# Show HN: Modelparams.dev: AI Model Parameters Database (UI, API, NPM) > Source: > Published: 2026-06-18 15:07:03+00:00 # Every LLM parameter, for every model. An open, community-maintained catalog of LLM model parameters. Browse the UI below, query the API, or install the npm package. Access type Providers Parameters 191 of 191 models ## OpenAI ## [Chatgpt 4o Latest](/models/openai/chatgpt-4o-latest) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [Gpt 3.5 Turbo](/models/openai/gpt-3.5-turbo) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [Gpt 4 Turbo](/models/openai/gpt-4-turbo) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [Gpt 4 Turbo 2024-04-09](/models/openai/gpt-4-turbo-2024-04-09) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [Gpt 4.1](/models/openai/gpt-4.1) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [Gpt 4.1 Mini](/models/openai/gpt-4.1-mini) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [Gpt 4.1 Nano](/models/openai/gpt-4.1-nano) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [GPT-4o](/models/openai/gpt-4o) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [Gpt 4o 2024-11-20](/models/openai/gpt-4o-2024-11-20) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [GPT-4o mini](/models/openai/gpt-4o-mini) OpenAI 3 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…2 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | — | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | — | ## [Gpt 5](/models/openai/gpt-5) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (minimal | low | medium | high) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5 Chat Latest](/models/openai/gpt-5-chat-latest) OpenAI 1 param Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | ## [Gpt 5 Mini](/models/openai/gpt-5-mini) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (minimal | low | medium | high) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5 Nano](/models/openai/gpt-5-nano) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (minimal | low | medium | high) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.1](/models/openai/gpt-5.1) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (none | low | medium | high) | "none" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.1 Codex Max](/models/openai/gpt-5.1-codex-max-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (minimal | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.1 Codex](/models/openai/gpt-5.1-codex-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (minimal | low | medium | high) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.2](/models/openai/gpt-5.2) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (none | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.2 Codex](/models/openai/gpt-5.2-codex-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (minimal | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.2](/models/openai/gpt-5.2-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (minimal | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.3 Codex](/models/openai/gpt-5.3-codex) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.3 Codex Spark](/models/openai/gpt-5.3-codex-spark-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (minimal | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.3 Codex](/models/openai/gpt-5.3-codex-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (minimal | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.4](/models/openai/gpt-5.4) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (none | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.4 Mini](/models/openai/gpt-5.4-mini) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (none | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.4 Mini](/models/openai/gpt-5.4-mini-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (minimal | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.4 Nano](/models/openai/gpt-5.4-nano) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (none | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.4 Pro](/models/openai/gpt-5.4-pro) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.4 Pro](/models/openai/gpt-5.4-pro-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.4](/models/openai/gpt-5.4-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (minimal | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.5](/models/openai/gpt-5.5) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (none | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.5 Pro](/models/openai/gpt-5.5-pro) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [Gpt 5.5 Pro](/models/openai/gpt-5.5-pro-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [Gpt 5.5](/models/openai/gpt-5.5-subscription) OpenAI Subscription 3 params Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning.effort` | enum (minimal | low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | | Reasoning summary `reasoning.summary` | enum (auto | concise | detailed | none) | "auto" | Controls the level of reasoning summary returned with the response. | — | Output 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Verbosity `text.verbosity` | enum (low | medium | high) | "medium" | Controls how concise or detailed the model's final text response should be. | — | ## [o1](/models/openai/o1) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [o1-mini](/models/openai/o1-mini) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (minimal | low | medium | high) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [O1 Preview](/models/openai/o1-preview) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (minimal | low | medium | high) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [o3](/models/openai/o3) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [o3-mini](/models/openai/o3-mini) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [O3 Pro](/models/openai/o3-pro) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## [o4-mini](/models/openai/o4-mini) OpenAI 2 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max completion tokens `max_completion_tokens` | integer (16…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Reasoning effort `reasoning_effort` | enum (low | medium | high | xhigh) | "medium" | Controls how much reasoning the model should perform before producing an answer. | — | ## Anthropic ## [Claude 3.5 Haiku 20241022](/models/anthropic/claude-3-5-haiku-20241022) Anthropic 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | ## [Claude 3.5 Haiku Latest](/models/anthropic/claude-3-5-haiku-latest) Anthropic 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | ## [Claude 3.5 Sonnet 20241022](/models/anthropic/claude-3-5-sonnet-20241022) Anthropic 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | ## [Claude 3.5 Sonnet Latest](/models/anthropic/claude-3-5-sonnet-latest) Anthropic 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | ## [Claude 3.7 Sonnet 20250219](/models/anthropic/claude-3-7-sonnet-20250219) Anthropic 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | ## [Claude 3.7 Sonnet Latest](/models/anthropic/claude-3-7-sonnet-latest) Anthropic 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | ## [Claude 3 Opus 20240229](/models/anthropic/claude-3-opus-20240229) Anthropic 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | ## [Claude 3 Opus Latest](/models/anthropic/claude-3-opus-latest) Anthropic 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | ## [Claude Fable 5](/models/anthropic/claude-fable-5) Anthropic 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (adaptive) | — | Only adaptive thinking is supported; omit the parameter entirely to run without thinking (an explicit disabled value is rejected). | — | | Thinking display `thinking.display` | enum (summarized | omitted) | "omitted" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "adaptive" | | Effort `output_config.effort` | enum (low | medium | high | xhigh | max) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Fable 5](/models/anthropic/claude-fable-5-subscription) Anthropic Subscription 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (adaptive) | — | Only adaptive thinking is supported; omit the parameter entirely to run without thinking (an explicit disabled value is rejected). | — | | Thinking display `thinking.display` | enum (summarized | omitted) | "omitted" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "adaptive" | | Effort `output_config.effort` | enum (low | medium | high | xhigh | max) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Haiku 4](/models/anthropic/claude-haiku-4) Anthropic 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | ## [Claude Haiku 4.5](/models/anthropic/claude-haiku-4-5) Anthropic 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | ## [Claude Haiku 4.5 20251001](/models/anthropic/claude-haiku-4-5-20251001) Anthropic 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" or top_p ≠ null | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" or temperature ≠ null | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | ## [Claude Haiku 4.5 20251001](/models/anthropic/claude-haiku-4-5-20251001-subscription) Anthropic Subscription 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" or top_p ≠ null | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" or temperature ≠ null | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | ## [Claude Haiku 4.5](/models/anthropic/claude-haiku-4-5-subscription) Anthropic Subscription 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | ## [Claude Haiku 4](/models/anthropic/claude-haiku-4-subscription) Anthropic Subscription 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | ## [Claude Opus 4.1 20250805](/models/anthropic/claude-opus-4-1-20250805) Anthropic 7 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" or top_p ≠ null | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" or temperature ≠ null | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "enabled" | ## [Claude Opus 4.1 20250805](/models/anthropic/claude-opus-4-1-20250805-subscription) Anthropic Subscription 7 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" or top_p ≠ null | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" or temperature ≠ null | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "enabled" | ## [Claude Opus 4 20250514](/models/anthropic/claude-opus-4-20250514) Anthropic 7 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "enabled" | ## [Claude Opus 4 20250514](/models/anthropic/claude-opus-4-20250514-subscription) Anthropic Subscription 7 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "enabled" | ## [Claude Opus 4.5 20251101](/models/anthropic/claude-opus-4-5-20251101) Anthropic 8 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" or top_p ≠ null | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" or temperature ≠ null | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 4 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "enabled" | | Effort `output_config.effort` | enum (low | medium | high) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Opus 4.5 20251101](/models/anthropic/claude-opus-4-5-20251101-subscription) Anthropic Subscription 8 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" or top_p ≠ null | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" or temperature ≠ null | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 4 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "enabled" | | Effort `output_config.effort` | enum (low | medium | high) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Opus 4.6](/models/anthropic/claude-opus-4-6) Anthropic 8 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"enabled", "adaptive"} or top_p ≠ null | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"enabled", "adaptive"} or temperature ≠ null | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"enabled", "adaptive"} | Reasoning 4 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | adaptive | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type ∈ {"adaptive", "enabled"} | | Effort `output_config.effort` | enum (low | medium | high | max) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Opus 4.6](/models/anthropic/claude-opus-4-6-subscription) Anthropic Subscription 8 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"enabled", "adaptive"} or top_p ≠ null | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"enabled", "adaptive"} or temperature ≠ null | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"enabled", "adaptive"} | Reasoning 4 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | adaptive | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type ∈ {"adaptive", "enabled"} | | Effort `output_config.effort` | enum (low | medium | high | max) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Opus 4.7](/models/anthropic/claude-opus-4-7) Anthropic 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | adaptive) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Thinking display `thinking.display` | enum (summarized | omitted) | "omitted" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "adaptive" | | Effort `output_config.effort` | enum (low | medium | high | xhigh | max) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Opus 4.7](/models/anthropic/claude-opus-4-7-subscription) Anthropic Subscription 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | adaptive) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Thinking display `thinking.display` | enum (summarized | omitted) | "omitted" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "adaptive" | | Effort `output_config.effort` | enum (low | medium | high | xhigh | max) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Opus 4.8](/models/anthropic/claude-opus-4-8) Anthropic 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | adaptive) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Thinking display `thinking.display` | enum (summarized | omitted) | "omitted" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "adaptive" | | Effort `output_config.effort` | enum (low | medium | high | xhigh | max) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Opus 4.8](/models/anthropic/claude-opus-4-8-subscription) Anthropic Subscription 4 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | adaptive) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Thinking display `thinking.display` | enum (summarized | omitted) | "omitted" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "adaptive" | | Effort `output_config.effort` | enum (low | medium | high | xhigh | max) | "high" | Controls Anthropic response thoroughness and token spend. | — | ## [Claude Opus 4](/models/anthropic/claude-opus-4-subscription) Anthropic Subscription 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | adaptive | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | ## [Claude Sonnet 4 20250514](/models/anthropic/claude-sonnet-4-20250514) Anthropic 7 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "enabled" | ## [Claude Sonnet 4 20250514](/models/anthropic/claude-sonnet-4-20250514-subscription) Anthropic Subscription 7 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type = "enabled" | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type = "enabled" | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type = "enabled" | Reasoning 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. | — | | Budget tokens `thinking.budget_tokens` | integer (1024…+∞) | 4096 | Maximum token budget Anthropic may use for extended thinking before producing the final answer. | Only when thinking.type = "enabled" | | Thinking display `thinking.display` | enum (summarized | omitted) | "summarized" | Controls whether Anthropic returns summarized or omitted thinking content. | Only when thinking.type = "enabled" | ## [Claude Sonnet 4.5](/models/anthropic/claude-sonnet-4-5) Anthropic 6 params Length 1 param | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Max tokens `max_tokens` | integer (1…+∞) | 4096 | Maximum number of output tokens the model may generate. | — | Sampling 3 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Temperature `temperature` | number (0…1 step 0.1) | 1 | Controls randomness. Lower values make outputs more focused; higher values make them more varied. | Not when thinking.type ∈ {"adaptive", "enabled"} | | Top P `top_p` | number (0…1 step 0.01) | 1 | Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value. | Not when thinking.type ∈ {"adaptive", "enabled"} or temperature ≠ 1 | | Top K `top_k` | integer (0…+∞) | 0 | Limits token sampling to the top K most likely next tokens. | Not when thinking.type ∈ {"adaptive", "enabled"} | Reasoning 2 params | Parameter | Type | Default | Description | Condition | |---|---|---|---|---| | Thinking mode `thinking.type` | enum (disabled | adaptive | enabled) | "disabled" | Controls the Anthropic thinking mode values supported by this model. |