Grok Imagine Video 1.5: Benchmarks, Pricing & Comparison

Grok Imagine Video 1.5 benchmarks

Image to video arena

How people rate generated videos in blind comparisons, Elo points · higher is better

20 of 21 models

MiniMax H31,495

Gemini Omni 1.1 Flash1,488

Dreamina Seedance 2.5 720p1,477

Dreamina Seedance 2.0 720p1,475

Gemini Omni Flash1,465

Grok Imagine Video 1.51,456

FLUX.3 Video1,449

Wan 2.71,428

Grok Imagine Video1,415

Veo 3.11,398

Veo 3.1 Fast1,385

Vidu Q3 Pro1,363

Kling 3.0 Pro1,354

Wan 2.61,310

PixVerse V5.61,299

Kling 2.6 Pro1,294

Hailuo 2.31,262

HunyuanVideo 1.51,198

Wan 2.2 A14B1,170

LTX-2 19B1,159

MiniMax H3

Gemini Omni 1.1 Flash

Dreamina Seedance 2.5 720p

Dreamina Seedance 2.0 720p

Gemini Omni Flash

Grok Imagine Video 1.5

as of September 22, 2026 · Source: LMArena

Text to video arena

How people rate generated videos in blind comparisons, Elo points · higher is better

20 of 23 models

Gemini Omni 1.1 Flash1,516

Gemini Omni Flash1,513

FLUX.3 Video1,493

Grok Imagine Video 1.51,492

Dreamina Seedance 2.0 720p1,479

Dreamina Seedance 2.5 720p1,474

MiniMax H31,460

Muse Video1,456

Sora 2 Pro1,368

Veo 3.11,364

Veo 3.1 Fast1,362

Sora 21,343

Grok Imagine Video1,342

Wan 2.71,337

Wan 2.61,327

PixVerse V5.61,240

Runway Gen-4.51,225

Kling 2.6 Pro1,216

Hailuo 2.31,206

HunyuanVideo 1.51,169

Gemini Omni 1.1 Flash

Gemini Omni Flash

FLUX.3 Video

Grok Imagine Video 1.5

Dreamina Seedance 2.0 720p

Dreamina Seedance 2.5 720p

as of September 22, 2026 · Source: LMArena

Show all 39 individual results from 14 sources

Published benchmarks

LMArena Text to Video

Elo ratings summarize pairwise comparisons within this leaderboard. They are not percentages. The scale does not express absolute quality or linear gaps between models.

Gemini Omni 1.1 Flash1,516 Elo

Gemini Omni Flash1,513 Elo

FLUX.3 Video1,493 Elo

Grok Imagine Video 1.51,492 Elo

Dreamina Seedance 2.0 720p1,479 Elo

Dreamina Seedance 2.5 720p1,474 Elo

MiniMax H31,460 Elo

Muse Video1,456 Elo

Sora 2 Pro1,368 Elo

Veo 3.11,364 Elo

Veo 3.1 Fast1,362 Elo

Sora 21,343 Elo

Grok Imagine Video1,342 Elo

Wan 2.71,337 Elo

Wan 2.61,327 Elo

PixVerse V5.61,240 Elo

Runway Gen-4.51,225 Elo

Kling 2.6 Pro1,216 Elo

Hailuo 2.31,206 Elo

HunyuanVideo 1.51,169 Elo

LTX-2 19B1,154 Elo

Wan 2.2 A14B1,132 Elo

Pika 2.21,009 Elo

higher is betterAs of November 5, 2026Scale: 0 Elo - 1,516 Elo

Source: LMArena

|

gradually.ai

Methodology and context

Metric: elo-rating
Scale: No upper bound is documented. The chart spans the recorded values and zero.
Participants: 23
Sample: 1,218

Source: LMArena

LMArena Image to Video

Elo ratings summarize pairwise comparisons within this leaderboard. They are not percentages. The scale does not express absolute quality or linear gaps between models.

