modelparams.dev
API MCP GitHub

Providers

Alibaba Anthropic Bedrock Cerebras Cohere DeepSeek Fireworks Google Groq Meta MiniMax Mistral Moonshot AI NVIDIA OpenAI Perplexity Thinking Machines Vertex xAI Xiaomi Z.ai

Providers

Alibaba Anthropic Bedrock Cerebras Cohere DeepSeek Fireworks Google Groq Meta MiniMax Mistral Moonshot AI NVIDIA OpenAI Perplexity Thinking Machines Vertex xAI Xiaomi Z.ai
Anthropic Subscription 6 params

Anthropic Claude Opus 4 (subscription) API parameters

These are the API parameters modelparams.dev tracks for Anthropic Claude Opus 4 when you reach it through a subscription rather than an API key — the settings you send in a request. Each row gives the type, default, valid range or values, and the conditions that gate it. It's the same data the JSON API serves.

After the parameter count instead — how many weights Claude Opus 4 has? That's a different number, and we don't track it. Here's the difference.

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"

Anthropic Claude Opus 4 API parameters in brief

Anthropic Claude Opus 4 via subscription documents 6 API parameters, grouped by what they control:

Frequently asked questions

Which API parameters does Anthropic Claude Opus 4 (subscription) support?
Anthropic Claude Opus 4 (subscription) accepts 6 API parameters in the request body: max_tokens, temperature, top_p, top_k, thinking.type, thinking.budget_tokens.
What is the default temperature for Anthropic Claude Opus 4 (subscription)?
The default temperature for Anthropic Claude Opus 4 (subscription) is 1, within a valid range of 0 to 1.
What is the default top_p for Anthropic Claude Opus 4 (subscription)?
The default top_p for Anthropic Claude Opus 4 (subscription) is 1, within a valid range of 0 to 1.
What is the default max_tokens for Anthropic Claude Opus 4 (subscription)?
The default max_tokens for Anthropic Claude Opus 4 (subscription) is 4096, with a minimum of 1.
What is the default top_k for Anthropic Claude Opus 4 (subscription)?
The default top_k for Anthropic Claude Opus 4 (subscription) is 0, with a minimum of 0.

Resources

All Anthropic models Glossary Full catalog

Claude Opus 4 — JSON

The full model definition as served by the API. Copy it or open the endpoint directly.

/api/v1/models/anthropic/claude-opus-4-subscription.json 
{
  "$schema": "https://modelparams.dev/api/v1/schema.json",
  "provider": "anthropic",
  "authType": "subscription",
  "model": "claude-opus-4",
  "params": [
    {
      "path": "max_tokens",
      "label": "Max tokens",
      "description": "Maximum number of output tokens the model may generate.",
      "group": "generation_length",
      "type": "integer",
      "default": 4096,
      "range": {
        "min": 1
      }
    },
    {
      "path": "temperature",
      "label": "Temperature",
      "description": "Controls randomness. Lower values make outputs more focused; higher values make them more varied.",
      "group": "sampling",
      "applicability": {
        "except": {
          "thinking.type": [
            "adaptive",
            "enabled"
          ]
        }
      },
      "type": "number",
      "default": 1,
      "range": {
        "min": 0,
        "max": 1,
        "step": 0.1
      }
    },
    {
      "path": "top_p",
      "label": "Top P",
      "description": "Controls nucleus sampling by limiting generation to tokens whose cumulative probability reaches this value.",
      "group": "sampling",
      "applicability": {
        "except": [
          {
            "thinking.type": [
              "adaptive",
              "enabled"
            ]
          },
          {
            "temperature": {
              "not": 1
            }
          }
        ]
      },
      "type": "number",
      "default": 1,
      "range": {
        "min": 0,
        "max": 1,
        "step": 0.01
      }
    },
    {
      "path": "top_k",
      "label": "Top K",
      "description": "Limits token sampling to the top K most likely next tokens.",
      "group": "sampling",
      "applicability": {
        "except": {
          "thinking.type": [
            "adaptive",
            "enabled"
          ]
        }
      },
      "type": "integer",
      "default": 0,
      "range": {
        "min": 0
      }
    },
    {
      "path": "thinking.type",
      "label": "Thinking mode",
      "description": "Controls the Anthropic thinking mode values supported by this model.",
      "group": "reasoning",
      "type": "enum",
      "default": "disabled",
      "values": [
        "disabled",
        "adaptive",
        "enabled"
      ]
    },
    {
      "path": "thinking.budget_tokens",
      "label": "Budget tokens",
      "description": "Maximum token budget Anthropic may use for extended thinking before producing the final answer.",
      "group": "reasoning",
      "applicability": {
        "only": {
          "thinking.type": "enabled"
        }
      },
      "type": "integer",
      "default": 4096,
      "range": {
        "min": 1024
      }
    }
  ]
}

