Fast and cost-efficient variant of GPT-5.4 with 400K context window and 128K output tokens. Excellent balance of performance and affordability for everyday tasks.
Copy usage instructions for Claude, ChatGPT, or other AI
| Token Type | Credits | USD Equivalent |
|---|---|---|
| Input Tokens | 750 | $0.75 |
| Output Tokens | 4,500 | $4.50 |
* 1 credit โ $0.001 (actual charges may vary based on usage)
curl -X POST "https://api.core.today/llm/openai/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer cdt_your_api_key" \
-d '{
"model": "gpt-5.4-mini",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Explain the difference between REST and GraphQL APIs with pros and cons."
}
],
"temperature": 0.7,
"max_completion_tokens": 2000
}'| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
messages | array | Yes | - | Array of message objects with role and content |
model | string | Yes | gpt-5.4-mini | Model identifier |
max_completion_tokens | integer | No | 4096 | Maximum tokens in response (up to 128000). Note: use max_completion_tokens, not max_tokens |
temperature | float | No | 1.0 | Sampling temperature (0-2) |
stream | boolean | No | false | Enable Server-Sent Events streaming |
top_p | float | No | 1.0 | Nucleus sampling threshold (0-1) |
Efficient conversation with GPT-5.4 Mini
curl -X POST "https://api.core.today/llm/openai/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer cdt_your_api_key" \
-d '{
"model": "gpt-5.4-mini",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Explain the difference between REST and GraphQL APIs with pros and cons."
}
],
"temperature": 0.7,
"max_completion_tokens": 2000
}'POST /llm/openai/v1/chat/completions