MiniMax H31,495 Elo

Gemini Omni 1.1 Flash1,488 Elo

Dreamina Seedance 2.5 720p1,477 Elo

Dreamina Seedance 2.0 720p1,475 Elo

Gemini Omni Flash1,465 Elo

Grok Imagine Video 1.51,456 Elo

FLUX.3 Video1,449 Elo

Wan 2.71,428 Elo

Grok Imagine Video1,415 Elo

Veo 3.11,398 Elo

Veo 3.1 Fast1,385 Elo

Vidu Q3 Pro1,363 Elo

Kling 3.0 Pro1,354 Elo

Wan 2.61,310 Elo

PixVerse V5.61,299 Elo

Kling 2.6 Pro1,294 Elo

Hailuo 2.31,262 Elo

HunyuanVideo 1.51,198 Elo

Wan 2.2 A14B1,170 Elo

LTX-2 19B1,159 Elo

Pika 2.2997 Elo

higher is betterAs of November 5, 2026Scale: 0 Elo - 1,495 Elo

Source: LMArena

|

gradually.ai

Methodology and context

Metric: elo-rating
Scale: No upper bound is documented. The chart spans the recorded values and zero.
Participants: 21
Sample: 137,459

Source: LMArena

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

AA Video Arena Elo (Show measurement, test conditions, and source)

Source value: 1060
Score: 1060
Metric: pairwise human-preference Elo
Unit: elo
Benchmark version: AA-Video-T2V v2.1
Category: text-to-video
Direction: Higher is better
Sample: 3748
Confidence interval: 16
Lower confidence bound: 1044
Upper confidence bound: 1076
Source type: independent-evaluator
Evaluator: Artificial Analysis AA-Video-T2V v2.1
Status: superseded
Retrieved at: 2026-10-16
Methodology: Independent evaluation. Text-to-video with audio; exact source row Grok Imagine Video 1.5.
Context: The published comparison includes audio; it is not a silent-video-only score.

Source Artificial Analysis AA-Video-T2V v2.1

AA Video Arena Elo (Show measurement, test conditions, and source)

Source value: 1068
Score: 1068
Metric: pairwise human-preference Elo
Unit: elo
Benchmark version: AA-Video-I2V v1.1
Category: image-to-video
Direction: Higher is better
Sample: 3211
Confidence interval: 17
Lower confidence bound: 1051
Upper confidence bound: 1085
Source type: independent-evaluator
Evaluator: Artificial Analysis AA-Video-I2V v1.1
Status: active
Retrieved at: 2026-10-16
Methodology: Independent evaluation. Image-to-video with audio; exact source row Grok Imagine Video 1.5.
Context: The published comparison includes audio; it is not a silent-video-only score.

Source Artificial Analysis AA-Video-I2V v1.1

Rapidata Physics human preference Elo (Show measurement, test conditions, and source)

Source value: 1154
Score: 1154
Metric: Overall equal-weight Elo across blind and with-reference leaderboards
Unit: elo
Benchmark version: Rapidata Physics Benchmark, README revision 5f99e9587b9d04017e8d3effe682af2385f78061
Category: image-to-video-physics-overall
Direction: Higher is better
Confidence interval: 26
Source type: independent-evaluator
Evaluator: Rapidata Physics Benchmark dataset card
Status: superseded
Retrieved at: 2026-10-17
Methodology: Independent evaluation. Exact displayed model label Grok Imagine Video 1.5. Image-to-video uses the Physics-IQ switch frame and scene description; 65 scenarios, four generated videos per scenario, about five seconds each. Humans rate realism pairwise. The published overall Elo equally weights ratings with and without the reference recording. Output resolution is not stated.
Context: The source gives the exact displayed label but no immutable serving revision, output resolution, or model-specific vote denominator. The displayed ± is defined as a 95% confidence interval.

