modelparams.dev
API GitHub

Providers

Alibaba Anthropic Cohere DeepSeek Google Meta MiniMax Mistral Moonshot AI Nvidia OpenAI Perplexity xAI Xiaomi Z.ai

Providers

Alibaba Anthropic Cohere DeepSeek Google Meta MiniMax Mistral Moonshot AI Nvidia OpenAI Perplexity xAI Xiaomi Z.ai
DeepSeek 5 params

DeepSeek Deepseek V4 Flash parameters

These are the parameters modelparams.dev tracks for DeepSeek Deepseek V4 Flash. 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.

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. In DeepSeek thinking mode this parameter is accepted for compatibility but has no effect.
Not when thinking.type = "enabled"
Top P
top_p 		number (0…1 step 0.01) 1 Controls nucleus sampling. In DeepSeek thinking mode this parameter is accepted for compatibility but has no effect.
Not when thinking.type = "enabled"
Reasoning 2 params
Parameter Type Default Description Condition
Thinking mode
thinking.type 		enum (enabled | disabled) "enabled" Controls whether DeepSeek uses thinking mode before producing the final answer. —
Reasoning effort
reasoning_effort 		enum (high | max) "high" Controls DeepSeek thinking effort when thinking mode is enabled.
Only when thinking.type = "enabled"

DeepSeek Deepseek V4 Flash parameters in brief

DeepSeek Deepseek V4 Flash documents 5 API parameters, grouped by what they control:

Resources

All DeepSeek models Glossary Full catalog

Deepseek V4 Flash — JSON

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

/api/v1/models/deepseek/deepseek-v4-flash.json 
{
  "$schema": "https://modelparams.dev/api/v1/schema.json",
  "provider": "deepseek",
  "authType": "api_key",
  "model": "deepseek-v4-flash",
  "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. In DeepSeek thinking mode this parameter is accepted for compatibility but has no effect.",
      "group": "sampling",
      "applicability": {
        "except": {
          "thinking.type": [
            "enabled"
          ]
        }
      },
      "type": "number",
      "default": 1,
      "range": {
        "min": 0,
        "max": 2,
        "step": 0.1
      }
    },
    {
      "path": "top_p",
      "label": "Top P",
      "description": "Controls nucleus sampling. In DeepSeek thinking mode this parameter is accepted for compatibility but has no effect.",
      "group": "sampling",
      "applicability": {
        "except": {
          "thinking.type": [
            "enabled"
          ]
        }
      },
      "type": "number",
      "default": 1,
      "range": {
        "min": 0,
        "max": 1,
        "step": 0.01
      }
    },
    {
      "path": "thinking.type",
      "label": "Thinking mode",
      "description": "Controls whether DeepSeek uses thinking mode before producing the final answer.",
      "group": "reasoning",
      "type": "enum",
      "default": "enabled",
      "values": [
        "enabled",
        "disabled"
      ]
    },
    {
      "path": "reasoning_effort",
      "label": "Reasoning effort",
      "description": "Controls DeepSeek thinking effort when thinking mode is enabled.",
      "group": "reasoning",
      "applicability": {
        "only": {
          "thinking.type": "enabled"
        }
      },
      "type": "enum",
      "default": "high",
      "values": [
        "high",
        "max"
      ]
    }
  ]
}

Other DeepSeek models

Deepseek Chat 4 params View Deepseek Reasoner 5 params View Deepseek V4 Pro 5 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/params/gpt-5.5.json
curl https://modelparams.dev/api/v1/params/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