diff --git a/models/anthropic/claude-haiku-4-5-20251001.yaml b/models/anthropic/claude-haiku-4-5-20251001.yaml index 392ad3b..2738963 100644 --- a/models/anthropic/claude-haiku-4-5-20251001.yaml +++ b/models/anthropic/claude-haiku-4-5-20251001.yaml @@ -25,9 +25,10 @@ params: group: sampling applicability: except: - thinking.type: - - adaptive - - enabled + - thinking.type: + - enabled + - top_p: + not: null - path: top_p type: number label: Top P @@ -43,10 +44,9 @@ params: applicability: except: - thinking.type: - - adaptive - enabled - temperature: - not: 1 + not: null - path: top_k type: integer label: Top K @@ -58,7 +58,6 @@ params: applicability: except: thinking.type: - - adaptive - enabled - path: thinking.type type: enum diff --git a/models/anthropic/claude-opus-4-6.yaml b/models/anthropic/claude-opus-4-6.yaml index af30e0c..c7f567f 100644 --- a/models/anthropic/claude-opus-4-6.yaml +++ b/models/anthropic/claude-opus-4-6.yaml @@ -25,9 +25,10 @@ params: group: sampling applicability: except: - thinking.type: - - adaptive - - enabled + - thinking.type: + - enabled + - top_p: + not: null - path: top_p type: number label: Top P @@ -43,10 +44,9 @@ params: applicability: except: - thinking.type: - - adaptive - enabled - temperature: - not: 1 + not: null - path: top_k type: integer label: Top K @@ -58,7 +58,6 @@ params: applicability: except: thinking.type: - - adaptive - enabled - path: thinking.type type: enum @@ -67,7 +66,6 @@ params: default: disabled values: - disabled - - adaptive - enabled group: reasoning - path: thinking.budget_tokens diff --git a/models/anthropic/claude-opus-4-7.yaml b/models/anthropic/claude-opus-4-7.yaml index b78228d..414f3f6 100644 --- a/models/anthropic/claude-opus-4-7.yaml +++ b/models/anthropic/claude-opus-4-7.yaml @@ -11,55 +11,6 @@ params: range: min: 1 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 1 - step: 0.1 - group: sampling - applicability: - except: - thinking.type: - - adaptive - - enabled - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - applicability: - except: - - thinking.type: - - adaptive - - enabled - - temperature: - not: 1 - - path: top_k - type: integer - label: Top K - description: Limits token sampling to the top K most likely next tokens. - default: 0 - range: - min: 0 - group: sampling - applicability: - except: - thinking.type: - - adaptive - - enabled - path: thinking.type type: enum label: Thinking mode @@ -67,5 +18,4 @@ params: default: disabled values: - disabled - - adaptive group: reasoning diff --git a/models/anthropic/claude-sonnet-4-5-20250929.yaml b/models/anthropic/claude-sonnet-4-5-20250929.yaml index 3b39817..6e1a141 100644 --- a/models/anthropic/claude-sonnet-4-5-20250929.yaml +++ b/models/anthropic/claude-sonnet-4-5-20250929.yaml @@ -25,9 +25,10 @@ params: group: sampling applicability: except: - thinking.type: - - adaptive - - enabled + - thinking.type: + - enabled + - top_p: + not: null - path: top_p type: number label: Top P @@ -43,10 +44,9 @@ params: applicability: except: - thinking.type: - - adaptive - enabled - temperature: - not: 1 + not: null - path: top_k type: integer label: Top K @@ -58,7 +58,6 @@ params: applicability: except: thinking.type: - - adaptive - enabled - path: thinking.type type: enum @@ -67,7 +66,6 @@ params: default: disabled values: - disabled - - adaptive - enabled group: reasoning - path: thinking.budget_tokens diff --git a/models/anthropic/claude-sonnet-4-6.yaml b/models/anthropic/claude-sonnet-4-6.yaml index 1e35b85..5e65af2 100644 --- a/models/anthropic/claude-sonnet-4-6.yaml +++ b/models/anthropic/claude-sonnet-4-6.yaml @@ -25,9 +25,10 @@ params: group: sampling applicability: except: - thinking.type: - - adaptive - - enabled + - thinking.type: + - enabled + - top_p: + not: null - path: top_p type: number label: Top P @@ -43,10 +44,9 @@ params: applicability: except: - thinking.type: - - adaptive - enabled - temperature: - not: 1 + not: null - path: top_k type: integer label: Top K @@ -58,7 +58,6 @@ params: applicability: except: thinking.type: - - adaptive - enabled - path: thinking.type type: enum @@ -67,7 +66,6 @@ params: default: disabled values: - disabled - - adaptive - enabled group: reasoning - path: thinking.budget_tokens diff --git a/models/openai/gpt-5-chat-latest.yaml b/models/openai/gpt-5-chat-latest.yaml index f4496a5..e0bd609 100644 --- a/models/openai/gpt-5-chat-latest.yaml +++ b/models/openai/gpt-5-chat-latest.yaml @@ -3,46 +3,11 @@ provider: openai authType: api_key model: gpt-5-chat-latest params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 2 - step: 0.1 - group: sampling - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - - path: reasoning_effort - type: enum - label: Reasoning effort - description: Controls how much reasoning the model should perform before producing an answer. - default: medium - values: - - minimal - - low - - medium - - high - group: reasoning diff --git a/models/openai/gpt-5-mini.yaml b/models/openai/gpt-5-mini.yaml index 43da32c..7ab3f1c 100644 --- a/models/openai/gpt-5-mini.yaml +++ b/models/openai/gpt-5-mini.yaml @@ -3,38 +3,14 @@ provider: openai authType: api_key model: gpt-5-mini params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 2 - step: 0.1 - group: sampling - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - path: reasoning_effort type: enum label: Reasoning effort diff --git a/models/openai/gpt-5-nano.yaml b/models/openai/gpt-5-nano.yaml index 13f9f62..bf6073a 100644 --- a/models/openai/gpt-5-nano.yaml +++ b/models/openai/gpt-5-nano.yaml @@ -3,38 +3,14 @@ provider: openai authType: api_key model: gpt-5-nano params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 2 - step: 0.1 - group: sampling - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - path: reasoning_effort type: enum label: Reasoning effort diff --git a/models/openai/gpt-5.1.yaml b/models/openai/gpt-5.1.yaml index 2609d54..0c902bf 100644 --- a/models/openai/gpt-5.1.yaml +++ b/models/openai/gpt-5.1.yaml @@ -3,38 +3,14 @@ provider: openai authType: api_key model: gpt-5.1 params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 2 - step: 0.1 - group: sampling - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - path: reasoning_effort type: enum label: Reasoning effort diff --git a/models/openai/gpt-5.2.yaml b/models/openai/gpt-5.2.yaml index b5ccd5b..299546a 100644 --- a/models/openai/gpt-5.2.yaml +++ b/models/openai/gpt-5.2.yaml @@ -3,45 +3,21 @@ provider: openai authType: api_key model: gpt-5.2 params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 2 - step: 0.1 - group: sampling - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - path: reasoning_effort type: enum label: Reasoning effort description: Controls how much reasoning the model should perform before producing an answer. default: medium values: - - minimal + - none - low - medium - high diff --git a/models/openai/gpt-5.4-mini.yaml b/models/openai/gpt-5.4-mini.yaml index 366a318..1f87ffb 100644 --- a/models/openai/gpt-5.4-mini.yaml +++ b/models/openai/gpt-5.4-mini.yaml @@ -3,45 +3,21 @@ provider: openai authType: api_key model: gpt-5.4-mini params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 2 - step: 0.1 - group: sampling - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - path: reasoning_effort type: enum label: Reasoning effort description: Controls how much reasoning the model should perform before producing an answer. default: medium values: - - minimal + - none - low - medium - high diff --git a/models/openai/gpt-5.4.yaml b/models/openai/gpt-5.4.yaml index adc236c..708fc18 100644 --- a/models/openai/gpt-5.4.yaml +++ b/models/openai/gpt-5.4.yaml @@ -3,45 +3,21 @@ provider: openai authType: api_key model: gpt-5.4 params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 2 - step: 0.1 - group: sampling - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - path: