Documentation 2026-08-27 22:01 UTC to 2026-08-28 18:00 UTC

401)401)

402puts(first.output_text)402puts(first.output_text)

403 403 

404history.concat(first.output.map(&:to_h))404history.concat(first.output)

405history << {role: :user, content: "Tell me another."}405history << {role: :user, content: "Tell me another."}

406 406 

407second = client.responses.create(407second = client.responses.create(

32 32 

33Choose a [GPT-5.6 model](https://developers.openai.com/api/docs/guides/latest-model) for the workload instead33Choose a [GPT-5.6 model](https://developers.openai.com/api/docs/guides/latest-model) for the workload instead

34of routing every request to the most capable tier. Use `gpt-5.6` or34of routing every request to the most capable tier. Use `gpt-5.6` or

35`gpt-5.6-sol` for frontier capability, `gpt-5.6-terra` for strong performance35`gpt-5.6-sol` for flagship capability, `gpt-5.6-terra` for strong performance

36at a lower price, and `gpt-5.6-luna` for efficient, high-volume workloads.36at a lower price, and `gpt-5.6-luna` for efficient, high-volume workloads.

37 37 

38When migrating, preserve the current model's workload role and effective38When migrating, preserve the current model's workload role and effective

1018 model: "gpt-5.6",1018 model: "gpt-5.6",

1019 input: long_window1019 input: long_window

1020)1020)

1021input = compacted.output.map(&:to_h)1021input = compacted.output.dup

1022input << {1022input << {

1023 role: :user,1023 role: :user,

1024 content: "We found the bad cache invalidation path. Write the fix plan and the verification checklist."1024 content: "We found the bad cache invalidation path. Write the fix plan and the verification checklist."

1443 include: ["reasoning.encrypted_content"],1443 include: ["reasoning.encrypted_content"],

1444 input: history1444 input: history

1445)1445)

1446history.concat(first.output.map(&:to_h))1446history.concat(first.output)

1447history << {1447history << {

1448 role: :user,1448 role: :user,

1449 content: "Now write the customer-facing explanation in plain English."1449 content: "Now write the customer-facing explanation in plain English."

25- **Persisted reasoning:** GPT-5.6 can reuse available reasoning items across turns to improve multi-turn quality and cache efficiency. Use `reasoning.context` to select the behavior. Learn how to [preserve reasoning across calls](https://developers.openai.com/api/docs/guides/reasoning#preserve-reasoning-across-calls).25- **Persisted reasoning:** GPT-5.6 can reuse available reasoning items across turns to improve multi-turn quality and cache efficiency. Use `reasoning.context` to select the behavior. Learn how to [preserve reasoning across calls](https://developers.openai.com/api/docs/guides/reasoning#preserve-reasoning-across-calls).

26- **Max reasoning effort:** GPT-5.6 supports `max` reasoning effort for demanding tasks that need more exploration and verification. If you currently use `xhigh`, compare both settings on representative workloads.26- **Max reasoning effort:** GPT-5.6 supports `max` reasoning effort for demanding tasks that need more exploration and verification. If you currently use `xhigh`, compare both settings on representative workloads.

27- **Pro mode:** GPT-5.6 can perform more model work to improve reliability on difficult tasks and return a single final answer. Enable it with `reasoning.mode: "pro"` when quality matters more than latency and token usage. Learn how to [use pro mode](https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode).27- **Pro mode:** GPT-5.6 can perform more model work to improve reliability on difficult tasks and return a single final answer. Enable it with `reasoning.mode: "pro"` when quality matters more than latency and token usage. Learn how to [use pro mode](https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode).

28- **Token efficiency:** GPT-5.6 reaches frontier performance with fewer output tokens.28- **Token efficiency:** GPT-5.6 reaches flagship-level performance with fewer output tokens.

29- **Frontend design:** GPT-5.6 creates more polished and usable websites and applications, with stronger layout, visual hierarchy, and design judgment.29- **Frontend design:** GPT-5.6 creates more polished and usable websites and applications, with stronger layout, visual hierarchy, and design judgment.

