impulse

GPT-5.6 Luna Pro

Frontier lab

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.

API id gpt-5.6-luna-proReleased 9 Jul 2026 (Jul 2026)
Input / 1M
$0.27
at Kyma API
Output / 1M
$1.62
at Kyma API
Context window
1.1M
tokens
Max output
128K
tokens per reply
Hosts
1
1 listings
Released
Jul 2026
9 Jul 2026

Pricing

List prices at Kyma API, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.27$1.62
Cached input
90% off input
$0.027

What it costs a month

At Kyma API list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$181
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$130
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$217
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,038
Use your own numbers

Where to run it

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

HostIn / out per 1M
gpt-5.6-luna-pro
$0.27 / $1.62

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
TextImagesPDFs
Produces
Text
Features
PDF inputPrompt caching

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 Kyma API.

Smaller OpenAI models

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    24% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    67% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    57% less

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    67% less

Open-weight picks

  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    14% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    21% less
  • MiMo V2.6 Pro
    Xiaomi · on GMI Cloud
    $0.348 / $0.696
    Has every key capability
    28% less
  • Muse Glimmer 30B
    Meta · on EmpirioLabs AI
    $0.20 / $0.80
    Has every key capability
    42% less

Call it

Using Kyma API's API.

Python
from litellm import completion

response = completion(
    model="kyma/gpt-5.6-luna-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does GPT-5.6 Luna Pro cost?

On Kyma API, GPT-5.6 Luna Pro costs $0.27 per million input tokens and $1.62 per million output tokens. Cached input costs $0.027 per million tokens.

Which APIs offer GPT-5.6 Luna Pro?

GPT-5.6 Luna Pro runs on 1 API: Kyma API.

What is GPT-5.6 Luna Pro's context window?

1.1M tokens, with up to 128K tokens in one reply.

Is GPT-5.6 Luna Pro being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to GPT-5.6 Luna Pro?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (24% less), Claude Haiku 5.5 on Anthropic (67% less) and DeepSeek Flash on DeepSeek (14% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-5.6 Luna Pro released?

OpenAI released it on 9 Jul 2026.

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

Use gpt-5.6-luna-pro with Kyma API.

Sources

Raw catalog entry for gpt-5.6-luna-pro on Kyma API
{
  "max_input_tokens": 1050000,
  "max_output_tokens": 128000,
  "input_cost_per_token": 2.703e-7,
  "cache_read_input_token_cost": 2.7e-8,
  "output_cost_per_token": 0.000001621,
  "litellm_provider": "kyma",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_vision": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_pdf_input": true
}