wrangler ai run failed: model not found

Not specified by the original author.

wrangler ai run failed: model not found

TL;DR

The model name in the run call does not match a Workers AI model: typo, wrong format, or a model not available on the account. Copy the exact model id from the docs and verify it is enabled. Model names are exact strings.

wrangler ai run failed: model not found

Steps

1. Copy the model id from the Workers AI docs and compare character by character. Expected: The typo or mismatch is found.

2. Check the model is available for your account/plan. Expected: Availability is confirmed.

3. Fix the call to use the exact id. Expected: The run succeeds.

4. Centralize model ids in config, not inline strings. Expected: Typos have one place to live.

5. Handle model-not-found distinctly from other AI errors in the code. Expected: The failure mode is clear.

When to use

• ai run fails with model not found
• the model name was typed by hand
• after a docs update

When not to use

• the model exists (check for a plan restriction)
• the error is on input format (different problem)
• the model was removed (check the changelog)

Tool compatibility

• wrangler
• Cloudflare Workers AI

Variant phrasings

• "workers ai model not found"
• "ai run model not found"
• "model id typo workers ai"

Why it happens

Model ids are opaque exact strings, and the catalog changes: models get renamed, deprecated, or gated. A hand-typed id drifts from reality, and the API's 'not found' is the only signal. Centralizing the ids turns a typo hunt into a config update.

Edge cases

• the catalog differs by account type; verify in your own dashboard
• deprecated models fail this way; check the deprecation list
• the exact id includes the org prefix; partial names do not resolve

Provenance

Resolved from the public thread: https://vectle.com/posts/pst_oeBQZHDsZQym81TAxawbRA

Resolved from the public thread: https://vectle.com/posts/pst_oeBQZHDsZQym81TAxawbRA

Thread query: wrangler ai run failed: model not found

TL;DR: The model name in the run call does not match a Workers AI model: typo, wrong format, or a model not available on the account. Copy the exact model id from the docs and verify it is enabled. Model names are exact strings.

Not specified by the original author.

TL;DR

First, try reaching the model through both the playground and the API to see if the error is API-only.

Fix

1. First, try reaching the model through both the playground and the API to see if the error is API-only. Expected: you can confirm this matches your situation.

When to use

• You are setting up or using this Fireworks AI feature.
• The symptom matches: Model not found when accessing a trained model.

When NOT to use

• Unrelated Fireworks AI issues (different feature, different failure).
• You need general documentation for the tool; check the official docs instead.

Compatibility

Reported against Fireworks AI. Source: https://docs.fireworks.ai/faq/models/fine-tuning/troubleshooting.

Variant phrasings

Model not found when accessing a trained model

Why it happens

After fine-tuning on Fireworks AI, requests to the trained model return a Model not found error even though the training job completed. The docs list this as a common access issue with specific troubleshooting steps.

Edge cases

• If your error message differs even slightly, this is probably a different issue; search the exact text.
• If the fix does not help, capture the full error output and check the source link for updates.

Source

https://docs.fireworks.ai/faq/models/fine-tuning/troubleshooting

Source: After fine-tuning on Fireworks AI, requests to the trained model return a Model not found error even though the training job completed. The docs list this as a common access issue with specific troubleshooting steps.

Verified resolution: [Fireworks AI docs, Training troubleshooting]: First, try reaching the model through both the playground and the API to see if the error is API-only. Check whether the error hits all users on the account, and verify the API key is valid. Common causes include a user email previously tied to a deleted account, API key permission issues, or access conflicts from multiple accounts. When contacting support, include the account ID, API key verification results, affected users/emails, and both playground and API test results.

Source URL: https://docs.fireworks.ai/faq/models/fine-tuning/troubleshooting

Not specified by the original author.

TL;DR

Upgrade the workers-ai provider to v0.0.13 or later, which contains the fix from PR #24. Maintainer andyjessop confirmed the fix shipped in v0.0.13 of the provider, via PR #24.

Steps

1. If wrangler dev gives you truncated or wrong generations through the AI SDK provider but wrangler dev --remote looks fine, the local proxying in the provider was at fault. Upgrade the workers-ai provider to v0.0.13 or later, which contains the fix from PR #24. You can sanity check by comparing the provider's local output against the Workers AI binding directly, since the binding was never affected.

When to use

You are seeing this: Running wrangler dev with the AI SDK's workers-ai provider produced incomplete or inaccurate generations, while wrangler dev --remote gave correct results every time. Use this skill when you run into "Text generation is wrong or incomplete during wrangler dev with the workers-ai provider".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

Versions mentioned in the source: v0.0.13. If you are on something much newer or older, the details may have shifted.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

A user asked: Running wrangler dev with the AI SDK's workers-ai provider produced incomplete or inaccurate generations, while wrangler dev --remote gave correct results every time. The same prompts worked fine through the Workers AI binding directly, so the problem was in how the provider proxied AI calls during local dev. Maintainer andyjessop confirmed the fix shipped in v0.0.13 of the provider, via PR #24. The verified answer: If wrangler dev gives you truncated or wrong generations through the AI SDK provider but wrangler dev --remote looks fine, the local proxying in the provider was at fault. Upgrade the workers-ai provider to v0.0.13 or later, which contains the fix from PR #24. You can sanity check by comparing the provider's local output against the Workers AI binding directly, since the binding was never affected. Thread: https://vectle.com/threads/thr_FSNPbAZdUSqriR-qAuvAVA