30- **Intent understanding:** GPT-5.6 can better infer the user's underlying goal and intended level of work from context, so you often do not need to prescribe every step. Continue to provide domain context, hard constraints, approval boundaries, and success criteria. Tell the model when an important ambiguity should trigger a question.30- **Intent understanding:** GPT-5.6 can better infer the user's underlying goal and intended level of work from context, so you often do not need to prescribe every step. Continue to provide domain context, hard constraints, approval boundaries, and success criteria. Tell the model when an important ambiguity should trigger a question.

31- **Original image detail:** GPT-5.6 preserves the original dimensions of images sent with `original` or `auto` detail instead of resizing them to a patch budget or pixel-dimension limit. Large images can use more input tokens and increase latency. Learn how to [choose an image detail level](https://developers.openai.com/api/docs/guides/images-vision#choose-an-image-detail-level).31- **Original image detail:** GPT-5.6 preserves the original dimensions of images sent with `original` or `auto` detail instead of resizing them to a patch budget or pixel-dimension limit. Large images can use more input tokens and increase latency. Learn how to [choose an image detail level](https://developers.openai.com/api/docs/guides/images-vision#choose-an-image-detail-level).

56 56 

57### Update API and model parameters57### Update API and model parameters

58 58 

59- Choose the target model for the workload. Use `gpt-5.6-sol` for frontier capability, `gpt-5.6-terra` for a balance of intelligence and cost, or `gpt-5.6-luna` for efficient, high-volume workloads. The `gpt-5.6` alias routes requests to `gpt-5.6-sol`.59- Choose the target model for the workload. Use `gpt-5.6-sol` for flagship capability, `gpt-5.6-terra` for a balance of intelligence and cost, or `gpt-5.6-luna` for efficient, high-volume workloads. The `gpt-5.6` alias routes requests to `gpt-5.6-sol`.

60- Use the [Responses API](https://developers.openai.com/api/docs/guides/migrate-to-responses) for reasoning, tool-calling, and multi-turn workflows.60- Use the [Responses API](https://developers.openai.com/api/docs/guides/migrate-to-responses) for reasoning, tool-calling, and multi-turn workflows.

61- Set `reasoning.effort` intentionally. GPT-5.6 supports `none`, `low`, `medium`, `high`, `xhigh`, and `max`.61- Set `reasoning.effort` intentionally. GPT-5.6 supports `none`, `low`, `medium`, `high`, `xhigh`, and `max`.

62 - If you are migrating from GPT-5.5 or GPT-5.4, preserve your current reasoning effort as the baseline, then compare one level lower.62 - If you are migrating from GPT-5.5 or GPT-5.4, preserve your current reasoning effort as the baseline, then compare one level lower.

817 model: "gpt-5.2",817 model: "gpt-5.2",

818 input: [818 input: [

819 {role: :user, content: "Write a very long poem about a dog."},819 {role: :user, content: "Write a very long poem about a dog."},

820 *response.output.map(&:to_h)820 *response.output

821 ]821 ]

822)822)

823 823 

25- **Persisted reasoning:** GPT-5.6 can reuse available reasoning items across turns to improve multi-turn quality and cache efficiency. Use `reasoning.context` to select the behavior. Learn how to [preserve reasoning across calls](https://developers.openai.com/api/docs/guides/reasoning#preserve-reasoning-across-calls).25- **Persisted reasoning:** GPT-5.6 can reuse available reasoning items across turns to improve multi-turn quality and cache efficiency. Use `reasoning.context` to select the behavior. Learn how to [preserve reasoning across calls](https://developers.openai.com/api/docs/guides/reasoning#preserve-reasoning-across-calls).

26- **Max reasoning effort:** GPT-5.6 supports `max` reasoning effort for demanding tasks that need more exploration and verification. If you currently use `xhigh`, compare both settings on representative workloads.26- **Max reasoning effort:** GPT-5.6 supports `max` reasoning effort for demanding tasks that need more exploration and verification. If you currently use `xhigh`, compare both settings on representative workloads.

