Skip to content
Model infoModelsSnapshot: 15 Oct 2026

OpenAI / GPT-5.6

GPT-5.6 Luna

OpenAI text generation, reasoning, agents model with developer-documented API access and version information.

Language models (LLMs)
availableClosed weightsText generationReasoningAgentsVision
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
16 of 20 specification fields collected
Input token limit922K922,000 tokens
Maximum output128K128,000 tokens
Input / 1M tokens$0.20OpenAI API
Output / 1M tokens$1.20USD · observed 12 Oct 2026

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
1,050,000 tokensSource for Context / input limit (opens in a new tab)
Maximum output
128,000 tokensSource for Maximum output (opens in a new tab)
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
SupportedSource for Reasoning (opens in a new tab)
Tool calling
SupportedSource for Tool calling (opens in a new tab)
Structured output
SupportedSource for Structured output (opens in a new tab)
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
SupportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)
Knowledge cutoff
2026-02-15Source for Knowledge cutoff (opens in a new tab)
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Maximum input tokens
922,000 tokensSource for Maximum input tokens (opens in a new tab)
Supported API routes
v1/chat/completions, v1/responses, v1/batchSource for Supported API routes (opens in a new tab)
Snapshots and aliases
gpt-5.6-lunaSource for Snapshots and aliases (opens in a new tab)

Aliases and pinned IDs listed by the developer. A snapshot date is not automatically the public release date.

Supported tools
web_search, file_search, image_generation, code_interpreter, hosted_shell, apply_patch, skills, computer_use, mcp, tool_searchSource for Supported tools (opens in a new tab)
Context caching
SupportedSource for Context caching (opens in a new tab)

Documented on at least one recorded endpoint. See Caching for host, lifecycle and billing restrictions.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

OpenAI API

Provider source (opens in a new tab)
API model ID
gpt-5.6-luna
Access
API account required. Model-specific permissions and rate limits apply.
Regions
Not collected
INPUT / 1M TOKENS$0.20
OUTPUT / 1M TOKENS$1.20

Standard text-token rates. Other modalities, tool usage and processing modes are billed separately. Long-context pricing applies to the full request; cached-rate treatment is shown only where explicit. Cached input price: $0.02 / 1M tokens (base tier).

Pricing by prompt length, USD / 1M tokens
Input lengthInputOutputCached input
Up to 272K input tokens$0.20$1.20$0.02
Above 272K input tokens$0.40$1.80Not collected
USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text tokensInput1$0.201M tokens
Text tokensCached input1$0.021M tokens
Text tokensOutput1$1.201M tokens

Rate conditions

  1. Base published rate. Check the model-card pricing conditions and the request modality.
Pricing source (opens in a new tab)

Data & enterprise terms

API data controls and retention depend on endpoint and account configuration; consult the linked provider policy.

Read the service policy (opens in a new tab)

Perplexity Agent API · default

Provider source (opens in a new tab)
API model ID
openai/gpt-5.6-luna
Access
Perplexity API key; POST https://api.perplexity.ai/v1/agent (compatibility alias: /v1/responses). Set service_tier=default. auto or an omitted tier also selects default processing.
Regions
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Context caching
SupportedSource for Context caching (opens in a new tab)
Service tier
defaultSource for Service tier (opens in a new tab)
INPUT / 1M TOKENS$0.20
OUTPUT / 1M TOKENS$1.20

Perplexity Agent API default processing; USD per million tokens. Long-context rates apply by prompt length; the higher tier starts above 272,000 tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero. Cached input price: $0.02 / 1M tokens (base tier).

