OpenAILLMAvailable now

~openai/gpt-luna-latest

Name: ~openai/gpt-luna-latest
Brand: OpenAI

~openai/gpt-luna-latest is an LLM tool from OpenAI that runs in the background and returns text and structured JSON. Pay as you go, with one API key.

Try it

Pricing

Up to $0.002669 per run at the default inputs. $0.13 per 1M input tokens, $0.013 per 1M cached input tokens, $0.1625 per 1M cache write tokens, $0.65 per 1M output tokens.

Limits

Runs: In the background
Returns: text, json
Longest queue wait: 1 hour
Run deadline: 30 minutes
Longest run, end to end: 225 minutes
Largest inline input: 1 MB
Largest input file: 500 MB
Largest output: 5 GB
Outputs per run: 16

Input

Field	Kind	Default	Description
`messages` required	JSON	—	The conversation so far, oldest first.
`seed`	number (whole)	—
`stop`	JSON	—
`tools`	JSON	—
`top_p`	number	—	Taken only with reasoning effort "none".
`logprobs`	true or false	—	Taken only with reasoning effort "none".
`reasoning`	JSON	—	Reasoning effort; reasoning tokens count toward max_tokens.
`max_tokens`	number (whole) 1 to 128000	—	The most output tokens to generate.
`temperature`	number	—	Taken only with reasoning effort "none".
`tool_choice`	JSON	—
`top_logprobs`	number (whole)	—	Taken only with reasoning effort "none".
`response_format`	JSON	—
`presence_penalty`	number	—	Taken only with reasoning effort "none".
`reasoning_effort`	one of none, low, medium, high, xhigh, max	medium	How much the model reasons.
`frequency_penalty`	number	—	Taken only with reasoning effort "none".
`parallel_tool_calls`	true or false	—

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openai",
    "model": "~openai/gpt-luna-latest",
    "input": {
      "messages": {}
    }
  }'