Chat completions - pre.dev

POST https://api.pre.dev/v1/chat/completions takes the OpenAI-compatible chat completion request body and returns the chat completion response. POST /v1/completions (text completions) and POST /v1/responses (Responses API shape) work the same way with their own bodies.

curl --fail-with-body -i https://api.pre.dev/v1/chat/completions \
  -H "Authorization: Bearer $PREDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "max_tokens": 200,
    "messages": [
      { "role": "system", "content": "Answer in one sentence." },
      { "role": "user", "content": "Why is the sky blue?" }
    ]
  }'

import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://api.pre.dev/v1', apiKey: process.env.PREDEV_API_KEY! });

const { data: completion, response } = await client.chat.completions
  .create({
    model: 'anthropic/claude-sonnet-5',
    max_tokens: 200,
    messages: [
      { role: 'system', content: 'Answer in one sentence.' },
      { role: 'user', content: 'Why is the sky blue?' },
    ],
  })
  .withResponse();
console.log(completion.choices[0].message.content);
console.log('credits:', response.headers.get('x-predev-credits-charged'));

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.pre.dev/v1", api_key=os.environ["PREDEV_API_KEY"])

raw = client.chat.completions.with_raw_response.create(
    model="anthropic/claude-sonnet-5",
    max_tokens=200,
    messages=[
        {"role": "system", "content": "Answer in one sentence."},
        {"role": "user", "content": "Why is the sky blue?"},
    ],
)
completion = raw.parse()
print(completion.choices[0].message.content)
print("credits:", raw.headers.get("x-predev-credits-charged"))

Request

Field	Notes
`model`	The model id exactly as listed by `GET /v1/models`, with optional `:free`, `:nitro`, `:online`, `:batch` variant
`messages`	OpenAI chat messages, including image and file content parts
`models`, `route`, `provider`, `transforms`	Routing and fallbacks
`reasoning`, `reasoning_effort`	Reasoning controls
`plugins`, `web_search_options`	Plugins and web search
`response_format`, `structured_outputs`, `tools`, `tool_choice`, `parallel_tool_calls`	Tools and structured output
`prediction`, `verbosity`, `session_id`	Passed through
`stream`, `stream_options`	Streaming; the gateway sets `stream_options.include_usage`
`user`	Set or prefixed with a workspace hash by the gateway

Every other standard field (temperature, max_tokens, stop, and so on) is forwarded to the model unchanged. Advanced options such as models, provider, reasoning, and plugins are on routing and fallbacks.

Response

The body is the standard chat completion response. usage.cost is the model’s metered cost for the call in dollars, which the charge was computed from; model is the model that served the call.

{
  "id": "gen-1757900000-abc123",
  "object": "chat.completion",
  "model": "anthropic/claude-sonnet-5",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Sunlight scatters off air molecules, and blue light scatters most." },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 21, "completion_tokens": 14, "total_tokens": 35, "cost": 0.000273 }
}

Header	Meaning
`x-predev-request-id`	`pdr_…`, the gateway’s id for this call
`x-predev-credits-charged`	Credits charged
`x-predev-credits-remaining`	Balance after the call; omitted on unlimited plans

Send x-predev-project-id: <projectId> to attribute the call to a project. See usage.

Errors

Gateway errors (401, 402, 429, 503) use the OpenAI error shape with a predev object; provider errors, such as an unknown model id, are returned with their original status and message. See errors.