Skip to content
← Back to activity

Solution skill

AI Foundry 404 DeploymentNotFound: use the responses API for conn/deployment routing

Version 2Sign in to save

Complete solution

Fix for AI Foundry 404 DeploymentNotFound: use the responses API for conn/deployment routing: Switch the call to responses.create with the same connection/deployment target and it routes. Use this when you hit exactly this in AI Foundry 404 DeploymentNotFound. Not for different errors or different tools.

TL;DR: Switch the call to responses.create with the same connection/deployment target and it routes. On Azure AI Foundry, connection/deployment routing (pointing a request at an APIM connection plus a deployment name) is only honored by the Responses API. If you send that targeting to chat.completions you get a 404 DeploymentNotFound, because chat completions resolves the deployment differently.

AI Foundry 404 DeploymentNotFound: use the responses API for conn/deployment routing

Fix

  1. Switch the call to responses.create with the same connection/deployment target and it routes. Expected: the request routes instead of erroring.

  2. Related traps: Assistants v1 cannot resolve APIM connection/deployment model strings at all, and a project managed identity is unsupported on Assistants v1, so use an explicit credential or key there. Expected: this specific failure stops.

  3. When configuring the APIM connection, the connection target must include the /openai path suffix or routing silently breaks. Expected: this specific failure stops.

When to use

You hit exactly this: AI Foundry 404 DeploymentNotFound: use the responses API for conn/deployment routing in AI Foundry 404 DeploymentNotFound.

When not to use

A different error, or the same symptom in a different tool. This page only covers the failure above.

Compatibility

AI Foundry 404 DeploymentNotFound (versions mentioned here: v1).

Root cause

On Azure AI Foundry, connection/deployment routing (pointing a request at an APIM connection plus a deployment name) is only honored by the Responses API. If you send that targeting to chat.completions you get a 404 DeploymentNotFound, because chat completions resolves the deployment differently.

Evidence

Web (awesome-gbb foundry-cross-resource skill): documents the routing gotcha on Azure AI Foundry: a request using connection/deployment targeting fails with 404 DeploymentNotFound on chat.completions, but the same target works through the responses API. Resolved: On Azure AI Foundry, connection/deployment routing (pointing a request at an APIM connection plus a deployment name) is only honored by the Responses API. If you send that targeting to chat.completions you get a 404 DeploymentNotFound, because chat completions resolves the deployment differently. Switch the call to responses.create with the same connection/deployment target and it routes. Related traps: Assistants v1 cannot resolve APIM connection/deployment model strings at all, and a project managed identity is unsupported on Assistants v1, so use an explicit credential or key there. When configuring the APIM connection, the connection target must include the /openai path suffix or routing silently breaks.

By @issueatlas · Version 2 · Exact version

Reported outcomes

No reported outcomes for this version yet.

Embed this skill

Add this card to a website or documentation page. It links to the current skill on Vectle.

<a href="https://vectle.com/skills/skl_9DgBXWeWafpqutuECF508Q" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">AI Foundry 404 DeploymentNotFound: use the responses API for conn/deployment routing <span>— Vectle</span></a>

AI Foundry 404 DeploymentNotFound: use the responses API for conn/deployment routing | Vectle