Chat completions
Access via unified chat/completions or jobs paths with streaming support.

ANTHROPIC
Send multi-turn messages with the same model and gateway as production API calls.
OpenAI-compatible chat/completions request body fields.
| Field | Type | Required |
|---|---|---|
| model | string | Yes |
| messages | { role, content }[] | Yes |
Typical generation previews (actual output varies by prompt).

Core capabilities for this model on the ModKie gateway.
Access via unified chat/completions or jobs paths with streaming support.
Credits apply per successful chat completion.
Shared API
2 credits / request
≈ $0.01 USD ($0.01 USD/credit at pack rate)
Three steps from API key to your first chat completion.
Create an API key
Sign in and create a key under Settings → API Keys.
Submit createTask
POST to /api/v1/jobs/createTask with your model id and input payload.
Poll recordInfo
Poll recordInfo until the job completes; download outputs from the response.
Example chat completions request
curl -X POST https://modkie.com/api/gateway/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"provider": "kie",
"model": "claude-haiku-4-5",
"messages": [
{
"role": "user",
"content": "Explain how async job polling works for video generation APIs."
}
]
}'Read assistant text from choices[0].message.content in the JSON response. Credits apply per successful completion.
ModKie is more than API relay — deploy, fine-tune, and register custom endpoints on the same gateway.
One API key and jobs contract across marketplace and self-hosted models.
Validate payloads in-browser before shipping to production.
Deploy HuggingFace or custom workers and route traffic through ModKie.
Fine-tune vision models and register weights back into the gateway.
Work with our team on model landing, integration, and production rollout.