Anthropic · tested in Taskade Genesis
Claude Haiku 4.5 in Taskade
Claude Haiku 4.5 from Anthropic runs on Pro and up, with your own API key. We last tested it on Oct 8, 2026 in TSK-1, our app-building test.
- Status
- Own key
- Plan
- Pro and up, with your own API key (BYOK)
- Where to pick it
- Agent settings
- Your own key
- Anthropic
- Last test
- Context window
- 200Ktokens
- Max output
- 64Ktokens
- Released
- Knowledge cutoff
- Where it runs
- 5services
TSK-1 scorecard for the Claude family
TSK Score
Claude family, across real apps made in Taskade Genesis
- Interfaceready to share
- Strong
- Taskcompletes your task
- Strong
- Memorykeeps your data
- Emerging
- Adapthandles follow-up edits
- Leading
Caught and repaired a problem that would have left the app blank.
Published scores
Benchmark scores that Anthropic and test sites published for Claude Haiku 4.5. Taskade did not re-run them. Lab-reported marks a score from Anthropic itself.
| Benchmark | Score | Source |
|---|---|---|
| SWE-Bench Proresolve rate · publicScale AI | 39.45% | Scale AI |
LMArena scores
| Benchmark | Score | Source |
|---|---|---|
| Text arena±2 · 149,199 votes · Rank 144 of 416 · LMArena | 1,414 | LMArena |
| WebDev arena±5 · 29,060 votes · Rank 121 of 145 · LMArena | 1,330 | LMArena |
Scores from the LMArena leaderboard dataset (CC BY 4.0). People vote between two answers, and the votes set the score. Taskade picked the Overall category and the default setting of each model.
Scores collected by models.dev (MIT). Each source links the page that published the score.
Versions tested
Open a version to read its findings. We ran these tests with an API key from the lab.
Claude Haiku 4.5Tested Oct 20264 findings
Caught and repaired a problem that would have left the app blank.
Found the problem while building, repaired it, and then finished: the only model in the test to recover on its own.
Fastest build of the test, but it left out the weekly recap automation the brief asked for.
Built the family intake form in under 4 minutes and took the new teacher question, but the family photo replaced the child photo on every submission.
Built a Dota 2 match tracker that saved logged matches and added a heroes page when asked, but its top-heroes chart showed empty axes.
Results by task
Model facts
The token limits are the most the model accepts. Taskade can run it with lower limits.
- Last updated
- Input types
- Text, Images, PDF
- Output types
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- File attachments
- Yes
- Structured output
- Yes
- Open weights
- No
Published specs from the model maker, via models.dev (MIT).
Run Claude Haiku 4.5 with your own key
Pick it with your own key in a custom agent.
| Key provider | Plan |
|---|---|
| Anthropic | Pro and up |
Where it runs
Services outside Taskade that serve Claude Haiku 4.5, from models.dev. Each link opens in a new tab. In Taskade, your own key works only through the key providers on this page.
How to choose Claude Haiku 4.5
- Open the agent settings.
- Under AI Model, choose the model.
- Under Bring Your Own Key, add or select your provider key.
Where Claude ranks
TSK Score out of 100.
Compare Claude
Other Anthropic models
FAQ
Which Taskade plans include Claude Haiku 4.5?
Claude Haiku 4.5 runs on Pro and up, with your own API key. Your provider bills the model use to your own account.
Has Taskade tested Claude Haiku 4.5?
Yes. We last tested Claude Haiku 4.5 on Oct 8, 2026 in the TSK-1 Benchmark. Caught and repaired a problem that would have left the app blank.
How do I choose Claude Haiku 4.5 in Taskade?
Open the agent settings. Under AI Model, choose Claude Haiku 4.5. Under Bring Your Own Key, select your provider key.
Can I use my own API key for Claude Haiku 4.5?
Yes. In a custom agent, you can pick Claude Haiku 4.5 with your own key from Anthropic (Pro and up). Your provider bills the model use to your own account.
Who makes Claude Haiku 4.5?
Anthropic makes Claude Haiku 4.5. Taskade runs it on Pro and up, with your own API key, beside frontier models from other top AI labs.