Source Rapidata Physics Benchmark dataset card

Rapidata Physics human preference Elo (Show measurement, test conditions, and source)

Source value: 1143
Score: 1143
Metric: With-reference Elo, realism choice with the real continuation shown
Unit: elo
Benchmark version: Rapidata Physics Benchmark, README revision 5f99e9587b9d04017e8d3effe682af2385f78061
Category: image-to-video-physics-with-reference
Direction: Higher is better
Confidence interval: 37
Source type: independent-evaluator
Evaluator: Rapidata Physics Benchmark dataset card
Status: superseded
Retrieved at: 2026-10-17
Methodology: Independent evaluation. Exact displayed model label Grok Imagine Video 1.5. Image-to-video uses the Physics-IQ switch frame and scene description; 65 scenarios, four generated videos per scenario, about five seconds each. Human pairwise realism ratings show the real continuation above the candidate videos. Output resolution is not stated.
Context: The source gives the exact displayed label but no immutable serving revision, output resolution, or model-specific vote denominator. The displayed ± is defined as a 95% confidence interval.

Source Rapidata Physics Benchmark dataset card

Rapidata Physics human preference Elo (Show measurement, test conditions, and source)

Source value: 1165
Score: 1165
Metric: Blind Elo, realism choice without showing the real continuation
Unit: elo
Benchmark version: Rapidata Physics Benchmark, README revision 5f99e9587b9d04017e8d3effe682af2385f78061
Category: image-to-video-physics-blind
Direction: Higher is better
Confidence interval: 37
Source type: independent-evaluator
Evaluator: Rapidata Physics Benchmark dataset card
Status: superseded
Retrieved at: 2026-10-17
Methodology: Independent evaluation. Exact displayed model label Grok Imagine Video 1.5. Image-to-video uses the Physics-IQ switch frame and scene description; 65 scenarios, four generated videos per scenario, about five seconds each. Human pairwise realism ratings do not show the real continuation. Output resolution is not stated.
Context: The source gives the exact displayed label but no immutable serving revision, output resolution, or model-specific vote denominator. The displayed ± is defined as a 95% confidence interval.

Source Rapidata Physics Benchmark dataset card

AA Video Arena Elo (Show measurement, test conditions, and source)

Source value: 1067
Score: 1067
Metric: Elo from pairwise human-preference votes
Unit: elo
Benchmark version: AA-Video-I2V v1.1, snapshot 2026-10-18
Category: image-to-video
Direction: Higher is better
Confidence interval: 17
Lower confidence bound: 1050
Upper confidence bound: 1084
Source type: community-reported
Evaluator: Artificial Analysis AA-Video-I2V v1.1
Status: active
Retrieved at: 2026-10-18
Methodology: Community-reported result. With Audio; image-to-video; exact leaderboard row Grok Imagine Video 1.5.
Context: Artificial Analysis describes Elo based on blind pairwise human-preference votes by validated private evaluators, but publishes no evaluator affiliations or evidence of institutional independence. The unit of the “Samples” column is undefined, so no sampleCount or per-cell N is inferred from it. This dated live-board snapshot does not identify an immutable serving revision and is not a separate test run by this project.

Source Artificial Analysis AA-Video-I2V v1.1

Rapidata Relative Camera Movement human-preference Elo (Show measurement, test conditions, and source)

Source value: 1226
Score: 1226
Metric: human-preference Elo
Unit: elo
Benchmark version: Relative Camera Movement v1
Category: image-to-video-relative-camera-movement-alignment
Direction: Higher is better
Confidence interval: 11
Source type: independent-evaluator
Evaluator: Rapidata Relative Camera Movement
Status: superseded
Retrieved at: 2026-10-19
Methodology: Independent evaluation. Relative Camera Movement v1, overall alignment view. The page describes 220 fixed camera instructions across 50 scenes, pairwise human judgements on the same prompts, at least five responses per match, and majority decisions. Bradley-Terry ratings are scaled to an Elo-like range. An exact API or serving revision is not published.
Context: This is a live leaderboard snapshot retrieved on 2026-10-19, not a dated immutable model evaluation. The row does not disclose an exact serving revision or a defined model-specific evaluation N. The displayed Responses count is not encoded as sampleCount.

