gpt
OpenAI GPT models via inference.sh CLI. Models: GPT-6 Astra (frontier), GPT-6.1 Sol (near-Astra at lower cost), GPT-6 Luna (efficient, high-volume). 1M context, 128k output, reasoning effort, vision, file input, tool use, structured output. Daybreak variants for vetted cybersecurity work on your own OpenAI key. Use for: coding, agents, reasoning, document analysis, extraction, chat, high-volume classification. Triggers: gpt, openai, gpt-6, gpt 6, gpt-6 astra, gpt-6.1 sol, gpt-6 luna, openai api, chatgpt api, gpt api, openai model, daybreak, openai daybreak, gpt reasoning
Try your first task
A source-grounded starter task has not been verified for this skill yet.
SKILL.md
name: gptdescription: "OpenAI GPT models via inference.sh CLI. Models: GPT-6 Astra (frontier), GPT-6.1 Sol (near-Astra at lower cost), GPT-6 Luna (efficient, high-volume). 1M context, 128k output, reasoning effort, vision, file input, tool use, structured output. Daybreak variants for vetted cybersecurity work on your own OpenAI key. Use for: coding, agents, reasoning, document analysis, extraction, chat, high-volume classification. Triggers: gpt, openai, gpt-6, gpt 6, gpt-6 astra, gpt-6.1 sol, gpt-6 luna, openai api, chatgpt api, gpt api, openai model, daybreak, openai daybreak, gpt reasoning"allowed-tools: Bash(belt *)Install the belt CLI skill:
npx skills add belt-sh/cli
GPT
Run OpenAI's GPT-6 models via inference.sh CLI.
Quick Start
Requires inference.sh CLI (
belt). Install instructions
belt login
belt app run openai/gpt-6-1-sol --input '{"text": "Explain the CAP theorem with an example"}'
Models
| Model | App ID | Best For |
|---|---|---|
| GPT-6 Astra | openai/gpt-6-astra | OpenAI's frontier model |
| GPT-6.1 Sol | openai/gpt-6-1-sol | Near-Astra quality at a fraction of the cost |
| GPT-6 Luna | openai/gpt-6-luna | Most efficient, focused high-volume tasks |
All three: 1M context, 128k output, reasoning, vision, file input and tool use via the OpenAI Responses API. Direct API.
Daybreak Variants
openai/gpt-6-astra-daybreak, openai/gpt-6-1-sol-daybreak, openai/gpt-6-luna-daybreak are for security teams in OpenAI's Daybreak program (Trusted Access for Cyber). They run on your own Daybreak-enabled OpenAI project key, and OpenAI bills your organization directly. Reduced refusals require OpenAI approval (Red for Astra and Sol; Blue or Red for Luna). Connect the key once per workspace:
belt credentials connect openai-daybreak --team
Older GPT versions: belt app search gpt.
Inputs
| Field | Description |
|---|---|
text | The user message |
system_prompt | System instructions |
images | Image files or URLs (vision) |
files | Document files |
context | Prior messages: [{"role": "user" | "assistant", "text": "..."}] |
reasoning_effort | none (default), low, medium, high |
temperature | Default 0.7 |
max_tokens | Default 64000 |
tools | Function tool definitions |
tool_choice | {"mode": "auto" | "none" | "required" | "function", "name": ...} |
response_format | {"type": "text" | "json_object" | "json_schema", ...} |
Output: response, reasoning, tool_calls, usage.
Each app also has an openai function that takes Chat Completions messages directly: belt app sample openai/gpt-6-astra -f openai.
Examples
Frontier Reasoning with Astra
belt app run openai/gpt-6-astra --input '{
"text": "Prove that there are infinitely many primes of the form 4k+3",
"reasoning_effort": "high"
}'
Everyday Coding with Sol
belt app run openai/gpt-6-1-sol --input '{
"system_prompt": "You are a TypeScript expert. Return only code.",
"text": "Write a debounce hook for React with cancel support",
"reasoning_effort": "medium"
}'
High Volume with Luna
belt app run openai/gpt-6-luna --input '{
"text": "Tag this support ticket as billing, bug, or feature-request: I was charged twice this month.",
"reasoning_effort": "none",
"max_tokens": 10
}'
Document Analysis
belt app run openai/gpt-6-1-sol --input '{
"text": "List every payment obligation and its due date in this contract",
"files": ["https://example.com/contract.pdf"]
}'
Vision
belt app run openai/gpt-6-astra --input '{
"text": "Transcribe the handwritten notes in this photo",
"images": ["https://example.com/notes.jpg"]
}'
Structured Output
belt app run openai/gpt-6-luna --input '{
"text": "Extract name and email: Contact Jane Doe at jane@example.com",
"response_format": {
"type": "json_schema",
"name": "contact",
"json_schema": {
"type": "object",
"properties": {"name": {"type": "string"}, "email": {"type": "string"}},
"required": ["name", "email"]
}
}
}'
Tool Use
belt app run openai/gpt-6-1-sol --input '{
"text": "Book a table for two at 7pm",
"tools": [{
"type": "function",
"function": {
"name": "book_table",
"description": "Reserve a restaurant table",
"parameters": {
"type": "object",
"properties": {"party_size": {"type": "integer"}, "time": {"type": "string"}},
"required": ["party_size", "time"]
}
}
}],
"tool_choice": {"mode": "auto"}
}'
Batch Inputs
# one JSON input per line
belt app run openai/gpt-6-luna --batch inputs.jsonl
Pricing
| Model | Input | Cached input | Output |
|---|---|---|---|
| GPT-6 Astra | $10.00/M | $1.00/M | $50.00/M |
| GPT-6.1 Sol | $2.00/M | $0.10/M | $10.00/M |
| GPT-6 Luna | $0.10/M | $0.01/M | $0.50/M |
Daybreak variants bill your OpenAI organization. Estimate a run: belt app estimate <app-id> --input input.json.
Related Skills
# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli
# All LLMs in one place
npx skills add inference-sh/skills@llm-models
# Other providers
npx skills add inference-sh/skills@claude
npx skills add inference-sh/skills@gemini
# Agents and tool use
npx skills add inference-sh/skills@agent-tools
# Web search for grounding
npx skills add inference-sh/skills@web-search
Browse all apps: belt app list
Documentation
- Agents Overview - Building AI agents
- Running Apps - How to run apps via CLI