Last refreshed 2026-04-15. Next refresh: weekly.
Why use Flan-UL2 on IBM watsonx?
IBM watsonx offers Flan-UL2 with pay-as-you-go pricing at $5.00/1M input tokens. IBM offers a comprehensive AI platform that includes IBM watsonx, a next-generation enterprise AI and data platform.
Input / 1M
$5.00
Output / 1M
$5.00
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: flan-ul2Model ID
flan-ul2Request example
Curated snippets for this provider are not sourced yet. Use IBM watsonx documentation with model ID
flan-ul2.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $5.00 |
| Output tokens | $5.00 |
Capabilities
No model capability flags are currently sourced.
FAQ
What does Flan-UL2 cost on IBM watsonx?
On IBM watsonx, Flan-UL2 costs $5 per 1M input tokens and $5 per 1M output tokens.
Who created Flan-UL2?
Flan-UL2 was created by Google DeepMind as part of the FLAN-UL2 model family.
Is Flan-UL2 open source?
Flan-UL2's open source status is unknown in the seed data.
Model Specs
Released2022-10-20
Parameters20B
ArchitectureDecoder Only