GPT-6 Luna
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.
gpt-6-lunaReleased 22 Sep 2026 (8 weeks ago)Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.10 | $0.50 | |
| Cached input 90% off input | $0.01 | 90% off input | |
| Cache write, 5 minutes | $0.125 | ||
| Batch 50% off | $0.05 | $0.25 | 50% off |
| Flex 50% off | $0.05 | $0.25 | 50% off |
| Priority 100% more | $0.20 | $1.00 | 100% more |
| Prompts over 272K tokens | $0.20 | $0.75 | |
| Web search $10.00 per 1,000 searches | $10.00 per 1,000 searches | ||
| Regional endpoints 10% more | 10% more |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$59.40
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$44.40
- Coding agent1,000 requests a day, 40K in / 2K out, cached$74.40
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$180
Where to run it
10 hosts serve GPT-6 Luna. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-6-luna | $0.10 / $0.50 | gpt-6-luna | |
Amazon BedrockCloud openai.gpt-6-luna | $0.10 / $0.50 | openai.gpt-6-luna | |
Azure OpenAICloud gpt-6-luna | $0.10 / $0.50 Retires 11 Mar 2028 | gpt-6-luna | Retires 11 Mar 2028 |
Azure AI FoundryCloud gpt-6-luna | $0.10 / $0.50 | gpt-6-luna | |
OpenCode GoCloud gpt-6-luna | $0.10 / $0.50 | gpt-6-luna | |
ZeroGPUCloud gpt-6-luna | $0.10 / $0.50 | gpt-6-luna | |
GMI CloudInference gpt-6-luna | $0.10 / $0.50 | gpt-6-luna | |
PerplexityGateway gpt-6-luna | $0.10 / $0.50 | gpt-6-luna | |
DatabricksCloud databricks-gpt-6-luna | $0.10 / $0.50 | databricks-gpt-6-luna | |
Kyma APICloud gpt-6-luna | $0.164 / $0.82 +64% vs headline | gpt-6-luna | |
GitHub CopilotSubscription gpt-6-luna | In the subscription | gpt-6-luna | |
ChatGPTSubscription gpt-6-luna | In the subscription | gpt-6-luna |
Show 6 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| global global.openai.gpt-6-luna | $0.10 / $0.50 | global.openai.gpt-6-luna | |||||
| Mantle openai.gpt-6-luna | $0.11 / $0.55 +10% vs headline | openai.gpt-6-luna | |||||
| us us.openai.gpt-6-luna | $0.11 / $0.55 +10% vs headline | us.openai.gpt-6-luna | |||||
| Azure OpenAI | |||||||
| 2026-09-22 gpt-6-luna-2026-09-22 | $0.10 / $0.50 Retires 11 Mar 2028 | gpt-6-luna-2026-09-22 | Retires 11 Mar 2028 | ||||
| us gpt-6-luna | $0.11 / $0.55 +10% vs headline Retires 11 Mar 2028 | gpt-6-luna | Retires 11 Mar 2028 | ||||
| eu gpt-6-luna | $0.12 / $0.60 +20% vs headline Retires 11 Mar 2028 | gpt-6-luna | Retires 11 Mar 2028 | ||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- ImagesTextPDFs
- Produces
- Text
- Effort settings the source lists
- nonexhighmax
- Features
- Computer useParallel tool callsPDF inputPrompt cachingTool searchBuilt-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than OpenAI.
Smaller OpenAI models
No cheaper OpenAI model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 10% less
- 11% less
- 29% less
- 30% less
Model line
Newer and older versions, at each lab's own price.
- Sep 2026GPT-6 LunaLatest$0.10 / $0.50
- Jul 2026GPT-5.6 Luna$0.20 / $1.20
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-6-luna", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-6-luna", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-6-luna",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-6 Luna cost?
On OpenAI, GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens. Cached input costs $0.01 per million tokens.
Which APIs offer GPT-6 Luna?
GPT-6 Luna runs on 10 APIs: OpenAI, Amazon Bedrock, Azure OpenAI, Azure AI Foundry, OpenCode Go, ZeroGPU, GMI Cloud, Perplexity, Databricks and Kyma API.
What is GPT-6 Luna's context window?
922K tokens, with up to 128K tokens in one reply.
Is GPT-6 Luna being retired?
Azure OpenAI retires it on 11 Mar 2028. 9 hosts keep serving it.
Is there a newer version of GPT-6 Luna?
