GPT-5 Mini

openai/gpt-5-mini

GPT-5 mini is the faster, more efficient tier of OpenAI's GPT-5 reasoning family, released in August 2025 with text and image input and text output. OpenAI recommends it for well-defined tasks and precise prompts in low-latency, high-volume workloads, keeping GPT-5's configurable reasoning. Choose it over full GPT-5 when speed and throughput matter more than maximum depth; OpenAI's later small models are its suggested successors.

Input price
$0.25USD / 1M tokens
Output price
$2.00USD / 1M tokens
Cache read
$0.03USD / 1M tokens
Context window
400K
Max output
128K

Specifications

CapabilitiesChatVisionReasoningStructured outputFunction calling
Input
Text, image
Output
Text
Available

Questions

FAQ

How do I call OpenAI GPT-5 Mini through SandBase?

Create a SandBase API key, then send requests with the model ID "openai/gpt-5-mini" to Responses API (/v1/responses) or Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does OpenAI GPT-5 Mini cost?

$0.25 per 1M input tokens and $2 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

What is the context window of OpenAI GPT-5 Mini?

400K tokens of context, with up to 128K output tokens per response.

Which features does OpenAI GPT-5 Mini support?

OpenAI GPT-5 Mini supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate OpenAI account?

No. One SandBase API key and balance gives you access to OpenAI GPT-5 Mini and the other models in the catalog; you do not need to sign up with OpenAI separately.