GPT-5.6 Luna Pro model profile
Evidence snapshot:
GPT-5.6 Luna Pro is a OpenAI model profile with a 1,050,000-token context window. The dated catalog snapshot records file, image, text modalities and interfaces for file input, prompt caching, reasoning controls, structured output, text generation.
GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Learn more in OpenAI's docs:
GPT-5.6 Luna Pro is a reference profile: OpenAI publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
GPT-5.6 Luna Pro is an independent knowledge profile. It does not claim that Kendr hosts the model, quote a Kendr customer price, promise API availability, or advertise a Kendr routing receipt.
GPT-5.6 Luna Pro accepts file, image, and text and returns text. The snapshot records file input, prompt caching, reasoning controls, structured output, text generation, tool calling, vision, and web search pricing as capabilities or interfaces.
The dated reference snapshot lists $0.1 input and $0.6 output per million tokens. Cached input is $0.01 per million tokens.
The 2026-09-06 snapshot includes AutoExacto results for 4 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
GPT-5.6 Luna Pro ranked #40 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.
Profile facts
- Profile type
- Model research profile
- Provider or publisher
- OpenAI
- Context window
- 1,050,000 tokens
- Snapshot date
- 2026-09-06
- Knowledge cutoff
- 2026-02-16
- Reference catalog ID
- openai/gpt-5.6-luna-pro
When to pick GPT-5.6 Luna Pro
GPT-5.6 Luna Pro is a reference profile: OpenAI publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call.
Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.
- Reach for it when a whole corpus has to fit in one prompt. The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked.
- Reach for it when the input includes images. The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described.
- Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.
- Reach for it when you want to trade depth against cost per call. Reasoning effort is selectable across max, xhigh, high, medium, low, none, so one route can serve both cheap and deep work.
- Look elsewhere when you need to call it through Kendr today. This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
Context, modalities, and identity
GPT-5.6 Luna Pro accepts file, image, and text and returns text. The snapshot records file input, prompt caching, reasoning controls, structured output, text generation, tool calling, vision, and web search pricing as capabilities or interfaces.
- Provider or publisher
- OpenAI
- Context window
- 1,050,000 tokens
- Maximum output
- 128,000 tokens
- Input modalities
- file, image, and text
- Output modalities
- text
- Knowledge cutoff
- 2026-02-16
Model overview
GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Learn more in OpenAI's docs:
- Reference model ID
- openai/gpt-5.6-luna-pro
- Canonical version
- openai/gpt-5.6-luna-pro-20260709
- Hugging Face ID
- Not separately documented
Capabilities and supported controls
Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.
- Supported parameters
- include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools
- file input
- prompt caching
- reasoning controls
- structured output
- text generation
- tool calling
- vision
- web search pricing
Dated pricing snapshot
The dated reference snapshot lists $0.1 input and $0.6 output per million tokens. Cached input is $0.01 per million tokens.
These are dated third-party reference prices, not Kendr prices or an availability offer. Routes, tiers, caching, region, and provider policy can change the landed price.
- Price date
- 2026-09-06
- Input
- $0.1 per 1M tokens
- Cached input
- $0.01 per 1M tokens
- Output
- $0.6 per 1M tokens
| Prompt threshold | Input | Cached input | Output |
|---|---|---|---|
| From 272,000 prompt tokens | $0.4 / 1M | $0.04 / 1M | $1.8 / 1M |
Provider routes, performance, and uptime
The snapshot retains 5 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.