27- **Pro mode:** GPT-5.6 can perform more model work to improve reliability on difficult tasks and return a single final answer. Enable it with `reasoning.mode: "pro"` when quality matters more than latency and token usage. Learn how to [use pro mode](https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode).27- **Pro mode:** GPT-5.6 can perform more model work to improve reliability on difficult tasks and return a single final answer. Enable it with `reasoning.mode: "pro"` when quality matters more than latency and token usage. Learn how to [use pro mode](https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode).

28- **Token efficiency:** GPT-5.6 reaches frontier performance with fewer output tokens.28- **Token efficiency:** GPT-5.6 reaches flagship-level performance with fewer output tokens.

29- **Frontend design:** GPT-5.6 creates more polished and usable websites and applications, with stronger layout, visual hierarchy, and design judgment.29- **Frontend design:** GPT-5.6 creates more polished and usable websites and applications, with stronger layout, visual hierarchy, and design judgment.

30- **Intent understanding:** GPT-5.6 can better infer the user's underlying goal and intended level of work from context, so you often do not need to prescribe every step. Continue to provide domain context, hard constraints, approval boundaries, and success criteria. Tell the model when an important ambiguity should trigger a question.30- **Intent understanding:** GPT-5.6 can better infer the user's underlying goal and intended level of work from context, so you often do not need to prescribe every step. Continue to provide domain context, hard constraints, approval boundaries, and success criteria. Tell the model when an important ambiguity should trigger a question.

31- **Original image detail:** GPT-5.6 preserves the original dimensions of images sent with `original` or `auto` detail instead of resizing them to a patch budget or pixel-dimension limit. Large images can use more input tokens and increase latency. Learn how to [choose an image detail level](https://developers.openai.com/api/docs/guides/images-vision#choose-an-image-detail-level).31- **Original image detail:** GPT-5.6 preserves the original dimensions of images sent with `original` or `auto` detail instead of resizing them to a patch budget or pixel-dimension limit. Large images can use more input tokens and increase latency. Learn how to [choose an image detail level](https://developers.openai.com/api/docs/guides/images-vision#choose-an-image-detail-level).

56 56 

57### Update API and model parameters57### Update API and model parameters

58 58 

59- Choose the target model for the workload. Use `gpt-5.6-sol` for frontier capability, `gpt-5.6-terra` for a balance of intelligence and cost, or `gpt-5.6-luna` for efficient, high-volume workloads. The `gpt-5.6` alias routes requests to `gpt-5.6-sol`.59- Choose the target model for the workload. Use `gpt-5.6-sol` for flagship capability, `gpt-5.6-terra` for a balance of intelligence and cost, or `gpt-5.6-luna` for efficient, high-volume workloads. The `gpt-5.6` alias routes requests to `gpt-5.6-sol`.

60- Use the [Responses API](https://developers.openai.com/api/docs/guides/migrate-to-responses) for reasoning, tool-calling, and multi-turn workflows.60- Use the [Responses API](https://developers.openai.com/api/docs/guides/migrate-to-responses) for reasoning, tool-calling, and multi-turn workflows.

61- Set `reasoning.effort` intentionally. GPT-5.6 supports `none`, `low`, `medium`, `high`, `xhigh`, and `max`.61- Set `reasoning.effort` intentionally. GPT-5.6 supports `none`, `low`, `medium`, `high`, `xhigh`, and `max`.

62 - If you are migrating from GPT-5.5 or GPT-5.4, preserve your current reasoning effort as the baseline, then compare one level lower.62 - If you are migrating from GPT-5.5 or GPT-5.4, preserve your current reasoning effort as the baseline, then compare one level lower.

