Models & Pricing

Veo 3.1 vs Veo 3.1 Fast

Choose two or three models. Copy the URL to share your selection.

ComparisonVeo 3.1
veo-3.1
Veo 3.1 Fast
veo-3.1-fast
TypeVideoVideo
Best forShort AI video clips from text or imagesShort AI video clips from text or images
TokenRex price$0.40 per second$0.10 per second
Cached input / 1M tokensNo separate cached rate listedNo separate cached rate listed
Cache write / 1M tokensNot applicableNot applicable
Cached outputNot offered · standard output rate appliesNot offered · standard output rate applies
Web searchNot applicableNot applicable
Market price$0.40 per second$0.10 per second
Input token limit (provider)Within the context windowWithin the context window
Vendor input modalitiesText, ImageText, Image
Vendor output modalitiesVideo with audioVideo with audio
TokenRex endpointsPOST /v1/videos · GET /v1/videos/{id}POST /v1/videos · GET /v1/videos/{id}
TokenRex inputText prompt, Optional base64 imageText prompt, Optional base64 image
TokenRex outputAsynchronous video job; retrieve the completed resultAsynchronous video job; retrieve the completed result
Duration accepted by TokenRex4, 6 or 8 seconds4, 6 or 8 seconds
Resolution accepted by TokenRex720p, 1080p or 4K720p, 1080p or 4K
Default request8 seconds at 720p8 seconds at 720p
Audio controlEnabled by default; generate_audio can disable itEnabled by default; generate_audio can disable it
Benchmarks
Benchmark evidence1 source-linked results1 source-linked results
AA-Video-T2V v2.0 (with audio)
962Elo

Freshly fetched overall with-audio v2.0 table, pairwise human preference Elo, 95% interval ±10. Arena revision and vote counts change; not an API availability or latency test.

Artificial Analysis · Text-to-Video Arena
961Elo

Freshly fetched overall with-audio v2.0 table, pairwise human preference Elo, 95% interval ±10. Arena revision and vote counts change; not an API availability or latency test.

Artificial Analysis · Text-to-Video Arena

No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenRex API support.

— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenRex media controls and response formats are listed separately.

Veo 3.1

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (3)
  • These durations and resolutions are accepted by the TokenRex endpoint; they are not fresh generation measurements.
  • TokenRex does not expose provider video extension, reference-image arrays or first/last-frame controls.
  • TokenRex’s endpoint requires 8 seconds for 1080p and 4K; this is its validation rule, not a claim about every upstream interface. Unsupported duration values are normalized to 8 seconds.

Veo 3.1 Fast

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (3)
  • These durations and resolutions are accepted by the TokenRex endpoint; they are not fresh generation measurements.
  • TokenRex does not expose provider video extension, reference-image arrays or first/last-frame controls.
  • TokenRex’s endpoint requires 8 seconds for 1080p and 4K; this is its validation rule, not a claim about every upstream interface. Unsupported duration values are normalized to 8 seconds.

Popular comparisons

Open the cost calculator →