- Active provider endpoints
- 5
- Best p50 latency
- 6.09 s
- Best p50 throughput
- 234 tok/s
- Availability with routing
- 99.98% over the sampled window
- Availability without routing
- 98.89% over the sampled window
- Performance date
- 2026-09-06
| Provider | Quantization | Input / 1M | Output / 1M | Cache read / 1M | Context | p50 latency | p50 throughput | Uptime (1d) |
|---|---|---|---|---|---|---|---|---|
| OpenAI Flex | unknown | $0.1 / 1M | $0.6 / 1M | $0.01 / 1M | 1,050,000 tokens | 52.76 s | 90 tok/s | 100.00% |
| Azure | unknown | $0.2 / 1M | $1.2 / 1M | $0.02 / 1M | 1,050,000 tokens | 16.32 s | 148 tok/s | 95.57% |
| OpenAI | unknown | $0.2 / 1M | $1.2 / 1M | $0.02 / 1M | 1,050,000 tokens | 10.51 s | 112 tok/s | 99.99% |
| Azure (EU) | unknown | $0.22 / 1M | $1.32 / 1M | $0.022 / 1M | 1,050,000 tokens | 11.63 s | 164.5 tok/s | 100.00% |
| OpenAI Fast | unknown | $0.4 / 1M | $2.4 / 1M | $0.04 / 1M | 1,050,000 tokens | 6.09 s | 234 tok/s | 100.00% |
Benchmark evidence and limitations
The 2026-09-06 snapshot includes AutoExacto results for 4 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable.
Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
- AutoExacto coverage
- 4 provider observations over 32 days
AutoExacto provider benchmarks
Rolling provider observations from the cited third-party benchmark view. The lookback is 32 days; GPQA Diamond and TAU-Bench Airline measure different abilities and should not be blended into one score.
| Provider | GPQA Diamond | TAU-Bench Airline | Runs |
|---|---|---|---|
| auto-routing | 89.9% | 70% | 1 |
| Azure | 90.74% | 66.67% | 1 |
| Azure (EU) | 91.41% | 70.67% | 1 |
| OpenAI | 90.4% | 68.67% | 1 |
Popularity and market context
GPT-5.6 Luna Pro ranked #40 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.
- Third-party catalog rank
- #40
- Global market share
- Not inferred
- Observation date
- 2026-09-06
Frequently asked questions
When should I use GPT-5.6 Luna Pro?
GPT-5.6 Luna Pro is a reference profile: OpenAI publishes it, Kendr documents it for comparison, and it carries no Kendr alias to call. Reach for it when a whole corpus has to fit in one prompt: The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked. Reach for it when the input includes images: The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose. Reach for it when you want to trade depth against cost per call: Reasoning effort is selectable across max, xhigh, high, medium, low, none, so one route can serve both cheap and deep work. Look elsewhere when you need to call it through Kendr today: This is a research reference profile with no Kendr alias. The facts and evidence here are published for comparison; the model is not routable on Kendr.
What is GPT-5.6 Luna Pro?
GPT-5.6 Luna Pro is a OpenAI model profile with a 1,050,000-token context window. The dated catalog snapshot records file, image, text modalities and interfaces for file input, prompt caching, reasoning controls, structured output, text generation.
What context window does GPT-5.6 Luna Pro have?
The dated profile lists 1,050,000 tokens of context and up to 128,000 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.
What benchmark evidence is available for GPT-5.6 Luna Pro?
The 2026-09-06 snapshot includes AutoExacto results for 4 provider observations. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.
Is GPT-5.6 Luna Pro available through Kendr?
This is an independent knowledge profile, not a Kendr-hosted availability claim. Check Kendr's live public model API for currently enabled Kendr aliases.
Does the popularity rank represent GPT-5.6 Luna Pro's global market share?
GPT-5.6 Luna Pro ranked #40 in the cited trailing-7-day third-party catalog usage dataset as of 2026-09-06. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share. No global market-share percentage is inferred when the source does not publish one.
Sources and evidence dates
- GPT-5.6 Luna Pro third-party catalog record (catalog, checked 2026-09-06)
- Third-party model catalog methodology (methodology, checked 2026-09-06)
- OpenAI official model documentation (primary, checked 2026-09-06)
- GPT-5.6 Luna Pro third-party catalog record (benchmark, checked 2026-09-06)