Other Anthropic models

Claude 3 Opus 20240229 4 params View Claude 3 Opus Latest 4 params View Claude 3.5 Haiku 20241022 4 params View Claude 3.5 Haiku Latest 4 params View Claude 3.5 Sonnet 20241022 4 params View Claude 3.5 Sonnet Latest 4 params View Claude 3.7 Sonnet 20250219 6 params View Claude 3.7 Sonnet Latest 6 params View Claude Fable 5 4 params View Claude Fable 5 Subscription 4 params View Claude Haiku 4 6 params View Claude Haiku 4 Subscription 6 params View Claude Haiku 4.5 6 params View Claude Haiku 4.5 Subscription 6 params View Claude Haiku 4.5 20251001 6 params View Claude Haiku 4.5 20251001 Subscription 6 params View Claude Opus 4 20250514 7 params View Claude Opus 4 20250514 Subscription 7 params View Claude Opus 4.1 20250805 7 params View Claude Opus 4.1 20250805 Subscription 7 params View Claude Opus 4.5 20251101 8 params View Claude Opus 4.5 20251101 Subscription 8 params View Claude Opus 4.6 8 params View Claude Opus 4.6 Subscription 8 params View Claude Opus 4.7 4 params View Claude Opus 4.7 Subscription 4 params View Claude Opus 4.8 4 params View Claude Opus 4.8 Subscription 4 params View Claude Opus 5 4 params View Claude Opus 5 Subscription 4 params View Claude Sonnet 4 Subscription 6 params View Claude Sonnet 4 20250514 7 params View Claude Sonnet 4 20250514 Subscription 7 params View Claude Sonnet 4.5 6 params View Claude Sonnet 4.5 Subscription 6 params View Claude Sonnet 4.5 20250929 6 params View Claude Sonnet 4.5 20250929 Subscription 6 params View Claude Sonnet 4.6 8 params View Claude Sonnet 4.6 Subscription 8 params View Claude Sonnet 5 4 params View Claude Sonnet 5 Subscription 4 params View

How to use

Building with an AI agent? Hit Copy to grab this whole guide as Markdown and paste it in — or point your agent straight at /llms.txt.

modelparams.dev is an open, community-maintained catalog of model parameters. Each entry shows the knobs you can turn — type, default, range, and the conditions that gate it.

The same model accessed via an API key and via a subscription usually exposes a different set of parameters. We list both as separate entries so the data stays honest.

Catalog API

The full catalog is static JSON, CORS-enabled, served from the edge.

curl https://modelparams.dev/api/v1/models.json

Each entry is keyed by provider/model for API-key variants; subscription variants append -subscription.

If you only need the params for one model contract, use the providerless endpoint. Subscription contracts are model slugs with -subscription. 

curl https://modelparams.dev/api/v1/models/openai/gpt-5.5.json
curl https://modelparams.dev/api/v1/models/openai/gpt-5.5-subscription.json

Single model

curl https://modelparams.dev/api/v1/models/anthropic/claude-opus-4-7.json
curl https://modelparams.dev/api/v1/models/anthropic/claude-opus-4-7-subscription.json

JSON Schema

Every entry validates against a JSON Schema you can use in your editor or pipeline. 

curl https://modelparams.dev/api/v1/schema.json

Add this header to any YAML you author for autocomplete in VS Code: 

# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json

Logos

Provider logos are available at /assets/logos/{provider}.svg where {provider} is the provider slug. They use currentColor so they inherit your text color. 

curl https://modelparams.dev/assets/logos/anthropic.svg

Logos are sourced from the models.dev repo (MIT) and used under nominative fair use.

Contribute

The data lives in YAML under models/{provider}/{model}-{auth}.yaml in the GitHub repo. Open a PR; CI validates against the schema and rebuilds.

Edit on GitHub MIT licensed