941 model: "gpt-5.6",941 model: "gpt-5.6",

942 input: context942 input: context

943)943)

944context.concat(first.output.map(&:to_h))944context.concat(first.output)

945context << {role: :user, content: "And its population?"}945context << {role: :user, content: "And its population?"}

946 946 

947second = client.responses.create(947second = client.responses.create(

918 input: history,918 input: history,

919 reasoning: {context: :current_turn}919 reasoning: {context: :current_turn}

920)920)

921history.concat(first.output.map(&:to_h))921history.concat(first.output)

922history << {role: :user, content: "Now patch the bug and explain the change."}922history << {role: :user, content: "Now patch the bug and explain the change."}

923 923 

924second = client.responses.create(924second = client.responses.create(

27- [codex-mini-latest](/api/docs/models/codex-mini-latest.md): Fast reasoning model optimized for the Codex CLI27- [codex-mini-latest](/api/docs/models/codex-mini-latest.md): Fast reasoning model optimized for the Codex CLI

28- [computer-use-preview](/api/docs/models/computer-use-preview.md): Specialized model for computer use tool28- [computer-use-preview](/api/docs/models/computer-use-preview.md): Specialized model for computer use tool

29- [davinci-002](/api/docs/models/davinci-002.md): Replacement for the GPT-3 curie and davinci base models29- [davinci-002](/api/docs/models/davinci-002.md): Replacement for the GPT-3 curie and davinci base models

30- [Daybreak Blue](/api/docs/models/daybreak-blue-latest.md): An alias for frontier general-purpose models with safeguards for defensive cybersecurity work.30- [Daybreak Blue](/api/docs/models/gpt-daybreak-blue-latest.md): An alias for flagship general-purpose models with safeguards for defensive cybersecurity work.

31- [Daybreak Red](/api/docs/models/daybreak-red-latest.md): An alias for advanced cybersecurity models for authorized vulnerability research and security testing.31- [Daybreak Red](/api/docs/models/gpt-daybreak-red-latest.md): An alias for advanced cybersecurity models for authorized vulnerability research and security testing.

32- [GPT-3.5 Turbo](/api/docs/models/gpt-3.5-turbo.md): Legacy GPT model for cheaper chat and non-chat tasks32- [GPT-3.5 Turbo](/api/docs/models/gpt-3.5-turbo.md): Legacy GPT model for cheaper chat and non-chat tasks

33- [GPT-4](/api/docs/models/gpt-4.md): An older high-intelligence GPT model33- [GPT-4](/api/docs/models/gpt-4.md): An older high-intelligence GPT model

34- [GPT-4 Turbo](/api/docs/models/gpt-4-turbo.md): An older high-intelligence GPT model34- [GPT-4 Turbo](/api/docs/models/gpt-4-turbo.md): An older high-intelligence GPT model

51- [GPT-4o Transcribe Diarize](/api/docs/models/gpt-4o-transcribe-diarize.md): Transcription model that identifies who's speaking when51- [GPT-4o Transcribe Diarize](/api/docs/models/gpt-4o-transcribe-diarize.md): Transcription model that identifies who's speaking when

52- [GPT-5](/api/docs/models/gpt-5.md): Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort52- [GPT-5](/api/docs/models/gpt-5.md): Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort

53- [GPT-5 Chat](/api/docs/models/gpt-5-chat-latest.md): GPT-5 model used in ChatGPT53- [GPT-5 Chat](/api/docs/models/gpt-5-chat-latest.md): GPT-5 model used in ChatGPT

54- [GPT-5 Mini](/api/docs/models/gpt-5-mini.md): Near-frontier intelligence for cost sensitive, low latency, high volume workloads54- [GPT-5 Mini](/api/docs/models/gpt-5-mini.md): Strong intelligence for cost sensitive, low latency, high volume workloads

55- [GPT-5 nano](/api/docs/models/gpt-5-nano.md): Fastest, most cost-efficient version of GPT-555- [GPT-5 nano](/api/docs/models/gpt-5-nano.md): Fastest, most cost-efficient version of GPT-5

