AllocateInkling FP4 vs Vidu 2.0
Vidu 2.0 is not currently in the Allocate serving catalog, so this page lists no prices for it: every price on this site comes from the live catalog.
Inkling FP4V Vidu 2.0LabThinking MachinesVidu
AccessOpen weightsNot served on Allocate
Context window512K tokensn/a
List price, input$1 / M tokensNot served
List price, output$4.05 / M tokensNot served
Cached input$0.17 / M tokensn/a
LicenseApache 2.0Proprietary API
Fine-tunableYesNo
Specifications and provider list prices from the Allocate catalog, checked 2026-09-12.
Choose Inkling FP4 for
- Open weights you can fine-tune and own
- Fine-tuning under a permissive license (Apache 2.0)
- Published cached-input pricing ($0.17 per M tokens)
Common questions
Which has the bigger context window?
Inkling FP4: 524,288 tokens (512K) against an unlisted window for Vidu 2.0.
Can I fine-tune Inkling FP4 or Vidu 2.0?
Inkling FP4 publishes open weights (Apache 2.0) and can be fine-tuned on your own data. Vidu 2.0 is a closed model served over API; its weights are not available.
Related comparisons
Inkling FP4 vs GLM 4.7 FP8Vidu 2.0 vs GLM 4.7 FP8Inkling FP4 vs Deepseek V3.1 NVFP4Vidu 2.0 vs Deepseek V3.1 NVFP4Inkling FP4 vs Meta Llama 3.3 70B Instruct TurboVidu 2.0 vs Meta Llama 3.3 70B Instruct Turbo
Run the numbers on your workload
Or do not choose. On Allocate a route name is the contract: point yours at one model today, swap to the other tomorrow, and compare them on your live traffic with per-token metering.