Source Rapidata Relative Camera Movement

HarnessEval-W observation metric (Table 2 literal Obs-Q) (Show measurement, test conditions, and source)

Source value: 85.1
Score: 85.1
Metric: Table 2 first Observation column (Obs-Q); normalized evaluator score on source scale 1-100
Unit: points
Direction: Higher is better
Source type: independent-evaluator
Evaluator: HarnessEval-W paper authors (arXiv:2608.16859v2), Table 2
Status: active
Retrieved at: 2026-10-21
Methodology: Independent evaluation. Independent evaluation of the released Grok Imagine Video 1.5 API through its native Prompt-I2V interface on the same frozen set of 330 HarnessEval-W cases. Table 4 reports API access, 848×480 output, 49 frames per turn, and 24 FPS. The evaluator used the same VLM backend, temperature, and frame-sampling configuration across models; the specific settings are not stated. The paper reports this metric on its normalized 1-100 score scale. Table 2's first observation header is Obs-Q; section 5.1 uses Obs-R for Render Quality, so the exact mapping is not asserted.
Context: Table 2 labels the first observation column Obs-Q, while section 5.1 names Render Quality as Obs-R. The raw Table 2 label is preserved; equivalence is not assumed. The paper does not state a separate evaluation run date, immutable API revision, or confidence intervals. Scores are on its normalized 1-100 evaluator scale, not percentages. Metric-specific case counts for transition and persistence columns are not stated in the captured results.

Source HarnessEval-W paper authors (arXiv:2608.16859v2), Table 2

HarnessEval-W Physical Observation Quality (Obs-P) (Show measurement, test conditions, and source)

Source value: 60.6
Score: 60.6
Metric: Physical Observation Quality (Obs-P); normalized evaluator score on source scale 1-100
Unit: points
Direction: Higher is better
Sample: 330
Source type: independent-evaluator
Evaluator: HarnessEval-W paper authors (arXiv:2608.16859v2), Table 2
Status: active
Retrieved at: 2026-10-21
Methodology: Independent evaluation. Independent evaluation of the released Grok Imagine Video 1.5 API through its native Prompt-I2V interface on the same frozen set of 330 HarnessEval-W cases. Table 4 reports API access, 848×480 output, 49 frames per turn, and 24 FPS. The evaluator used the same VLM backend, temperature, and frame-sampling configuration across models; the specific settings are not stated. The paper reports this metric on its normalized 1-100 score scale.
Context: The paper does not state a separate evaluation run date, immutable API revision, or confidence intervals. Scores are on its normalized 1-100 evaluator scale, not percentages. Metric-specific case counts for transition and persistence columns are not stated in the captured results.

Source HarnessEval-W paper authors (arXiv:2608.16859v2), Table 2

HarnessEval-W Exploratory Transition Correctness (Trans-E) (Show measurement, test conditions, and source)

Source value: 76.4
Score: 76.4
Metric: Exploratory Transition Correctness (Trans-E); normalized evaluator score on source scale 1-100
Unit: points
Direction: Higher is better
Source type: independent-evaluator
Evaluator: HarnessEval-W paper authors (arXiv:2608.16859v2), Table 2
Status: active
Retrieved at: 2026-10-21
Methodology: Independent evaluation. Independent evaluation of the released Grok Imagine Video 1.5 API through its native Prompt-I2V interface on the same frozen set of 330 HarnessEval-W cases. Table 4 reports API access, 848×480 output, 49 frames per turn, and 24 FPS. The evaluator used the same VLM backend, temperature, and frame-sampling configuration across models; the specific settings are not stated. The paper reports this metric on its normalized 1-100 score scale.
Context: The paper does not state a separate evaluation run date, immutable API revision, or confidence intervals. Scores are on its normalized 1-100 evaluator scale, not percentages. Metric-specific case counts for transition and persistence columns are not stated in the captured results.