56- [GPT-5 Pro](/api/docs/models/gpt-5-pro.md): Version of GPT-5 that produces smarter and more precise responses56- [GPT-5 Pro](/api/docs/models/gpt-5-pro.md): Version of GPT-5 that produces smarter and more precise responses

57- [GPT-5-Codex](/api/docs/models/gpt-5-codex.md): A version of GPT-5 optimized for agentic coding in Codex57- [GPT-5-Codex](/api/docs/models/gpt-5-codex.md): A version of GPT-5 optimized for agentic coding in Codex

60- [GPT-5.1-Codex](/api/docs/models/gpt-5.1-codex.md): A version of GPT-5.1 optimized for agentic coding in Codex.60- [GPT-5.1-Codex](/api/docs/models/gpt-5.1-codex.md): A version of GPT-5.1 optimized for agentic coding in Codex.

61- [GPT-5.1-Codex Mini](/api/docs/models/gpt-5.1-codex-mini.md): Smaller, more cost-effective, less-capable version of GPT-5.1-Codex61- [GPT-5.1-Codex Mini](/api/docs/models/gpt-5.1-codex-mini.md): Smaller, more cost-effective, less-capable version of GPT-5.1-Codex

62- [GPT-5.1-Codex-Max](/api/docs/models/gpt-5.1-codex-max.md): A version of GPT-5.1-codex optimized for long running tasks.62- [GPT-5.1-Codex-Max](/api/docs/models/gpt-5.1-codex-max.md): A version of GPT-5.1-codex optimized for long running tasks.

63- [GPT-5.2](/api/docs/models/gpt-5.2.md): Previous frontier model for professional work with configurable reasoning effort63- [GPT-5.2](/api/docs/models/gpt-5.2.md): Previous flagship model for professional work with configurable reasoning effort

64- [GPT-5.2 Chat](/api/docs/models/gpt-5.2-chat-latest.md): GPT-5.2 model used in ChatGPT64- [GPT-5.2 Chat](/api/docs/models/gpt-5.2-chat-latest.md): GPT-5.2 model used in ChatGPT

65- [GPT-5.2 Pro](/api/docs/models/gpt-5.2-pro.md): Previous pro model for professional work that produces smarter and more precise responses.65- [GPT-5.2 Pro](/api/docs/models/gpt-5.2-pro.md): Previous pro model for professional work that produces smarter and more precise responses.

66- [GPT-5.2-Codex](/api/docs/models/gpt-5.2-codex.md): Our most intelligent coding model optimized for long-horizon, agentic coding tasks.66- [GPT-5.2-Codex](/api/docs/models/gpt-5.2-codex.md): Our most intelligent coding model optimized for long-horizon, agentic coding tasks.

74- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.74- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.

75- [GPT-5.6 Cyber](/api/docs/models/gpt-5.6-cyber.md): Our most advanced cybersecurity model for authorized vulnerability research and security testing.75- [GPT-5.6 Cyber](/api/docs/models/gpt-5.6-cyber.md): Our most advanced cybersecurity model for authorized vulnerability research and security testing.

76- [GPT-5.6 Luna](/api/docs/models/gpt-5.6-luna.md): GPT-5.6 model optimized for cost-sensitive workloads76- [GPT-5.6 Luna](/api/docs/models/gpt-5.6-luna.md): GPT-5.6 model optimized for cost-sensitive workloads

77- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): Frontier model for complex professional work77- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): Flagship model for complex professional work

78- [GPT-5.6 Terra](/api/docs/models/gpt-5.6-terra.md): GPT-5.6 model that balances intelligence and cost78- [GPT-5.6 Terra](/api/docs/models/gpt-5.6-terra.md): GPT-5.6 model that balances intelligence and cost

79- [GPT-Audio](/api/docs/models/gpt-audio.md): For audio inputs and outputs with Chat Completions API79- [GPT-Audio](/api/docs/models/gpt-audio.md): For audio inputs and outputs with Chat Completions API