Pricing by prompt length, USD / 1M tokens
Input lengthInputOutputCached input
Up to 272,000 prompt tokens$0.20$1.20$0.02
Above 272,000 prompt tokens$0.40$1.80$0.04
USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Tool add-onWeb search1$0.0025invocation
Tool add-onFast search2$0.001invocation
Tool add-onImage search3$0.0025successful invocation
Tool add-onURL fetch4$0.0005invocation
Tool add-onPeople search5$0.005invocation
Tool add-onFinance search6$0.005invocation
Tool add-onCode sandbox7$0.03container session
Tool add-onSearch inside sandbox8$0.0025SDK search request

Rate conditions

  1. Standard web search. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  2. web_search with search_type=fast. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  3. Image search bills successful invocations. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  4. Fetch and extract URL content. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  5. People search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  6. Financial search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  7. Up to 20 minutes of active use per billing window; this is not a runtime cap. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  8. Additional SDK search calls made inside a sandbox. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Perplexity Agent API · flex

Provider source (opens in a new tab)
API model ID
openai/gpt-5.6-luna
Access
Perplexity API key; POST https://api.perplexity.ai/v1/agent (compatibility alias: /v1/responses). Set service_tier=flex. Confirm the served tier in response.service_tier; unsupported tiers fall back to default.
Regions
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Context caching
SupportedSource for Context caching (opens in a new tab)
Service tier
flexSource for Service tier (opens in a new tab)
INPUT / 1M TOKENS$0.10
OUTPUT / 1M TOKENS$0.60

Perplexity Agent API flex processing; USD per million tokens. 0.5× listed token rates; fast is an alias for priority. Long-context rates apply by prompt length; the higher tier starts above 272,000 tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero. Cached input price: $0.01 / 1M tokens (base tier).

Pricing by prompt length, USD / 1M tokens
Input lengthInputOutputCached input
Up to 272,000 prompt tokens$0.10$0.60$0.01
Above 272,000 prompt tokens$0.20$0.90$0.02
USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Tool add-onWeb search1$0.0025invocation
Tool add-onFast search2$0.001invocation
Tool add-onImage search3$0.0025successful invocation
Tool add-onURL fetch4$0.0005invocation
Tool add-onPeople search5$0.005invocation
Tool add-onFinance search6$0.005invocation
Tool add-onCode sandbox7$0.03container session
Tool add-onSearch inside sandbox8$0.0025SDK search request

Rate conditions

  1. Standard web search. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  2. web_search with search_type=fast. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  3. Image search bills successful invocations. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  4. Fetch and extract URL content. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  5. People search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  6. Financial search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  7. Up to 20 minutes of active use per billing window; this is not a runtime cap. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  8. Additional SDK search calls made inside a sandbox. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Perplexity Agent API · priority

Provider source (opens in a new tab)
API model ID
openai/gpt-5.6-luna
Access
Perplexity API key; POST https://api.perplexity.ai/v1/agent (compatibility alias: /v1/responses). Set service_tier=priority. Confirm the served tier in response.service_tier; unsupported tiers fall back to default.
Regions
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Context caching
SupportedSource for Context caching (opens in a new tab)
Service tier
prioritySource for Service tier (opens in a new tab)
INPUT / 1M TOKENS$0.40
OUTPUT / 1M TOKENS$2.40

Perplexity Agent API priority processing; USD per million tokens. 2× listed token rates; fast is an alias for priority. Long-context rates apply by prompt length; the higher tier starts above 272,000 tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero. Cached input price: $0.04 / 1M tokens (base tier).

Pricing by prompt length, USD / 1M tokens
Input lengthInputOutputCached input
Up to 272,000 prompt tokens$0.40$2.40$0.04
Above 272,000 prompt tokens$0.80$3.60$0.08
USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Tool add-onWeb search1$0.0025invocation
Tool add-onFast search2$0.001invocation
Tool add-onImage search3$0.0025successful invocation
Tool add-onURL fetch4$0.0005invocation
Tool add-onPeople search5$0.005invocation
Tool add-onFinance search6$0.005invocation
Tool add-onCode sandbox7$0.03container session
Tool add-onSearch inside sandbox8$0.0025SDK search request

