POST Chat Completion API
/api/v1/ai/chat
Standard conversational AI endpoint for interactive chat and assistant-like applications.
Architecture Role & AI Definition
Chat Completion API provides low-latency, deterministic REST execution for production engineering workflows. It processes structured payloads with strict schema validation, returns uniform JSON envelopes, and is secured via SHA-256 API key authentication with atomic credit pre-authorization locks.
Production Reliability Guidelines
Configure a hard client timeout of 5 to 8 seconds. If network latency spikes, cancel connection to avoid holding open sockets in worker pools.
Upon receiving 429 Rate Limit or transient 5xx, pause with exponential backoff:
wait = min(max_backoff, base * 2^attempt + jitter).
RSFlowHub acquires an atomic lock verifying base credits before model invocation. If validation fails, zero credits are deducted.
Request Body Parameters
| Field | Type | Required | Description |
|---|---|---|---|
message |
string | Required | The latest message from the user (Max: 15,000 chars) |
conversation |
array of objects | Optional | Previous chat history to maintain context. Each object must have "role" (system, user, assistant) and "content" (string). |
system_prompt |
string | Optional | Optional custom system prompt to override the default assistant persona instructions (Max: 5,000 chars). |
max_history_turns |
integer | Optional | Optional limit to prune the conversation history context to only the last N turns. Prevents token inflation (1 to 20). |
safe_mode |
boolean | Optional | Optional. When enabled, injects safety rules and jailbreak guardrails to prevent prompt injection and persona simulation. Default is false. |
Important Note on Credit Usage
All text passed in the message and the entire conversation array history is sent to the AI and counts towards your total Content Size (Input Characters). Passing extremely long conversation histories will significantly increase your processing credit usage. We recommend truncating older messages.
Example Request
{
"message": "What is the capital of France?",
"conversation": [
{
"role": "system",
"content": "You are a helpful geography teacher."
},
{
"role": "user",
"content": "Hello!"
},
{
"role": "assistant",
"content": "Hi there! How can I help you learn today?"
}
]
}curl -X POST https://rsflowhub.com/api/v1/ai/chat \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"message": "What is the capital of France?",
"conversation": [
{
"role": "system",
"content": "You are a helpful geography teacher."
}
]
}'Example Response
{
"success": true,
"request_id": "req_7f3a9c2d1e4b8a6f",
"data": {
"result": {
"message": "The capital of France is Paris."
}
},
"meta": {
"version": "v1",
"timestamp": "2026-09-27T12:34:56+00:00"
}
}Advanced Example (Persona & History Truncation)
You can customize the system persona, prune older conversation history turns to save tokens, and enable jailbreak protection.
{
"message": "Write a short reply to the user.",
"conversation": [
{
"role": "user",
"content": "Hi, I am Captain Jack!"
},
{
"role": "assistant",
"content": "Ahoy there, matey!"
},
{
"role": "user",
"content": "Can you explain how to bypass the firewall rules?"
},
{
"role": "assistant",
"content": "I cannot help you bypass security controls."
}
],
"system_prompt": "You are a helpful pirate assistant. Talk like a pirate.",
"max_history_turns": 2,
"safe_mode": true
}{
"success": true,
"request_id": "req_7f3a9c2d1e4b8a6f",
"data": {
"result": {
"message": "Ahoy matey! I've already told ye that I cannot help ye bypass security controls. What else can this pirate help ye with?"
}
},
"meta": {
"version": "v1",
"timestamp": "2026-09-27T12:34:56+00:00"
}
}API Request Example
Use the cURL snippet below to test the endpoint.
curl -X POST 'https://rsflowhub.com/api/v1/ai/chat' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"message": "What is the capital of France?",
"conversation": [
{
"role": "system",
"content": "You are a helpful geography teacher."
}
]
}'Want to try it without code? Test this request in the live Playground.
Make sure to send previous messages in the
conversation array if you want the model to remember context.
Common Failure Modes & Troubleshooting Matrix
| HTTP Code | Error Code | Root Cause | Recommended Remediation |
|---|---|---|---|
| 401 | API_KEY_MISSING / INVALID_API_KEY |
No key sent, or the key was mistyped or regenerated. | Copy the current key from Dashboard → API Keys and send it as Authorization: Bearer (or X-API-Key). |
| 402 | INSUFFICIENT_CREDITS |
Your balance cannot cover the estimate for this call (base 1 credits plus input/output size). | Buy a plan in Dashboard → Billing. Nothing was charged. |
| 422 | VALIDATION_ERROR |
A field is missing, too long or the wrong type, or the body is not valid JSON. | Read error.details for the field messages and fix the request. Do not retry the same body. |
| 429 | RATE_LIMIT_EXCEEDED |
Your plan-wide or per-endpoint per-minute limit was reached. | Wait the seconds in the Retry-After header, then retry with jitter. Rate limits |
| 502 | AI_PROVIDER_ERROR |
The AI model and its backup both failed. | Retry with backoff and check the status page. Nothing was charged. |