Flan-T5 XL
Flan-T5 XL is worth evaluating for general LLM work when its provider route and context window match the workload.
Use it for
- Teams evaluating general LLM work
- Workloads that can use a 512 context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- FLAN-T5
- Released
- 2022-10-03
- Context
- 512
- Parameters
- 3B
- Architecture
- Decoder Only
- Specialization
- general
- License
- Unknown / UnverifiedCommercial use: unknown
- Weights
- Unknown
- Code
- Unknown
- Training
- Fine-tuned
Cheapest of 2 routes · IBM watsonx
About
Flan-T5 XL is Google DeepMind's FLAN-T5 model. It was released 2022-10-03.
Flan-T5 XL is a model in the FLAN-T5 family. The structured metadata tracks a 512-token context window. This page tracks provider routes through IBM watsonx and Replicate API, with the cheapest tracked route listed at $0.6 input and $0.6 output per 1M tokens. No headline benchmark score is tracked for Flan-T5 XL yet.
Top use-case fit
No primary decision-task fit is mapped for this model yet.
Provider price ladder
Compare all 2Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| IBM watsonx | $0.600 | $0.600 | Serverless |
| Replicate API | - | - | ServerlessPartial |
Capabilities
No model capability flags are currently sourced.
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
Frequently asked questions
What is the context window of Flan-T5 XL?
Flan-T5 XL has a context window of 512 tokens.
How much does Flan-T5 XL cost?
Flan-T5 XL is available at $0.6/1M input tokens through IBM watsonx.
When was Flan-T5 XL released?
Flan-T5 XL was released on 2022-10-03.
Which providers offer Flan-T5 XL?
Flan-T5 XL is available from 2 providers: IBM watsonx, Replicate API.
Cheapest of 2 routes · IBM watsonx