Migrating to Valar

Valar speaks the OpenAI Responses and Chat Completions APIs, so moving an app from OpenAI - or any OpenAI-compatible provider - is mostly three changes: the base URL, the API key, and the model id. Your request and response shapes stay the same.

Create a Valar API key

Sign in at the Valar dashboard and create a key. Store it as VALAR_API_KEY so the OpenAI SDK and other clients pick it up.

export VALAR_API_KEY=sk_...

Point your client at Valar

Keep your existing OpenAI client. Change the base URL to https://api.valarhq.ai/v1 and pass your Valar key - Valar authenticates with Authorization: Bearer <key>.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.valarhq.ai/v1",
    api_key="YOUR_VALAR_API_KEY",
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.valarhq.ai/v1",
  apiKey: process.env.VALAR_API_KEY,
});

curl https://api.valarhq.ai/v1/responses \
  -H "Authorization: Bearer $VALAR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "moonshotai/Kimi-K2.7", "input": "Hello"}'

Switch to a Valar model

Valar serves open-weight models, so update the model field - OpenAI names like gpt-4o won’t resolve. Pick one from the Models page, such as moonshotai/Kimi-K2.7 or zai-org/GLM-5.2-FP8, and confirm availability at runtime with GET /v1/models.

Tune cost and latency (optional)

For work that doesn’t need an instant answer, set background=True and choose a completion window - standard or flex - to trade a little latency for a lower rate. See Inference modes.

What changes

	OpenAI	Valar
Base URL	`https://api.openai.com/v1`	`https://api.valarhq.ai/v1`
Auth header	`Authorization: Bearer <openai key>`	`Authorization: Bearer <valar key>`
Key env var	`OPENAI_API_KEY`	`VALAR_API_KEY`
Model id	`gpt-4o`, `o3`, …	open-weight ids from Models
Surfaces	Responses, Chat Completions	Responses, Chat Completions

A few behaviors differ from OpenAI - worth checking before you ship:

Streaming is available on Chat Completions and Messages. The Responses API rejects stream: true; for long jobs use background: true and poll or wait on webhooks. Inference modes covers the realtime / async / batch split.
Completion windows replace latency tuning. Use metadata.completion_window (asap, standard, or flex) instead of service_tier. See Pricing.
Structured outputs work the same way - text.format on Responses, or response_format on Chat Completions, with a JSON schema. See Structured outputs.
Some OpenAI-only parameters are ignored or rejected (server-side tools, conversation chaining, sampling penalties, and others). The API support matrix lists exactly what each surface accepts.

Coming from Anthropic? The OpenAI SDK works against Valar’s Responses and Chat Completions APIs, and the Anthropic SDK works against Valar’s Messages API — see Anthropic SDK & Claude Agent SDK.

Let your coding agent do it

Valar’s docs are built to be read by agents: every page has a Markdown view, the full index lives at /llms.txt, and there’s an MCP server at https://docs.valarhq.ai/mcp. Point your coding agent (Cursor, Claude Code, and the like) at the docs and hand it a prompt such as:

Migrate this project from OpenAI to Valar (https://docs.valarhq.ai).
- Change the OpenAI client base_url to https://api.valarhq.ai/v1 and read the key from VALAR_API_KEY.
- Replace OpenAI model ids with a Valar model from /models (e.g. moonshotai/Kimi-K2.7).
- Keep request and response shapes the same; flag any OpenAI-only params Valar doesn't support (see /support).

Next steps

Quickstart

Make your first Valar request.

Models

Pick a model and copy its id.

Inference modes

Realtime, async, batch, and completion windows.

Structured outputs

Get schema-constrained JSON back.

Getting started

Build agents

Run in production

ValarCode

Platform

Migrating to Valar

What changes

Let your coding agent do it

Next steps

Quickstart

Models

Inference modes

Structured outputs

​What changes

​Let your coding agent do it

​Next steps

Quickstart

Models

Inference modes

Structured outputs

What changes

Let your coding agent do it

Next steps