80- [GPT-Audio Mini](/api/docs/models/gpt-audio-mini.md): A cost-efficient version of GPT Audio80- [GPT-Audio Mini](/api/docs/models/gpt-audio-mini.md): A cost-efficient version of GPT Audio

27- [codex-mini-latest](/api/docs/models/codex-mini-latest.md): Fast reasoning model optimized for the Codex CLI27- [codex-mini-latest](/api/docs/models/codex-mini-latest.md): Fast reasoning model optimized for the Codex CLI

28- [computer-use-preview](/api/docs/models/computer-use-preview.md): Specialized model for computer use tool28- [computer-use-preview](/api/docs/models/computer-use-preview.md): Specialized model for computer use tool

29- [davinci-002](/api/docs/models/davinci-002.md): Replacement for the GPT-3 curie and davinci base models29- [davinci-002](/api/docs/models/davinci-002.md): Replacement for the GPT-3 curie and davinci base models

30- [Daybreak Blue](/api/docs/models/daybreak-blue-latest.md): An alias for frontier general-purpose models with safeguards for defensive cybersecurity work.30- [Daybreak Blue](/api/docs/models/gpt-daybreak-blue-latest.md): An alias for flagship general-purpose models with safeguards for defensive cybersecurity work.

31- [Daybreak Red](/api/docs/models/daybreak-red-latest.md): An alias for advanced cybersecurity models for authorized vulnerability research and security testing.31- [Daybreak Red](/api/docs/models/gpt-daybreak-red-latest.md): An alias for advanced cybersecurity models for authorized vulnerability research and security testing.

32- [GPT-3.5 Turbo](/api/docs/models/gpt-3.5-turbo.md): Legacy GPT model for cheaper chat and non-chat tasks32- [GPT-3.5 Turbo](/api/docs/models/gpt-3.5-turbo.md): Legacy GPT model for cheaper chat and non-chat tasks

33- [GPT-4](/api/docs/models/gpt-4.md): An older high-intelligence GPT model33- [GPT-4](/api/docs/models/gpt-4.md): An older high-intelligence GPT model

34- [GPT-4 Turbo](/api/docs/models/gpt-4-turbo.md): An older high-intelligence GPT model34- [GPT-4 Turbo](/api/docs/models/gpt-4-turbo.md): An older high-intelligence GPT model

51- [GPT-4o Transcribe Diarize](/api/docs/models/gpt-4o-transcribe-diarize.md): Transcription model that identifies who's speaking when51- [GPT-4o Transcribe Diarize](/api/docs/models/gpt-4o-transcribe-diarize.md): Transcription model that identifies who's speaking when

52- [GPT-5](/api/docs/models/gpt-5.md): Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort52- [GPT-5](/api/docs/models/gpt-5.md): Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort

53- [GPT-5 Chat](/api/docs/models/gpt-5-chat-latest.md): GPT-5 model used in ChatGPT53- [GPT-5 Chat](/api/docs/models/gpt-5-chat-latest.md): GPT-5 model used in ChatGPT

54- [GPT-5 Mini](/api/docs/models/gpt-5-mini.md): Near-frontier intelligence for cost sensitive, low latency, high volume workloads54- [GPT-5 Mini](/api/docs/models/gpt-5-mini.md): Strong intelligence for cost sensitive, low latency, high volume workloads

55- [GPT-5 nano](/api/docs/models/gpt-5-nano.md): Fastest, most cost-efficient version of GPT-555- [GPT-5 nano](/api/docs/models/gpt-5-nano.md): Fastest, most cost-efficient version of GPT-5

56- [GPT-5 Pro](/api/docs/models/gpt-5-pro.md): Version of GPT-5 that produces smarter and more precise responses56- [GPT-5 Pro](/api/docs/models/gpt-5-pro.md): Version of GPT-5 that produces smarter and more precise responses

57- [GPT-5-Codex](/api/docs/models/gpt-5-codex.md): A version of GPT-5 optimized for agentic coding in Codex57- [GPT-5-Codex](/api/docs/models/gpt-5-codex.md): A version of GPT-5 optimized for agentic coding in Codex

60- [GPT-5.1-Codex](/api/docs/models/gpt-5.1-codex.md): A version of GPT-5.1 optimized for agentic coding in Codex.60- [GPT-5.1-Codex](/api/docs/models/gpt-5.1-codex.md): A version of GPT-5.1 optimized for agentic coding in Codex.

