impulse

GPT-5.6 Luna

Frontier lab

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.

API id gpt-5.6-lunaReleased 9 Jul 2026 (Jul 2026)
Input / 1M
$0.20
at OpenAI
Output / 1M
$1.20
at OpenAI
Context window
922K
tokens
Max output
128K
tokens per reply
Hosts
11
23 listings
Released
Jul 2026
9 Jul 2026

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.20$1.20
Cached input
90% off input
$0.02
Cache write, 5 minutes$0.25
Batch
50% off
$0.10$0.60
Flex
50% off
$0.10$0.60
Priority
100% more
$0.40$2.40
Prompts over 272K tokens$0.40$1.80
Web search
$10.00 per 1,000 searches
Regional endpoints
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$134
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$96.00
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$161
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$384
Use your own numbers

Where to run it

11 hosts serve GPT-5.6 Luna. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-5.6-luna
$0.20 / $1.20
databricks-gpt-5-6-luna
$0.20 / $1.20
global
global.openai.gpt-5.6-luna
$0.20 / $1.20
gpt-5.6-luna
$0.20 / $1.20
Retires 11 Jan 2028
gpt-5.6-luna
$0.20 / $1.20
ZeroGPUCloud
gpt-5.6-luna
$0.20 / $1.20
AIHubMixGateway
gpt-5.6-luna
$0.20 / $1.20
PerplexityGateway
gpt-5.6-luna
$0.20 / $1.20
gpt-5.6-luna
$0.294 / $1.77
+47% vs headline
GMI CloudInference
gpt-5.6-luna
$1.00 / $6.00
+400% vs headline
ReplicateInference
gpt-5.6-luna
$1.00 / $6.00
+400% vs headline
GitHub CopilotSubscription
gpt-5.6-luna
In the subscription
ChatGPTSubscription
gpt-5.6-luna
In the subscription
Show 10 more listings: regions, snapshots and variants
Amazon Bedrock
Mantle
openai.gpt-5.6-luna
$0.22 / $1.32
+10% vs headline
in
in.openai.gpt-5.6-luna
$0.22 / $1.32
+10% vs headline
us
us.openai.gpt-5.6-luna
$0.22 / $1.32
+10% vs headline
us-gov-west-1 · Mantle
openai.gpt-5.6-luna
$0.264 / $1.58
+32% vs headline
us-gov-east-1 · Mantle
openai.gpt-5.6-luna
$0.264 / $1.58
+32% vs headline
us-gov
us-gov.openai.gpt-5.6-luna
$0.264 / $1.58
+32% vs headline
Azure OpenAI
2026-07-09
gpt-5.6-luna-2026-07-09
$0.20 / $1.20
Retires 11 Jan 2028
us
gpt-5.6-luna
$0.22 / $1.32
+10% vs headline
Retires 11 Jan 2028
eu
gpt-5.6-luna
$0.22 / $1.32
+10% vs headline
Retires 11 Jan 2028
us-gov
gpt-5.6-luna
$0.275 / $1.65
+38% vs headline

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
nonexhigh
Features
Parallel 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

  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    56% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    42% less

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    56% less

Open-weight picks

  • MiMo V2.6 Pro
    Xiaomi · on GMI Cloud
    $0.348 / $0.696
    Has every key capability
    3% less
  • Muse Glimmer 30B
    Meta · on EmpirioLabs AI
    $0.20 / $0.80
    Has every key capability
    22% less
  • Deepseekv4.1 Flash
    DeepSeek · on Sarvam
    $0.149 / $0.585
    Has every key capability
    43% less
  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    44% less

Model line

Newer and older versions, at each lab's own price.

  1. Sep 2026GPT-6 LunaLatest$0.10 / $0.50
  2. Jul 2026GPT-5.6 LunaThis page$0.20 / $1.20

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-5.6-luna", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-5.6 Luna cost?

