Models

The gateway serves hundreds of models from every major lab. Use the model id exactly as listed by GET /v1/models: if the catalog lists it, model: "<author>/<slug>" works here.

Example id	Author
`anthropic/claude-sonnet-5`	Anthropic
`deepseek/deepseek-v4.1-flash`	DeepSeek
`google/gemini-3.8-flash`	Google
`openai/gpt-5.6-luna`	OpenAI

Variant suffixes are accepted: deepseek/deepseek-v4.1-flash:free, anthropic/claude-sonnet-5:nitro, google/gemini-3.8-flash:online, openai/gpt-5.6-luna:batch. :free variants are rate-limited and may train on prompts; :nitro is shorthand for throughput-sorted provider routing and :online for the web search plugin. See routing and fallbacks.

List models with prices

curl --fail-with-body https://api.pre.dev/v1/models \
  -H "Authorization: Bearer $PREDEV_API_KEY"

Each row describes the model (id, name, context_length, dollar pricing, and so on) and carries a predev object with its prices in credits:

{
  "id": "deepseek/deepseek-v4.1-flash",
  "name": "DeepSeek V4.1 Flash",
  "context_length": 262144,
  "pricing": { "prompt": "0.0000002", "completion": "0.0000008" },
  "predev": {
    "credits_per_m_input": 2.86,
    "credits_per_m_output": 11.43
  }
}

`predev` field	Present when
`credits_per_m_input`	Always
`credits_per_m_output`	Always
`credits_per_m_cache_read`	The model prices cache reads
`credits_per_m_cache_write`	The model prices cache writes
`credits_per_image`	The model prices image inputs
`credits_per_request`	The model has a per-request price

The catalog refreshes every 15 minutes. The x-predev-catalog-age response header reports seconds since the last refresh. Catalog reads are free and not rate-limited. Other catalog endpoints: /v1/models/count, /v1/models/{author}/{slug}/endpoints for the providers behind one model, /v1/embeddings/models, /v1/images/models, /v1/videos/models, and /v1/providers. See the catalog reference.

Pick a model in code

Filter the catalog rather than hard-coding assumptions about price or context length:

const response = await fetch('https://api.pre.dev/v1/models', {
  headers: { Authorization: `Bearer ${process.env.PREDEV_API_KEY}` },
});
const { data } = await response.json();
const cheapest = data
  .filter((m: any) => m.context_length >= 128000)
  .sort((a: any, b: any) => a.predev.credits_per_m_output - b.predev.credits_per_m_output)[0];
console.log(cheapest.id, cheapest.predev);

import os
import requests

rows = requests.get(
    "https://api.pre.dev/v1/models",
    headers={"Authorization": f"Bearer {os.environ['PREDEV_API_KEY']}"},
).json()["data"]
cheapest = min(
    (m for m in rows if m["context_length"] >= 128000),
    key=lambda m: m["predev"]["credits_per_m_output"],
)
print(cheapest["id"], cheapest["predev"])

Invalid ids

An id the catalog does not recognize returns the provider’s error with its original status and message; the gateway does not rewrite it. See errors. Send several ids in models to fall back automatically. See routing and fallbacks.

Get started

Guides

API reference

List models with prices

Pick a model in code

Invalid ids

​List models with prices

​Pick a model in code

​Invalid ids

List models with prices

Pick a model in code

Invalid ids