GPT 5.6 Luna
openai/gpt-5.6-lunaGPT 5.6 Luna is a reasoning model by OpenAI with vision, function calling, prompt caching, structured output — designed for complex, multi-step problem solving where accuracy matters more than speed. It supports a 1.1M token context window with up to 128K tokens of output. Priced at $0.2 per million input tokens and $1.2 per million output tokens, it is one of the most cost-efficient options in its class. Access GPT 5.6 Luna through Inworld LLM Inference with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.
- Input
- $0.20
- Output
- $1.20
- Cache read
- $0.02
- Context
- 1.1M
- Max output
- 128K
curl --fail-with-body https://api.inworld.ai/v1/chat/completions \
-H "Authorization: Basic $INWORLD_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "openai/gpt-5.6-luna",
"messages": [{"role": "user", "content": "Hello"}],
"stream": true
}'Pricing and providers
Access GPT 5.6 Luna through Inworld LLM Inference or speech to speech via OpenAI. By using the providers below you agree to their terms, listed under each provider's name in the Legal section.
| Modalities | |||||||
|---|---|---|---|---|---|---|---|
OpenAIThis pageopenai/gpt-5.6-luna | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | TextImageFile→Text |
Start building with GPT 5.6 Luna
Access GPT 5.6 Luna and every other model through LLM Inference or speech to speech. Create a free account and start in minutes.