modelparams.dev
API GitHub

Providers

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

Providers

Alibaba Anthropic Cerebras Cohere DeepSeek Google Groq Meta MiniMax Mistral Moonshot AI NVIDIA OpenAI Perplexity Thinking Machines xAI Xiaomi Z.ai
Mistral 9 params

Mistral Codestral 2508 API parameters

These are the API parameters modelparams.dev tracks for Mistral Codestral 2508 — 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 Codestral 2508 has? That's a different number, and we don't track it. Here's the difference.

Length 2 params
Parameter Type Default Description Condition
Max tokens
max_tokens 		integer (1…+∞) — Maximum number of tokens to generate in the completion. —
Stop sequence
stop 		string — Stops generation when this string is detected. —
Sampling 5 params
Parameter Type Default Description Condition
Temperature
temperature 		number (0…1.5 step 0.1) — 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 within the selected cumulative probability. —
Random seed
random_seed 		integer (0…+∞) — Seed used for deterministic sampling when reproducible outputs are desired. —
Presence penalty
presence_penalty 		number (-2…2 step 0.1) 0 Penalizes repeated words or phrases to encourage a wider variety of generated content. —
Frequency penalty
frequency_penalty 		number (-2…2 step 0.1) 0 Penalizes words based on how often they already appear in the generated text. —
Output 1 param
Parameter Type Default Description Condition
Response format
response_format.type 		enum (text | json_object) "text" Controls whether the model returns normal text or JSON mode output. —
Metadata 1 param
Parameter Type Default Description Condition
Safe prompt
safe_prompt 		boolean false Controls whether Mistral injects its safety prompt before the conversation. —

Mistral Codestral 2508 API parameters in brief

Mistral Codestral 2508 documents 9 API parameters, grouped by what they control:

Frequently asked questions

Which API parameters does Mistral Codestral 2508 support?
Mistral Codestral 2508 accepts 9 API parameters in the request body: max_tokens, stop, temperature, top_p, random_seed, presence_penalty, and more.
What is the default top_p for Mistral Codestral 2508?
The default top_p for Mistral Codestral 2508 is 1, within a valid range of 0 to 1.

Resources

All Mistral models Glossary Full catalog

Codestral 2508 — JSON

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

/api/v1/models/mistral/codestral-2508.json 
{
  "$schema": "https://modelparams.dev/api/v1/schema.json",
  "provider": "mistral",
  "authType": "api_key",
  "model": "codestral-2508",
  "params": [
    {
      "path": "max_tokens",
      "label": "Max tokens",
      "description": "Maximum number of tokens to generate in the completion.",
      "group": "generation_length",
      "type": "integer",
      "range": {
        "min": 1
      }
    },
    {
      "path": "stop",
      "label": "Stop sequence",
      "description": "Stops generation when this string is detected.",
      "group": "generation_length",
      "type": "string"
    },
    {
      "path": "temperature",
      "label": "Temperature",
      "description": "Controls randomness. Lower values make outputs more focused; higher values make them more varied.",
      "group": "sampling",
      "type": "number",
      "range": {
        "min": 0,
        "max": 1.5,
        "step": 0.1
      }
    },
    {
      "path": "top_p",
      "label": "Top P",
      "description": "Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.",
      "group": "sampling",
      "type": "number",
      "default": 1,
      "range": {
        "min": 0,
        "max": 1,
        "step": 0.01
      }
    },
    {
      "path": "random_seed",
      "label": "Random seed",
      "description": "Seed used for deterministic sampling when reproducible outputs are desired.",
      "group": "sampling",
      "type": "integer",
      "range": {
        "min": 0
      }
    },
    {
      "path": "presence_penalty",
      "label": "Presence penalty",
      "description": "Penalizes repeated words or phrases to encourage a wider variety of generated content.",
      "group": "sampling",
      "type": "number",
      "default": 0,
      "range": {
        "min": -2,
        "max": 2,
        "step": 0.1
      }
    },
    {
      "path": "frequency_penalty",
      "label": "Frequency penalty",
      "description": "Penalizes words based on how often they already appear in the generated text.",
      "group": "sampling",
      "type": "number",
      "default": 0,
      "range": {
        "min": -2,
        "max": 2,
        "step": 0.1
      }
    },
    {
      "path": "response_format.type",
      "label": "Response format",
      "description": "Controls whether the model returns normal text or JSON mode output.",
      "group": "output_format",
      "type": "enum",
      "default": "text",
      "values": [
        "text",
        "json_object"
      ]
    },
    {
      "path": "safe_prompt",
      "label": "Safe prompt",
      "description": "Controls whether Mistral injects its safety prompt before the conversation.",
      "group": "provider_metadata",
      "type": "boolean",
      "default": false
    }
  ]
}

Other Mistral models

Codestral Latest 9 params View Devstral 2512 9 params View Devstral Latest 9 params View Magistral Medium Latest 10 params View Magistral Small Latest 10 params View Ministral 14B Latest 9 params View Ministral 3B Latest 9 params View Ministral 8B Latest 9 params View Mistral Large Latest 9 params View Mistral Medium 3.5 9 params View Mistral Medium Latest 9 params View Mistral NeMo 9 params View Mistral Small Latest 9 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