Rate conditions

  1. Standard web search. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  2. web_search with search_type=fast. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  3. Image search bills successful invocations. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  4. Fetch and extract URL content. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  5. People search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  6. Financial search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  7. Up to 20 minutes of active use per billing window; this is not a runtime cap. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  8. Additional SDK search calls made inside a sandbox. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

OpenAI API

gpt-5.6-luna
Documented
Support evidence (opens in a new tab)
How it works
Automatic prefix reuse + explicit breakpointsSource for How it works (opens in a new tab)
Minimum reusable input
1,024 visible input tokensSource for Minimum reusable input (opens in a new tab)
Lifetime & refresh
Minimum 30 minutes since the latest write or reuse; longer retention is possible.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Use prompt_cache_options.mode and prompt_cache_breakpoint for explicit control. ttl defaults to 30m. Up to four writes per request; implicit mode consumes one slot.Source for How to enable it (opens in a new tab)
Usage fields
Inspect cached_tokens and cache_write_tokens in API usage.Source for Usage fields (opens in a new tab)
Billing rules
Cache writes use 1.25× the uncached input rate instead of the normal input rate. Reads use the published model-specific cached rate. Output is still billed.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Exact rendered-prefix matching. No sharing across organizations or processing regions. Routing and load can prevent hits. Check account retention policy before selecting persistent caching.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Up to 272K input tokens$0.02 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Standard text-token rates. Other modalities, tool usage and processing modes are billed separately. Long-context pricing applies to the full request; cached-rate treatment is shown only where explicit.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Perplexity Agent API · default

openai/gpt-5.6-luna
Documented
Support evidence (opens in a new tab)
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected

Do not inherit the model developer’s direct-API retention policy onto the Perplexity endpoint.

How to enable it
Not collected
Usage fields
Not collected
Billing rules
Published discounted cache-read rates apply to this default service tier. Write charges, minimum cacheable input, retention and cache controls have not been verified for this host.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Up to 272,000 prompt tokens$0.02 / 1M tokensPricing evidence (opens in a new tab)
Cache read1Text tokens · Above 272,000 prompt tokens$0.04 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Perplexity Agent API default processing; USD per million tokens. Long-context rates apply by prompt length; the higher tier starts above 272,000 tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Perplexity Agent API · flex

openai/gpt-5.6-luna
Documented
Support evidence (opens in a new tab)
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected

Do not inherit the model developer’s direct-API retention policy onto the Perplexity endpoint.

How to enable it
Not collected
Usage fields
Not collected
Billing rules
Published discounted cache-read rates apply to this flex service tier. Write charges, minimum cacheable input, retention and cache controls have not been verified for this host.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Up to 272,000 prompt tokens$0.01 / 1M tokensPricing evidence (opens in a new tab)
Cache read1Text tokens · Above 272,000 prompt tokens$0.02 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Perplexity Agent API flex processing; USD per million tokens. 0.5× listed token rates; fast is an alias for priority. Long-context rates apply by prompt length; the higher tier starts above 272,000 tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Perplexity Agent API · priority

openai/gpt-5.6-luna
Documented
Support evidence (opens in a new tab)
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected

Do not inherit the model developer’s direct-API retention policy onto the Perplexity endpoint.

How to enable it
Not collected
Usage fields
Not collected
Billing rules
Published discounted cache-read rates apply to this priority service tier. Write charges, minimum cacheable input, retention and cache controls have not been verified for this host.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Up to 272,000 prompt tokens$0.04 / 1M tokensPricing evidence (opens in a new tab)
Cache read1Text tokens · Above 272,000 prompt tokens$0.08 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Perplexity Agent API priority processing; USD per million tokens. 2× listed token rates; fast is an alias for priority. Long-context rates apply by prompt length; the higher tier starts above 272,000 tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Proprietary OpenAI release in the official hosted-model catalog. Explicit open-weight releases and unresolved routing aliases are excluded.

Classification evidence (opens in a new tab)

Sources reviewed