Source HarnessEval-W paper authors (arXiv:2608.16859v2), Table 2

Recorded measurement details

LMArena Text to Video: LMArena Text to Video (Show measurement, test conditions, and source)

Source value: 1492
Score: 1492
Metric: elo-rating
Unit: Elo
Task: lmarena-text-to-video
Task label: LMArena Text to Video
Direction: Higher is better
Source rank: 4
Sample: 1218
Lower confidence bound: 1474
Upper confidence bound: 1510
Retrieved at: 2026-11-05

Source LMArena

LMArena Image to Video: LMArena Image to Video (Show measurement, test conditions, and source)

Source value: 1456
Score: 1456
Metric: elo-rating
Unit: Elo
Task: lmarena-image-to-video
Task label: LMArena Image to Video
Direction: Higher is better
Source rank: 8
Sample: 137459
Lower confidence bound: 1452
Upper confidence bound: 1460
Retrieved at: 2026-11-05

Source LMArena

Page 1 of 4

What Grok Imagine Video 1.5 can do

“n/a” means the provider does not state it or we have not sourced it yet. That is not a “no”.

Text to videoyesSource

Image to videoyesSource

Referencesn/a

AudioyesSource

Runs locallynoSource

Extendn/a

Start and end framen/a

Max. resolution1080pSource

Video sample from our test

This video exists as a documented run for the exact model version. Playback is muted.

Motion and physical consistency

This sample tests Anatomy, object consistency, camera tracking, rain, and reflections.

Open video at original size Open source

Prompt and settings

Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.

Generated through fal.ai with model xai/grok-imagine-video/v1.5/text-to-video. Archived settings were 16:9, one request, first output, requested 5 s, seed provider random, request {"prompt":"Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.","duration":5,"resolution":"720p","aspect_ratio":"16:9"}, configured price estimate $0.70.

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

0 to 100, higher is more popular

20 of 98 models

LTX-2.570

Sora 259

Veo 3.150

SkyReels V2 T2V 14B42

Grok Imagine Video42

Mochi 1 Preview39

Grok Imagine Video 1.529

Grok Imagine Video 1.5

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 5, 2026

Grok Imagine Video 1.5Kling 2.6 ProHunyuanVideo 1.5Dreamina Seedance 2.0 720pWan 2.2 A14B

Grok Imagine Video 1.5 compared

Compare with another model

First video model

Second video model

Predecessor and successor

PredecessorGrok Imagine Video 1.5 vs. Grok Imagine VideoPredecessor of Grok Imagine Video 1.5

The most popular comparisons

Show all 47 comparisons

All specifications

Input and output

Maximum resolution: 1080p; Source: Maximum resolution
Native audio: Yes; Source: Native audio

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking: Unknown; no source
Watermarking technique: Not known; no source

Licence and access

Weights: Proprietary; Source: Weights
Access: API, Web; Source: Access

Prices

PricesSubscriptions

Representative price: $0.08 per second ($0.40 per 5 s clip)Source
fal.ai (xai/grok-imagine-video/v1.5/text-to-video): $0.7 per request (estimated)Source

No xAI subscription includes this model. Through other providers from ≈ €21.20 a month (Recraft Pro, with limited credits). 7 plans in Germany.

AllIndividuals3Teams3Enterprise1

Plan	Monthly price	Note
Recraft Pro	≈ €21.20	with limited credit
Recraft Teams	≈ €23.33	with limited credit, for teams, per seat
Higgsfield Plus	€70.21	with limited credit
Higgsfield Team	€94.01	with limited credit, for teams, per seat
Higgsfield Ultra	€153.51	with limited credit
Higgsfield Scale	€201.11	with limited credit, for teams, per seat
Higgsfield Enterprise	n/a	for enterprises

All plans in the AI subscription comparison

Frequently asked questions about Grok Imagine Video 1.5

How good is Grok Imagine Video 1.5?

Rank 4 of 23 in the text-to-video arena rating. With a start image: rank 6 of 21.

LMArena, as of Sep 22, 2026

Arena ratingtext to video, from user votes · higher is better

Gemini Omni 1.1 Flash1,516

Gemini Omni Flash1,513

FLUX.3 Video1,493

Grok Imagine Video 1.5Rank 4 of 231,492

Dreamina Seedance 2.0 720p1,479

Dreamina Seedance 2.5 720p1,474

MiniMax H31,460

How much does a video with Grok Imagine Video 1.5 cost?

