I stopped hardcoding model IDs. models.dev + /v1/models changed the workflow

Disclosure and availability: DaoXE is a multi-model multi-protocol API gateway we operate. It is listed on models.dev as provider key daoxe with api=https://daoxe.com/v1 and env DAOXE_API_KEY. It is not available in mainland China. This article is for developers in regions allowed by the service terms.

For a long time my gateway setup notes looked like this:

base_url = https://something/v1

model    = gpt-4o-mini   # hope this still exists

That pattern fails in three predictable ways:

1. The blog model ID is not in your account catalog.


2. The host is correct, but the provider key your client expects is different.


3. The catalog moved and your README did not.

This post is the discovery workflow I use now: public catalog first, account catalog second, client third.

Series context

Earlier posts covered smoke tests, multiprotocol checks, client setup, and IDE failure isolation:

3. is a public provider/model catalog many coding tools read.
   
   
   

   When a gateway lands there, clients that support custom / catalog-driven providers can resolve:

   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   

   Field	Why it matters
   provider key	stable id for configs (daoxe, not a marketing name)
   api base	host + /v1 shape
   env var	which secret name tools expect

   
   
   

   For DaoXE the live catalog entry is effectively:
   
   

   
   
   
   
   

   CODE Kopieren

   key: daoxe
   
   api: https://daoxe.com/v1
   
   env: DAOXE_API_KEY
   
   

   
   
   
   
   
   
   
   

   That is public discovery, not proof your account can call every model.

   
   
   

   
   
   
   2. Account catalog: GET /v1/models
   

   
   
   

   Public catalogs and account catalogs are different objects.
   
   

   
   
   
   
   

   CODE Kopieren

   export DAOXE_API_KEY="your_api_key"
   
   export DAOXE_BASE_URL="https://daoxe.com/v1"
   
   
   
   curl --fail-with-body --show-error --silent \
   
     -H "Authorization: Bearer $DAOXE_API_KEY" \
   
     "$DAOXE_BASE_URL/models"
   
   

   
   
   
   
   
   
   
   

   I treat the response as live data for this account only:

   
   
   
   
   
   • copy an exact id
     
   
   
   • do not invent IDs from screenshots
   
   
   • do not assume yesterday's list is still valid
   
   
   
   
   

   If /models returns 401, stop blaming the IDE. Fix auth first.

   
   
   

   
   
   
   3. One tiny Chat Completions smoke with that exact ID
   

   
   
   
   
   
   
   

   CODE Kopieren

   export DAOXE_MODEL="paste_exact_id_from_models_response"
   
   
   
   curl --fail-with-body --show-error --silent \
   
     -H "Authorization: Bearer $DAOXE_API_KEY" \
   
     -H "Content-Type: application/json" \
   
     -d "{
   
       \"model\": \"$DAOXE_MODEL\",
   
       \"max_tokens\": 8,
   
       \"messages\": [{\"role\":\"user\",\"content\":\"Reply with OK.\"}]
   
     }" \
   
     "$DAOXE_BASE_URL/chat/completions"
   
   

   
   
   
   
   
   
   
   

   Only after this returns HTTP 200 do I open Cline / Continue / Claude-shaped tools.

   
   
   

   
   
   
   4. Wire the client to the same triple
   

   
   
   

   The only triple that should move between tools:

   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   

   Piece	Example for DaoXE
   Base URL	https://daoxe.com/v1
   API key storage	env / secret store (DAOXE_API_KEY or the client's custom key field)
   Model ID	exact id from /v1/models now

   
   
   

   Public setup notes:

   
   
   
   
   
   
   
   
   
   

   
   
   
   Footguns this workflow prevents
   

   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   
   

   Footgun	Symptom	Fix
   Blog model ID	model_not_found	re-copy from /v1/models
   Marketing name as API id	client 400	use catalog id, not label
   Public catalog only	"listed but my key fails"	public catalog ≠ account access
   Account catalog only	"works for me, not for teammate"	each account has its own list
   Skipping smoke	IDE red noise	curl first

   
   
   

   
   
   
   What success looks like
   

   
   
   

   Success is not "every model on models.dev works for every key."

   
   
   

   Success is:

   
   
   
   
   
   1. you can find the gateway in a public catalog or docs
   
   
   2. you can list models for your key
   
   
   3. you can call one model with a tiny request
   
   
   4. you can clone that triple into one client without guessing
   
   
   
   
   

   
   
   
   Soft CTA
   

   
   
   

   If you want the product side of this writeup:

   
   
   

   https://daoxe.com/?utm_source=devto&utm_medium=organic&utm_campaign=global_launch_modelsdev

   
   
   

   If something fails, comment with client name + whether /v1/models returned 200 for your key. Do not paste API keys.

   
   
   

   
   
   
   Series
   

   
   
   
   
   
   1. Smoke test
      
   
   
   2. Multiprotocol checklist
      
   
   
   3. Client setup
      
   
   
   4. curl OK, IDE fails
      
   
   
   5. Claude protocol
      
   
   
   6. 
      This post: models.dev + account /models discovery
      
   
   
   Vollständiger Original-Bericht

   Ausführliche Details, Code-Beispiele & Hersteller-Stellungnahme auf dev.to.

   ↗ Original-Artikel auf dev.to lesen