phantom-1

Three models. One chat model ID.

phantom-1 chooses from an economy, standard or frontier chat model at the start of a conversation. The selected model handles follow-ups unless the route is escalated or a fallback occurs. You pay the applicable rate of the model that actually runs.

These are the defaults. A key can run another model in any tier: pick it in the key’s controls, or send PUT /v1/key/lineup.

How routing works

Phantom makes a model selection when a new chat conversation begins. It filters out the models that can’t accept the request, then selects from the models that remain. Follow-up requests stay with that model unless you ask to escalate or a fallback is needed.

A chat request with an image runs Qwen 3.7 Flash, an image-capable model outside the three text tiers.

curl https://phantom.codes/v1/key/route/test \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "phantom-1",
    "messages": [{
      "role": "user",
      "content": "Find the race condition in the webhook worker."
    }]
  }'

Control how requests are routed

Choose when to exclude free models, restrict providers by data handling policy, or escalate a conversation. These controls affect which models Phantom can select. Phantom keeps no prompt or completion text; these flags govern what the upstream provider may keep, and they are off unless you send them.

curl -i https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -H "x-phantom-session: refund-bug" \
  -d '{
    "model": "phantom-1",
    "zdr": true,
    "messages": [{
      "role": "user",
      "content": "Find the race condition in the webhook worker."
    }]
  }'

Request controls

Response metadata

HTTP/2 200
x-phantom-router: phantom-1
x-phantom-fallback: false
x-phantom-cost-usd: 0.003120
x-phantom-receipt: <signed receipt, base64>

Measured results, with the tradeoffs shown

These historical evaluations compare the model selected by the router with running a frontier model for every task. The results show both the savings and the accuracy differences. They are not a guarantee for future requests or the currently deployed routing configuration.

One familiar model ID across API endpoints

Chat uses automatic routing. On supported non-chat endpoints, phantom-1 maps to a specific model for that operation. The same API key and model name work across these endpoints, but non-chat calls do not run the three-model chat router.