About $0.40 for a 5 s clip, $0.08 per second of video. That is cheap.

Price per seconddollars per second of video · lower is better

Pika 2.2$0.04

PixVerse V5.6$0.045

Grok Imagine Video$0.05

Grok Imagine Video 1.5Rank 4 of 19$0.08

Wan 2.2 A14B$0.08

Hailuo 2.3$0.082

Gemini Omni Flash$0.10

Where can I use Grok Imagine Video 1.5?

Not in a xAI subscription. Including other providers that makes 7 plans in Germany.

Subscription comparison, prices in Germany incl. VAT

At xAI

No xAI subscription includes this model.

Through other providers

7 plans from 2 providers, from ≈ €21.20 a month (Recraft Pro), with limited credits.

Sources and data date

Show all 28 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

Evaluator	Test series	Composite indices	Recorded active measurements
Artificial Analysis	0	0	4
LMArena	0	0	2

Without vendor claims and historical or disputed results; those stay labelled in the single values. 6 measurements are not yet assigned to a test series.

Type	Evidence and data date
Research status	Research date October 16, 2026. 22 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	wiro-video-models-exact-row Note The inspected Wiro leaderboard has no exact model-version route. Nearby variants were not transferred.
Not found in the inspected sources	arena-video-edit-exact-row Note The inspected Video Edit table has no exact model-version row. T2V and I2V values were not reused.
Not found in the inspected sources	vabench-exact-model-row Note VABench has no exact model row. Sora 2 was not transferred to Sora 2 Pro or other models.
Unresolved	vbench-current-public-leaderboard Note The current VBench leaderboard is embedded in a dynamic Hugging Face iframe and was not retrievable; current scores remain unresolved.
Not found in the inspected sources	vidbenchmark-exact-row Note No exact model id is present in the 2026-08-04 dataset; similarly named variants were not transferred.
Not published	immutable-serving-revision Note The dataset names Grok Imagine Video 1.5 but does not publish an immutable serving revision.
Not published	output-resolution Note The dataset describes the input image and clip duration but does not state generated output resolution.
Not published	model-specific-vote-denominator Note The dataset reports an approximate global vote total, not a model-specific vote denominator.
Additional source	xAI · xAI Grok Imagine Video 1.5 announcement · Editorial description reviewed October 2, 2026
Additional source	Video pricing
Additional source	fal.ai
Additional source	LMArena (retrieved November 5, 2026)1 2
Additional source	Artificial Analysis AA-Video-T2V v2.1 (retrieved October 16, 2026; October 28, 2026)
Additional source	Artificial Analysis AA-Video-I2V v1.1 (retrieved October 16, 2026; October 18, 2026; October 28, 2026)
Additional source	Rapidata Physics Benchmark dataset card (retrieved October 17, 2026)
Additional source	Rapidata Relative Camera Movement (retrieved October 19, 2026; October 28, 2026)
Additional source	HarnessEval-W paper authors (arXiv:2608.16859v2), Table 2 (retrieved October 21, 2026)
Additional source	Arena Video Image-to-Video (retrieved September 21, 2026; October 16, 2026; October 28, 2026)
Additional source	Arena Video Text-to-Video (retrieved September 21, 2026; October 16, 2026; October 28, 2026)
Additional source	Definition AI Video Leaderboard (retrieved October 21, 2026; October 28, 2026)
Additional source	MemeBench Video Arena (retrieved October 28, 2026)
Additional source	Rapidata Camera Movement (retrieved October 28, 2026)
Additional source	Rapidata I2V Physics benchmark (retrieved October 22, 2026; October 28, 2026)
Additional source	Rapidata I2V Realism benchmark (retrieved October 22, 2026; October 28, 2026)
Additional source	Model metadata (retrieved October 16, 2026)1 2 3
Additional source	Model metadata (retrieved October 28, 2026)
Additional source	xAI Imagine API overview · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0