GPT-5.6 Luna API Pricing
As of October 10, 2026, GPT-5.6 Luna costs $0.20 per 1M input tokens and $1.20 per 1M output tokens on OpenAI, with cache reads at $0.02 and cache writes at $0.25 per 1M tokens. Across 9 providers on LiteLLM, the input price ranges from $0.20 to $1.00. It has a 922,000-token context window and returns up to 128,000 tokens per response.
- Input
- $0.20 / 1M tokens
- Output
- $1.20 / 1M tokens
- Cache read
- $0.02 / 1M tokens
- Context window
- 922,000 tokens
- Max output
- 128,000 tokens
- Providers
- 9
- Added to LiteLLM
- July 9, 2026
GPT-5.6 Luna pricing by provider
14 listings across 9 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Cache write | Batch in | Batch out | Context |
|---|---|---|---|---|---|---|---|---|
| OpenAI | gpt-5.6-luna | $0.20 | $1.20 | $0.02 | $0.25 | $0.10 | $0.60 | 922K |
| AIHubMix | aihubmix/gpt-5.6-luna | $0.20 | $1.20 | $0.02 | $0.25 | – | – | 1M |
| Amazon Bedrock Mantle | bedrock_mantle/openai.gpt-5.6-luna | $0.22 | $1.32 | $0.022 | $0.275 | – | – | 1M |
| Azure OpenAI | azure/gpt-5.6-luna | $0.20 | $1.20 | $0.02 | $0.25 | – | – | 922K |
| Azure OpenAIsnapshot 2026-07-09 | azure/gpt-5.6-luna-2026-07-09 | $0.20 | $1.20 | $0.02 | $0.25 | – | – | 922K |
| ChatGPT Subscription | chatgpt/gpt-5.6-luna | – | – | – | – | – | – | 1M |
| Databricks | databricks/databricks-gpt-5-6-luna | $1.00 | $6.00 | $0.10 | $1.25 | – | – | 922K |
| GitHub Copilot | github_copilot/gpt-5.6-luna | – | – | – | – | – | – | 200K |
| Perplexity | perplexity/openai/gpt-5.6-luna | $0.20 | $1.20 | $0.02 | – | – | – | – |
| Amazon BedrockGlobal cross-region | global.openai.gpt-5.6-luna | $0.20 | $1.20 | $0.02 | $0.25 | – | – | 1M |
| Amazon BedrockUS cross-region | us.openai.gpt-5.6-luna | $0.22 | $1.32 | $0.022 | $0.275 | – | – | 1M |
| Amazon Bedrock Mantleus-gov-west-1 | bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna | $0.27 | $1.62 | $0.027 | $0.3375 | – | – | 1M |
| Azure OpenAIeu | azure/eu/gpt-5.6-luna | $0.22 | $1.32 | $0.022 | $0.275 | – | – | 922K |
| Azure OpenAIus | azure/us/gpt-5.6-luna | $0.22 | $1.32 | $0.022 | $0.275 | – | – | 922K |
Other GPT-5.6 Luna prices on OpenAI
| Priority input | $0.40 per 1M tokens |
| Priority output | $2.40 per 1M tokens |
| Flex input | $0.10 per 1M tokens |
| Flex output | $0.60 per 1M tokens |
| Input above 272K tokens | $0.40 per 1M tokens |
| Output above 272K tokens | $1.80 per 1M tokens |
| Cache read above 272K tokens | $0.04 per 1M tokens |
| Web search | $10.00 per 1K searches |
What GPT-5.6 Luna costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| OpenAI | $1.00 |
| AIHubMix | $1.00 |
| Azure OpenAI | $1.00 |
| Perplexity | $1.00 |
| OpenAI batch | $0.50 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| OpenAI | $2.24 |
| AIHubMix | $2.24 |
| Azure OpenAI | $2.24 |
| Perplexity | $2.24 |
GPT-5.6 Luna features
Input: text, image. Output: text.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- PDF input
- Reasoning
- Prompt caching
- Web search
Use GPT-5.6 Luna with LiteLLM
Call GPT-5.6 Luna through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="gpt-5.6-luna",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-5.6-luna
litellm_params:
model: gpt-5.6-luna
api_key: os.environ/OPENAI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-5.6-luna",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT-5.6 Luna FAQ
How much does GPT-5.6 Luna cost?
GPT-5.6 Luna costs $0.20 per 1M input tokens and $1.20 per 1M output tokens on OpenAI, with cache reads at $0.02 and cache writes at $0.25 per 1M tokens. Batch requests cost $0.10 per 1M input tokens and $0.60 per 1M output tokens. Above 272K input tokens, input costs $0.40 and output costs $1.80 per 1M tokens. Across 9 providers on LiteLLM, the input price ranges from $0.20 to $1.00.
What is the context window of GPT-5.6 Luna?
GPT-5.6 Luna has a 922,000-token context window and returns up to 128,000 tokens per response.
Which providers offer GPT-5.6 Luna?
GPT-5.6 Luna is available from 9 providers through LiteLLM: OpenAI, AIHubMix, Amazon Bedrock Mantle, Azure OpenAI, ChatGPT Subscription, Databricks, GitHub Copilot, Perplexity and Amazon Bedrock. The lowest price is on OpenAI.
How do I call GPT-5.6 Luna with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gpt-5.6-luna", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does GPT-5.6 Luna support?
GPT-5.6 Luna supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching and web search.
When did LiteLLM add GPT-5.6 Luna?
GPT-5.6 Luna was added to LiteLLM's model price file on July 9, 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- developers.openai.com/api/docs/pricing
- aihubmix.com/api/v1/models
- docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
LiteLLM docs: OpenAI, AIHubMix, Amazon Bedrock Mantle, Azure OpenAI, ChatGPT Subscription, Databricks.
Provider pages: OpenAI, AIHubMix, Amazon Bedrock Mantle, Azure OpenAI, ChatGPT Subscription, Databricks, GitHub Copilot, Perplexity, Amazon Bedrock.
