modelparams.dev
Sampling integer 34 models

Seed generationConfig.seed

Optional seed used for decoding when reproducible sampling is desired.

Type
integer
Default
no default

generationConfig.seed by model

The exact type, default, range, and conditions for generationConfig.seed on each model that documents it.

Model Provider Type Default Range / values Condition
Gemini 2.5 Flash Google integer — — —
Gemini 2.5 Flash Subscription Google integer — — —
Gemini 2.5 Flash Lite Google integer — — —
Gemini 2.5 Flash Lite Subscription Google integer — — —
Gemini 2.5 Pro Google integer — — —
Gemini 2.5 Pro Subscription Google integer — — —
Gemini 3 Flash Preview Google integer — — —
Gemini 3 Flash Preview Subscription Google integer — — —
Gemini 3.1 Flash Lite Google integer — — —
Gemini 3.1 Flash Lite Subscription Google integer — — —
Gemini 3.1 Flash Lite Preview Google integer — — —
Gemini 3.1 Flash Lite Preview Subscription Google integer — — —
Gemini 3.1 Pro Preview Google integer — — —
Gemini 3.1 Pro Preview Subscription Google integer — — —
Gemini 3.1 Pro Preview Customtools Google integer — — —
Gemini 3.5 Flash Google integer — — —
Gemini 3.5 Flash Lite Google integer — — —
Gemini 3.6 Flash Google integer — — —
Gemini 3.7 Flash Google integer — — —
Gemini 3.8 Flash Google integer — — —
Gemini Flash Latest Google integer — — —
Gemma 4 26B A4B IT Google integer — — —
Gemma 4 31B IT Google integer — — —
Gemini 2.5 Flash Vertex integer — — —
Gemini 2.5 Flash Lite Vertex integer — — —
Gemini 2.5 Pro Vertex integer — — —
Gemini 3 Flash Preview Vertex integer — — —
Gemini 3.1 Flash Lite Vertex integer — — —
Gemini 3.1 Pro Preview Vertex integer — — —
Gemini 3.1 Pro Preview Customtools Vertex integer — — —
Gemini 3.5 Flash Vertex integer — — —
Gemini 3.5 Flash Lite Vertex integer — — —
Gemini 3.6 Flash Vertex integer — — —
Gemini 3.7 Flash Vertex integer — — —

Models without generationConfig.seed documented yet

These models don't list generationConfig.seed in the catalog. That may mean the provider doesn't accept it, or it simply hasn't been added yet — the data is community-maintained.

Cerebras

Thinking Machines

Related sampling parameters

Resources

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