reasoning_effort type: enum label: Reasoning effort description: Controls how much reasoning the model should perform before producing an answer. default: medium values: - - minimal + - none - low - medium - high diff --git a/models/openai/gpt-5.5.yaml b/models/openai/gpt-5.5.yaml index af1b65c..e5c6221 100644 --- a/models/openai/gpt-5.5.yaml +++ b/models/openai/gpt-5.5.yaml @@ -3,45 +3,21 @@ provider: openai authType: api_key model: gpt-5.5 params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 2 - step: 0.1 - group: sampling - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - path: reasoning_effort type: enum label: Reasoning effort description: Controls how much reasoning the model should perform before producing an answer. default: medium values: - - minimal + - none - low - medium - high diff --git a/models/openai/gpt-5.yaml b/models/openai/gpt-5.yaml index 5d62f79..5a2c130 100644 --- a/models/openai/gpt-5.yaml +++ b/models/openai/gpt-5.yaml @@ -3,38 +3,14 @@ provider: openai authType: api_key model: gpt-5 params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - - path: temperature - type: number - label: Temperature - description: >- - Controls randomness. Lower values make outputs more focused; higher values make them more - varied. - default: 1 - range: - min: 0 - max: 2 - step: 0.1 - group: sampling - - path: top_p - type: number - label: Top P - description: >- - Controls nucleus sampling by limiting generation to tokens whose cumulative probability - reaches this value. - default: 1 - range: - min: 0 - max: 1 - step: 0.01 - group: sampling - path: reasoning_effort type: enum label: Reasoning effort diff --git a/models/openai/o1.yaml b/models/openai/o1.yaml index 35ec80c..7866237 100644 --- a/models/openai/o1.yaml +++ b/models/openai/o1.yaml @@ -3,13 +3,13 @@ provider: openai authType: api_key model: o1 params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - path: reasoning_effort type: enum @@ -17,8 +17,8 @@ params: description: Controls how much reasoning the model should perform before producing an answer. default: medium values: - - minimal - low - medium - high + - xhigh group: reasoning diff --git a/models/openai/o3-mini.yaml b/models/openai/o3-mini.yaml index beb1f43..367d746 100644 --- a/models/openai/o3-mini.yaml +++ b/models/openai/o3-mini.yaml @@ -3,13 +3,13 @@ provider: openai authType: api_key model: o3-mini params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - path: reasoning_effort type: enum @@ -17,8 +17,8 @@ params: description: Controls how much reasoning the model should perform before producing an answer. default: medium values: - - minimal - low - medium - high + - xhigh group: reasoning diff --git a/models/openai/o3.yaml b/models/openai/o3.yaml index c2d5af6..27597b3 100644 --- a/models/openai/o3.yaml +++ b/models/openai/o3.yaml @@ -3,13 +3,13 @@ provider: openai authType: api_key model: o3 params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - path: reasoning_effort type: enum @@ -17,8 +17,8 @@ params: description: Controls how much reasoning the model should perform before producing an answer. default: medium values: - - minimal - low - medium - high + - xhigh group: reasoning diff --git a/models/openai/o4-mini.yaml b/models/openai/o4-mini.yaml index e676838..7bdbc41 100644 --- a/models/openai/o4-mini.yaml +++ b/models/openai/o4-mini.yaml @@ -3,13 +3,13 @@ provider: openai authType: api_key model: o4-mini params: - - path: max_tokens + - path: max_completion_tokens type: integer label: Max tokens description: Maximum number of output tokens the model may generate. default: 4096 range: - min: 1 + min: 16 group: generation_length - path: reasoning_effort type: enum @@ -17,8 +17,8 @@ params: description: Controls how much reasoning the model should perform before producing an answer. default: medium values: - - minimal - low - medium - high + - xhigh group: reasoning