On OpenAI, GPT-5.6 Luna costs $0.20 per million input tokens and $1.20 per million output tokens. Cached input costs $0.02 per million tokens.

Which APIs offer GPT-5.6 Luna?

GPT-5.6 Luna runs on 11 APIs: OpenAI, Databricks, Amazon Bedrock, Azure OpenAI, OpenCode Go, ZeroGPU, AIHubMix, Perplexity, Kyma API and 2 more.

What is GPT-5.6 Luna's context window?

922K tokens, with up to 128K tokens in one reply.

Is GPT-5.6 Luna being retired?

Azure OpenAI (except US government regions) retires it on 11 Jan 2028. 11 hosts keep serving it.

Is there a newer version of GPT-5.6 Luna?

Yes. GPT-6 Luna is the newest model in this line, released on 22 Sep 2026.

What are cheaper alternatives to GPT-5.6 Luna?

Models that cost less and keep most of what it can do: GPT-6 Luna on OpenAI (56% less), Claude Haiku 5.5 on Anthropic (56% less) and MiMo V2.6 Pro on GMI Cloud (3% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-5.6 Luna released?

OpenAI released it on 9 Jul 2026.

What is GPT-5.6 Luna's API model id?

Use gpt-5.6-luna with OpenAI. Other hosts use their own ids: databricks-gpt-5-6-luna on Databricks, global.openai.gpt-5.6-luna on Amazon Bedrock.

Sources

Raw catalog entry for gpt-5.6-luna on OpenAI
{
  "cache_creation_input_token_cost": 2.5e-7,
  "cache_creation_input_token_cost_above_12hr": 5e-7,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens": 0.000001,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens_batches": 5e-7,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex": 5e-7,
  "cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority": 0.000002,
  "cache_creation_input_token_cost_above_12hr_batches": 2.5e-7,
  "cache_creation_input_token_cost_above_12hr_flex": 2.5e-7,
  "cache_creation_input_token_cost_above_12hr_priority": 0.000001,
  "cache_creation_input_token_cost_above_272k_tokens": 5e-7,
  "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-7,
  "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000001,
  "cache_creation_input_token_cost_flex": 1.25e-7,
  "cache_creation_input_token_cost_priority": 5e-7,
  "cache_read_input_token_cost": 2e-8,
  "cache_read_input_token_cost_above_272k_tokens": 4e-8,
  "cache_read_input_token_cost_above_272k_tokens_flex": 2e-8,
  "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8,
  "cache_read_input_token_cost_batches": 1e-8,
  "cache_read_input_token_cost_above_272k_tokens_batches": 2e-8,
  "cache_creation_input_token_cost_batches": 1.25e-7,
  "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-7,
  "cache_read_input_token_cost_flex": 1e-8,
  "cache_read_input_token_cost_priority": 4e-8,
  "input_cost_per_token": 2e-7,
  "input_cost_per_token_above_272k_tokens": 4e-7,
  "input_cost_per_token_above_272k_tokens_flex": 2e-7,
  "input_cost_per_token_above_272k_tokens_priority": 8e-7,
  "input_cost_per_token_batches": 1e-7,
  "input_cost_per_token_above_272k_tokens_batches": 2e-7,
  "input_cost_per_token_flex": 1e-7,
  "input_cost_per_token_priority": 4e-7,
  "litellm_provider": "openai",
  "max_input_tokens": 922000,
  "max_output_tokens": 128000,
  "mode": "chat",
  "output_cost_per_token": 0.0000012,
  "output_cost_per_token_above_272k_tokens": 0.0000018,
  "output_cost_per_token_above_272k_tokens_flex": 9e-7,
  "output_cost_per_token_above_272k_tokens_priority": 0.0000036,
  "output_cost_per_token_batches": 6e-7,
  "output_cost_per_token_above_272k_tokens_batches": 9e-7,
  "output_cost_per_token_flex": 6e-7,
  "output_cost_per_token_priority": 0.0000024,
  "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"
  ],
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_function_calling": 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
}