D scenes · Models1251 Elowin rate 47.0% · source rank 28the board, 113 ranked
- Code · Models1264 Elowin rate 47.4% · source rank 32the board, 120 ranked
- Data visualisation · Models1223 Elowin rate 44.5% · source rank 47the board, 110 ranked
- Game development · Models1305 Elowin rate 50.4% · source rank 19the board, 120 ranked
- SVG · Models1270 Elowin rate 50.4% · source rank 16the board, 83 ranked
- UI components · Models1276 Elowin rate 49.7% · source rank 29the board, 116 ranked
- Websites · Models1243 Elowin rate 45.6% · source rank 48the board, 126 ranked
Position 39 of the 258 models Epoch has placed, which is not the population of either board above, on a scale anchored at Claude 3.5 Sonnet 130 and GPT-5 150. Epoch states that absolute values are meaningless by themselves and that comparisons between models are what the index is for, that values are not linearly related to benchmark accuracy, and that a highly specialised model may score low while being capable in its own domain.
Benchmark results
2 of 6 boards · 33 results| Task | All runs | Score |
|---|---|---|
| Chess Puzzles | 167 | 0.41 |
| FrontierMath-Erdos | 16 | 0 |
| FrontierMath-Tier-4-v2-Private | 84 | 0.17 |
| FrontierMath-Tiers-1-3-v2-Private | 128 | 0.53 |
| Furniture Assembly | 42 | 0.21 |
| GPQA diamond | 342 | 0.93 |
| MirrorCode | 48 | 0.54 |
| Mystery Game Puzzles | 149 | 0.29 |
| OTIS Mock AIME 2024-2025 | 319 | 0.98 |
| SimpleQA Verified | 106 | 0.56 |
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-4.7_xhigh. 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.
| Task | Score |
|---|---|
| AMPS_Hard | 98 |
| code_completion | 78.26 |
| code_generation | 76.06 |
| connections | 98 |
| consecutive_events | 85.73 |
| integrals_with_game | 96 |
| javascript | 63.64 |
| logic_with_navigation | 66 |
| math_comp | 97.06 |
| olympiad | 91.65 |
| paraphrase | 78.05 |
| plot_unscrambling | 72.42 |
| python | 55 |
| simplify | 69.97 |
| spatial | 94 |
| story_generation | 74.92 |
| summarize | 78.17 |
| tablejoin | 44.92 |
| tablereformat | 100 |
| theory_of_mind | 84.61 |
| typescript | 43.33 |
| typos | 70 |
| zebra_puzzle | 86 |
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-4.7-xhigh. 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 4.7, 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.
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.
Source: the Epoch AI Capabilities Index (epoch.ai/eci), as of 20 Nov 2026. 258 models placed over 2917 benchmark results.
Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
Vitna ran none of these evaluations and adjusted none of these figures.
