GPT-5 Mini

Model Information

Display Name: GPT-5 Mini

API Model ID: openai/gpt-5-mini

Category: Image To Text

Description: GPT-5 Mini is a compact version of GPT-5 for lighter-weight reasoning tasks. It keeps GPT-5's instruction following and safety tuning with lower latency and cost, over a 400K-token context window. **Key Features:** - 400,000-token context window - Up to 128K output tokens - Multimodal input: text and image - Function/tool calling and structured outputs (JSON schema) - Reasoning with adjustable effort - Prompt caching for cheaper repeated context **Best For:** - High-volume chat and assistant workloads - Everyday reasoning at low cost - Instruction-following and structured extraction - Long-document question answering

Context Window: 400,000 tokens

Max Output: 128,000 tokens

How to Use This Model

To use GPT-5 Mini via the HInow.ai API, use the model ID: openai/gpt-5-mini

API Request Example (Chat/Text)


POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "openai/gpt-5-mini",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}
              

API Request Example (Image Generation)


POST https://api.hinow.ai/v1/images
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "openai/gpt-5-mini",
  "prompt": "Your image description here"
}
              

Pricing

  • input: $0.375
  • output: $3.00

Available Parameters

  • max_tokens: Max tokens to generate, including reasoning (Options: 512, 1024, 2048, 4096, 8192, 16384, 32768, 65536, 128000)
  • reasoning_effort: Reasoning depth. Reasoning cannot be fully disabled on this endpoint (Options: minimal, low, medium, high)
  • seed: Integer seed for reproducible sampling
  • tools: Function/tool definitions for agentic workflows
  • tool_choice: Controls whether the model calls a tool (Options: auto, none, required)
  • response_format: Output format (structured outputs supported) (Options: text, json_object, json_schema)

Quick Reference

To use this model, set: "model": "openai/gpt-5-mini"

Featured: No

Documentation: https://hinow.ai/models/openai/gpt-5-mini

API Endpoint: https://api.hinow.ai/v1

Back to Models
GPT-5 Mini

GPT-5 Mini

openai/gpt-5-mini

$0.375 / $3.00
per 1M tokens (in/out)

About

GPT-5 Mini is a compact version of GPT-5 for lighter-weight reasoning tasks. It keeps GPT-5's instruction following and safety tuning with lower latency and cost, over a 400K-token context window.

Key Features:

  • 400,000-token context window
  • Up to 128K output tokens
  • Multimodal input: text and image
  • Function/tool calling and structured outputs (JSON schema)
  • Reasoning with adjustable effort
  • Prompt caching for cheaper repeated context

Best For:

  • High-volume chat and assistant workloads
  • Everyday reasoning at low cost
  • Instruction-following and structured extraction
  • Long-document question answering

Capabilities

Image To TextText To Text
Context400K tokens
Max Output128K tokens

Parameters

max_tokens

Max tokens to generate, including reasoning

5121024204840968192163843276865536128000
reasoning_effort

Reasoning depth. Reasoning cannot be fully disabled on this endpoint

minimallowmediumhigh
seed

Integer seed for reproducible sampling

tools

Function/tool definitions for agentic workflows

tool_choice

Controls whether the model calls a tool

autononerequired
response_format

Output format (structured outputs supported)

textjson_objectjson_schema

Code Examples

curl -X POST https://api.hinow.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "openai/gpt-5-mini",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Describe this image"},
          {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
        ]
      }
    ],
    "parameters": {
      "max_tokens": "512",
      "reasoning_effort": "minimal",
      "seed": "",
      "tools": "",
      "tool_choice": "auto",
      "response_format": "text"
    }
  }'