No. GPT-6 Luna is the newest model in its line.
What are cheaper alternatives to GPT-6 Luna?
Models that cost less and keep most of what it can do: Qwen3.8 Flash on AIHubMix (10% less). Savings are on a mix of 3 input tokens to 1 output token.
When was GPT-6 Luna released?
OpenAI released it on 22 Sep 2026.
What is GPT-6 Luna's API model id?
Use gpt-6-luna with OpenAI. Other hosts use their own ids: openai.gpt-6-luna on Amazon Bedrock, databricks-gpt-6-luna on Databricks.
Sources
- Databricks pricing
- Amazon Bedrock pricing
- Azure OpenAI pricing
- Azure AI Foundry pricing
- ChatGPT pricing
- GitHub Copilot pricing
- GMI Cloud pricing
- OpenAI pricing
- OpenCode Go pricing
- Perplexity pricing
- ZeroGPU pricing
- LiteLLM model map
Raw catalog entry for gpt-6-luna on OpenAI
{
"cache_creation_input_token_cost": 1.25e-7,
"cache_creation_input_token_cost_above_12hr": 2.5e-7,
"cache_creation_input_token_cost_above_12hr_batches": 1.25e-7,
"cache_creation_input_token_cost_above_12hr_above_272k_tokens": 5e-7,
"cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 2.5e-7,
"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 2.5e-7,
"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 0.000001,
"cache_creation_input_token_cost_above_12hr_flex": 1.25e-7,
"cache_creation_input_token_cost_above_12hr_priority": 5e-7,
"cache_creation_input_token_cost_decisions": 1.25e-7,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-7,
"cache_creation_input_token_cost_above_272k_tokens_decisions": 2.5e-7,
"cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-7,
"cache_creation_input_token_cost_above_272k_tokens_priority": 5e-7,
"cache_creation_input_token_cost_flex": 6.25e-8,
"cache_creation_input_token_cost_priority": 2.5e-7,
"cache_read_input_token_cost": 1e-8,
"cache_read_input_token_cost_decisions": 1e-8,
"cache_read_input_token_cost_above_272k_tokens": 2e-8,
"cache_read_input_token_cost_above_272k_tokens_decisions": 2e-8,
"cache_read_input_token_cost_above_272k_tokens_flex": 1e-8,
"cache_read_input_token_cost_above_272k_tokens_priority": 4e-8,
"cache_read_input_token_cost_batches": 5e-9,
"cache_read_input_token_cost_above_272k_tokens_batches": 1e-8,
"cache_creation_input_token_cost_batches": 6.25e-8,
"cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-7,
"cache_read_input_token_cost_flex": 5e-9,
"cache_read_input_token_cost_priority": 2e-8,
"input_cost_per_token": 1e-7,
"input_cost_per_token_decisions": 1e-7,
"input_cost_per_token_above_272k_tokens": 2e-7,
"input_cost_per_token_above_272k_tokens_decisions": 2e-7,
"input_cost_per_token_above_272k_tokens_flex": 1e-7,
"input_cost_per_token_above_272k_tokens_priority": 4e-7,
"input_cost_per_token_batches": 5e-8,
"input_cost_per_token_above_272k_tokens_batches": 1e-7,
"input_cost_per_token_flex": 5e-8,
"input_cost_per_token_priority": 2e-7,
"litellm_provider": "openai",
"max_input_tokens": 922000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-7,
"output_cost_per_token_decisions": 0,
"output_cost_per_token_above_272k_tokens": 7.5e-7,
"output_cost_per_token_above_272k_tokens_decisions": 0,
"output_cost_per_token_above_272k_tokens_flex": 3.75e-7,
"output_cost_per_token_above_272k_tokens_priority": 0.0000015,
"output_cost_per_token_batches": 2.5e-7,
"output_cost_per_token_above_272k_tokens_batches": 3.75e-7,
"output_cost_per_token_flex": 2.5e-7,
"output_cost_per_token_priority": 0.000001,
"reasoning_contexts": [
"auto",
"current_turn",
"all_turns"
],
"reasoning_modes": [
"standard",
"pro"
],
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"fedramp_uplift_multiplier": 1.1,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://developers.openai.com/api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses",
"/v1/decisions"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_minimal_reasoning_effort": false,
"supports_native_streaming": true,
"supports_none_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_cache_breakpoint": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_tool_search": true,
"supports_vision": true,
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
}