Models - Runtools.ai

{ "data": { "platform": [ { "model": "claude-opus-4.6", "displayName": "Claude Opus 4.6", "available": true } ], "byok": [ { "model": "gpt-5", "displayName": "GPT-5", "requiresSecret": "OPENAI_API_KEY", "available": false } ] } }

Availability

GET /v1/models/available returns the models currently visible to the caller. Platform models are served by Runtools-managed capacity and billed by token usage. BYOK models use user- or org-provided provider keys and are marked available only when the required secret exists.

The API intentionally does not expose internal platform provider routing. Customers should treat Platform models as Runtools-managed models.

array

Platform model entries with model, displayName, and available.

array

BYOK model entries with model, displayName, requiresSecret, and available.

curl https://api.runtools.ai/v1/models/available \
  -H "X-API-Key: $RUNTOOLS_API_KEY"

{
  "data": {
    "platform": [
      {
        "model": "claude-opus-4.6",
        "displayName": "Claude Opus 4.6",
        "available": true
      }
    ],
    "byok": [
      {
        "model": "gpt-5",
        "displayName": "GPT-5",
        "requiresSecret": "OPENAI_API_KEY",
        "available": false
      }
    ]
  }
}

Platform Model Proxy

Advanced local runtimes can call the platform model proxy directly. Normal agent runs do not need this endpoint; POST /v1/run handles model calls for you.

Method	Path	Description
`POST`	`/v1/model-proxy`	Non-streaming platform model call
`POST`	`/v1/model-proxy/stream`	Streaming platform model call as newline-delimited JSON

string

required

Model identifier.

object

required

Provider-neutral generation options passed through to the model gateway.

string

default:"platform"

Only platform is accepted by the public model proxy. BYOK calls use local or agent-host credentials instead.

cURL

curl -X POST https://api.runtools.ai/v1/model-proxy \
  -H "X-API-Key: $RUNTOOLS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4.6",
    "options": {
      "messages": [
        { "role": "user", "content": "Say hello." }
      ]
    }
  }'

The streaming variant returns:

Content-Type: application/x-ndjson
Cache-Control: no-cache

Billing

Platform model calls are charged by token usage. BYOK model usage is not charged as Runtools platform inference usage, because the call uses the customer’s own key.

​Availability

​Platform Model Proxy

​Billing

Availability

Platform Model Proxy

Billing