modelparams.dev
Output enum 106 models

Response format response_format.type

Forces the response into plain text or a JSON object.

Type
enum
Default
"text"

response_format.type by model

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

Model Provider Type Default Range / values Condition
Zai GLM-4.7 Cerebras enum "text" text | json_object
Command A 03 2025 Cohere enum "text" text | json_object
Command A Plus 05 2026 Cohere enum "text" text | json_object
Command A Reasoning 08 2025 Cohere enum "text" text | json_object
Command A Translate 08 2025 Cohere enum "text" text | json_object
Command A Vision 07 2025 Cohere enum "text" text | json_object
Command R 08 2024 Cohere enum "text" text | json_object
Command R Plus 08 2024 Cohere enum "text" text | json_object
Command R7B 12 2024 Cohere enum "text" text | json_object
DeepSeek v4 Flash 0731 Fireworks enum text | json_object
DeepSeek v4 Pro Fireworks enum text | json_object
DeepSeek v4 Pro 0813 Fireworks enum text | json_object
GLM-5p2 Fireworks enum text | json_object
GPT-OSS 120B Fireworks enum text | json_object
GPT-OSS 20B Fireworks enum text | json_object
Inkling Fireworks enum text | json_object
Kimi K2p6 Fireworks enum text | json_object
Kimi K2p7 Code Fireworks enum text | json_object
Kimi K3 Fireworks enum text | json_object
MiniMax M2p7 Fireworks enum text | json_object
MiniMax M3 Fireworks enum text | json_object
Muse Glimmer 30B Fireworks enum text | json_object
Qwen3p7 Plus Fireworks enum text | json_object
Qwen3p8 2p4t A95B Fireworks enum text | json_object
Qwen3p8 Max Fireworks enum text | json_object
GPT-OSS 120B Groq enum "text" text | json_object
GPT-OSS 20B Groq enum "text" text | json_object
GPT-OSS Safeguard 20B Groq enum "text" text | json_object
Qwen3 32B Groq enum "text" text | json_object
Qwen3.6 27B Groq enum "text" text | json_object
Llama 3.3 70B Instruct Meta enum "text" text | json_schema
Llama 3.3 8B Instruct Meta enum "text" text | json_schema
Llama 4 Maverick 17B 128E Instruct FP8 Meta enum "text" text | json_schema
Llama 4 Scout 17B 16E Instruct FP8 Meta enum "text" text | json_schema
Muse Spark 1.1 Meta enum "text" text | json_object | json_schema
Muse Spark 1.2 Contributor Meta enum "text" text | json_object | json_schema
Codestral 2508 Mistral enum "text" text | json_object | json_schema
Codestral Latest Mistral enum "text" text | json_object | json_schema
Devstral 2512 Mistral enum "text" text | json_object | json_schema
Devstral Latest Mistral enum "text" text | json_object | json_schema
Magistral Medium Latest Mistral enum "text" text | json_object | json_schema
Magistral Small Latest Mistral enum "text" text | json_object | json_schema
Ministral 14B 2512 Mistral enum "text" text | json_object | json_schema
Ministral 14B Latest Mistral enum "text" text | json_object | json_schema
Ministral 3B 2512 Mistral enum "text" text | json_object | json_schema
Ministral 3B Latest Mistral enum "text" text | json_object | json_schema
Ministral 8B 2512 Mistral enum "text" text | json_object | json_schema
Ministral 8B Latest Mistral enum "text" text | json_object | json_schema
Mistral Large 2512 Mistral enum "text" text | json_object | json_schema
Mistral Large Latest Mistral enum "text" text | json_object | json_schema
Mistral Medium 3 Mistral enum "text" text | json_object | json_schema
Mistral Medium 3.5 Mistral enum "text" text | json_object | json_schema