61- [GPT-5.1-Codex Mini](/api/docs/models/gpt-5.1-codex-mini.md): Smaller, more cost-effective, less-capable version of GPT-5.1-Codex61- [GPT-5.1-Codex Mini](/api/docs/models/gpt-5.1-codex-mini.md): Smaller, more cost-effective, less-capable version of GPT-5.1-Codex

62- [GPT-5.1-Codex-Max](/api/docs/models/gpt-5.1-codex-max.md): A version of GPT-5.1-codex optimized for long running tasks.62- [GPT-5.1-Codex-Max](/api/docs/models/gpt-5.1-codex-max.md): A version of GPT-5.1-codex optimized for long running tasks.

63- [GPT-5.2](/api/docs/models/gpt-5.2.md): Previous frontier model for professional work with configurable reasoning effort63- [GPT-5.2](/api/docs/models/gpt-5.2.md): Previous flagship model for professional work with configurable reasoning effort

64- [GPT-5.2 Chat](/api/docs/models/gpt-5.2-chat-latest.md): GPT-5.2 model used in ChatGPT64- [GPT-5.2 Chat](/api/docs/models/gpt-5.2-chat-latest.md): GPT-5.2 model used in ChatGPT

65- [GPT-5.2 Pro](/api/docs/models/gpt-5.2-pro.md): Previous pro model for professional work that produces smarter and more precise responses.65- [GPT-5.2 Pro](/api/docs/models/gpt-5.2-pro.md): Previous pro model for professional work that produces smarter and more precise responses.

66- [GPT-5.2-Codex](/api/docs/models/gpt-5.2-codex.md): Our most intelligent coding model optimized for long-horizon, agentic coding tasks.66- [GPT-5.2-Codex](/api/docs/models/gpt-5.2-codex.md): Our most intelligent coding model optimized for long-horizon, agentic coding tasks.

74- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.74- [GPT-5.5 Pro](/api/docs/models/gpt-5.5-pro.md): Version of GPT-5.5 that produces smarter and more precise responses.

75- [GPT-5.6 Cyber](/api/docs/models/gpt-5.6-cyber.md): Our most advanced cybersecurity model for authorized vulnerability research and security testing.75- [GPT-5.6 Cyber](/api/docs/models/gpt-5.6-cyber.md): Our most advanced cybersecurity model for authorized vulnerability research and security testing.

76- [GPT-5.6 Luna](/api/docs/models/gpt-5.6-luna.md): GPT-5.6 model optimized for cost-sensitive workloads76- [GPT-5.6 Luna](/api/docs/models/gpt-5.6-luna.md): GPT-5.6 model optimized for cost-sensitive workloads

77- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): Frontier model for complex professional work77- [GPT-5.6 Sol](/api/docs/models/gpt-5.6-sol.md): Flagship model for complex professional work

78- [GPT-5.6 Terra](/api/docs/models/gpt-5.6-terra.md): GPT-5.6 model that balances intelligence and cost78- [GPT-5.6 Terra](/api/docs/models/gpt-5.6-terra.md): GPT-5.6 model that balances intelligence and cost

79- [GPT-Audio](/api/docs/models/gpt-audio.md): For audio inputs and outputs with Chat Completions API79- [GPT-Audio](/api/docs/models/gpt-audio.md): For audio inputs and outputs with Chat Completions API

80- [GPT-Audio Mini](/api/docs/models/gpt-audio-mini.md): A cost-efficient version of GPT Audio80- [GPT-Audio Mini](/api/docs/models/gpt-audio-mini.md): A cost-efficient version of GPT Audio