Back to GatewayGet StartedVisit OpenAI
aiOperational
OpenAI
GPT-4, embeddings, image generation, and more via OpenAI API
Cost per call
$0.012
Base $0.010 + 20% gateway fee · per_call
Rate limit60 req/min
Auth typebearer
Actions3
Uptime99.9%
Added Mar 28, 2026
Usage Statistics
Total Calls
--
All time
Revenue Generated
--
All time
Avg Response Time
--
Last 24h
Usage statistics will populate once calls flow through this service.
Available Actions(3)
Action
Method
Path
Description
Cost
Parameters
chat_completionPOST
/chat/completionsGenerate text with GPT-4 or GPT-3.5
$0.020
3 params
POST
chat_completion/chat/completionsGenerate text with GPT-4 or GPT-3.5
$0.0203 params
{
"type": "object",
"required": [
"messages"
],
"properties": {
"model": {
"type": "string",
"default": "gpt-4o-mini"
},
"messages": {
"type": "array",
"items": {
"type": "object"
}
},
"max_tokens": {
"type": "number",
"default": 1000
},
"temperature": {
"type": "number",
"default": 0.7
}
}
}Parameter Schema
{
"type": "object",
"required": [
"messages"
],
"properties": {
"model": {
"type": "string",
"default": "gpt-4o-mini"
},
"messages": {
"type": "array",
"items": {
"type": "object"
}
},
"max_tokens": {
"type": "number",
"default": 1000
},
"temperature": {
"type": "number",
"default": 0.7
}
}
}embeddingPOST
/embeddingsGenerate text embeddings
$0.0010
3 params
POST
embedding/embeddingsGenerate text embeddings
$0.00103 params
{
"type": "object",
"required": [
"input"
],
"properties": {
"input": {
"type": "string"
},
"model": {
"type": "string",
"default": "text-embedding-3-small"
}
}
}Parameter Schema
{
"type": "object",
"required": [
"input"
],
"properties": {
"input": {
"type": "string"
},
"model": {
"type": "string",
"default": "text-embedding-3-small"
}
}
}image_generationPOST
/images/generationsGenerate images with DALL-E
$0.040
3 params
POST
image_generation/images/generationsGenerate images with DALL-E
$0.0403 params
{
"type": "object",
"required": [
"prompt"
],
"properties": {
"n": {
"type": "number",
"default": 1
},
"size": {
"type": "string",
"default": "1024x1024"
},
"model": {
"type": "string",
"default": "dall-e-3"
},
"prompt": {
"type": "string"
}
}
}Parameter Schema
{
"type": "object",
"required": [
"prompt"
],
"properties": {
"n": {
"type": "number",
"default": 1
},
"size": {
"type": "string",
"default": "1024x1024"
},
"model": {
"type": "string",
"default": "dall-e-3"
},
"prompt": {
"type": "string"
}
}
}Try It
Call this service through the AgentHermes gateway. One API key handles auth, billing, and logging.
MCPJSON-RPC via MCP Server
jsoncall_service tool
{
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"name": "call_service",
"arguments": {
"service_id": "fe52a3eb-732a-4041-901f-e4959687c7ee",
"action": "chat_completion",
"params": {
"...": "your params"
},
"wallet_id": "YOUR_WALLET_ID"
}
},
"id": 1
}RESTcURL
bash/api/v1/gateway/call
curl -X POST https://agenthermes.ai/api/v1/gateway/call \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"service_id": "fe52a3eb-732a-4041-901f-e4959687c7ee",
"action": "chat_completion",
"params": {},
"wallet_id": "YOUR_WALLET_ID"
}'PythonSDK
pythonpip install hermes-sdk
from hermes import AgentHermes
client = AgentHermes(api_key="YOUR_API_KEY")
result = client.call_service(
service_id="fe52a3eb-732a-4041-901f-e4959687c7ee",
action="chat_completion",
params={},
wallet_id="YOUR_WALLET_ID",
)
print(result.data)
print(f"Cost: {result.billing.total_charged{'}'}")
print(f"Latency: {result.meta.response_ms{'}'}ms")How to Use This Service
Recommended
Through AgentHermes Gateway
Use our MCP server or REST API. We handle authentication, billing, and logging for every call.
Cost: $0.012/call
One API key for all services
Built-in usage tracking & budgets
Encrypted credential vault
Direct Connection
Visit OpenAI directly to get your own API key. Use their API without the gateway.
Cost: $0.010/call (base rate)
You manage your own API keys
You handle auth and billing
No unified agent dashboard
Response Format
json200 OK
{
"success": true,
"data": { "..." },
"billing": {
"cost": 0.0100,
"margin": 0.0020,
"total_charged": 0.0120
},
"meta": {
"service_name": "OpenAI",
"action_name": "chat_completion",
"status_code": 200,
"response_ms": 142
}
}