Hi Pallav,

I wouldn’t take the display name mismatch alone as proof that the backend is routing to the wrong model, but it is definitely worth reporting because the model catalog/API should not label openai/gpt-oss-20b as GPT OSS 120B.

A useful way to separate “display metadata bug” from “routing bug” would be to compare the two model IDs directly:

1
curl -s https://ai-gateway.vercel.sh/v1/models \
2
  | jq '.data[] | select(.id == "openai/gpt-oss-20b" or .id == "openai/gpt-oss-120b")'
3

Then, if you have an AI Gateway key, compare the endpoint metadata too:

1
curl -s https://ai-gateway.vercel.sh/v1/models/openai/gpt-oss-20b/endpoints \
2
  -H "Authorization: Bearer $AI_GATEWAY_API_KEY"
3

4
curl -s https://ai-gateway.vercel.sh/v1/models/openai/gpt-oss-120b/endpoints \
5
  -H "Authorization: Bearer $AI_GATEWAY_API_KEY"
6

If only the name field is wrong but the IDs, endpoints, pricing/context fields, and generation records differ correctly, then it is probably a catalog/display bug. If the 20B ID returns the same endpoint/pricing/usage behavior as 120B, then that is stronger evidence of a routing/config issue.

For a clean bug report, I’d include:

1
model id: openai/gpt-oss-20b
2
incorrect name returned: GPT OSS 120B
3
timestamp:
4
output from /v1/models for both 20B and 120B:
5
generationId from one tiny test request, if available:
6

Don’t include the AI Gateway key.