Mistral Medium Latest Mistral enum "text" text | json_object | json_schema
Mistral NeMo Mistral enum "text" text | json_object | json_schema
Mistral Small 2603 Mistral enum "text" text | json_object | json_schema
Mistral Small Latest Mistral enum "text" text | json_object | json_schema
Kimi K2.5 Moonshot AI enum "text" text | json_object
Kimi K2.6 Moonshot AI enum "text" text | json_object
Kimi K2.6 Subscription Moonshot AI enum "text" text | json_object
Kimi K2.7 Code Moonshot AI enum "text" text | json_object | json_schema
Kimi K2.7 Code Subscription Moonshot AI enum "text" text | json_object
Kimi K2.7 Code Highspeed Moonshot AI enum "text" text | json_object | json_schema
Kimi K2.7 Code Highspeed Subscription Moonshot AI enum "text" text | json_object
Kimi K3 Moonshot AI enum "text" text | json_object | json_schema
Moonshot v1 128K Moonshot AI enum "text" text | json_object
Moonshot v1 32K Moonshot AI enum "text" text | json_object
Moonshot v1 8K Moonshot AI enum "text" text | json_object
GPT-4 OpenAI enum "text" text | json_schema
GPT-OSS 120B OpenAI enum "text" text | json_schema
GPT-OSS 20B OpenAI enum "text" text | json_schema
Grok 4.20 0309 Non Reasoning xAI enum "text" text | json_object | json_schema
Grok 4.20 0309 Non Reasoning Subscription xAI enum "text" text | json_object | json_schema
Grok 4.20 0309 Reasoning xAI enum "text" text | json_object | json_schema
Grok 4.20 0309 Reasoning Subscription xAI enum "text" text | json_object | json_schema
Grok 4.3 xAI enum "text" text | json_object | json_schema
Grok 4.3 Subscription xAI enum "text" text | json_object | json_schema
Grok 4.5 xAI enum "text" text | json_object | json_schema
Grok 4.5 Subscription xAI enum "text" text | json_object | json_schema
Grok 4.6 xAI enum "text" text | json_object | json_schema
Grok Build 0.1 xAI enum "text" text | json_object | json_schema
Grok Build 0.1 Subscription xAI enum "text" text | json_object | json_schema
MiMo v2.5 Xiaomi enum "text" text | json_object
MiMo v2.5 Subscription Xiaomi enum "text" text | json_object
MiMo v2.5 Pro Xiaomi enum "text" text | json_object
GLM-4.5 Z.ai enum "text" text | json_object
GLM-4.5 Subscription Z.ai enum "text" text | json_object
GLM-4.5-Air Z.ai enum "text" text | json_object
GLM-4.5-Air Subscription Z.ai enum "text" text | json_object
GLM-4.5-AirX Z.ai enum "text" text | json_object
GLM-4.5-Flash Z.ai enum "text" text | json_object
GLM-4.5-X Z.ai enum "text" text | json_object
GLM-4.6 Z.ai enum "text" text | json_object
GLM-4.6 Subscription Z.ai enum "text" text | json_object
GLM-4.7 Z.ai enum "text" text | json_object
GLM-4.7 Subscription Z.ai enum "text" text | json_object
GLM-4.7-Flash Z.ai enum "text" text | json_object
GLM-4.7-FlashX Z.ai enum "text" text | json_object
GLM-5 Z.ai enum "text" text | json_object
GLM-5 Subscription Z.ai enum "text" text | json_object
GLM-5-Turbo Z.ai enum "text" text | json_object
GLM-5-Turbo Subscription Z.ai enum "text" text | json_object
GLM-5.1 Z.ai enum "text" text | json_object
GLM-5.1 Subscription Z.ai enum "text" text | json_object
GLM-5.2 Z.ai enum "text" text | json_object
GLM-5.2 Subscription Z.ai enum "text" text | json_object
GLM-5.3 Z.ai enum "text" text | json_object

Models without response_format.type documented yet

These models don't list response_format.type 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.

Thinking Machines

Related output 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