One OpenAI-compatible API. Multiple models, one key.

Drop-in OpenAI-compatible API. One key, many models.

Point your existing OpenAI SDK at a single endpoint and switch models without rewrites — USD billing, no extra accounts to set up.

Get your API key View pricing

OpenAI SDK, different base URL

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxx",
    base_url="https://api.glideflowai.com/v1",
)

r = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello"}],
)

print(r.choices[0].message.content)

Price-performance

Use the API shape you know. Pay closer to open-model economics.

The comparison below is configured data, not hard-coded page copy. Update one file when final launch prices change.

Provider	Model	Input	Output	Note
Glideflow	DeepSeek Chat	$0.14 / 1M	$0.28 / 1M	Launch placeholder
Glideflow	DeepSeek Reasoner	$0.55 / 1M	$2.19 / 1M	Launch placeholder
OpenAI	GPT-5.5	$1.75 / 1M	$14 / 1M	Public list price
Anthropic	Claude Sonnet 4.6	$3 / 1M	$15 / 1M	Public list price
Google	Gemini 2.5 Pro	$1.25 / 1M	$10 / 1M	Public list price, lower context tier

Models

A focused model menu for everyday builders.

Start with deepseek-chat, then switch models without changing SDKs.

Coding and general chat

DeepSeek Chat

deepseek-chat

A strong default for coding help, chat workflows, and everyday product features.

Input: $0.14
Output: $0.28

Reasoning and debugging

DeepSeek Reasoner

deepseek-reasoner

Step-by-step reasoning for debugging, planning, and harder multi-step tasks.

Input: $0.55
Output: $2.19

Multilingual apps

Qwen Max

qwen-max

A capable multilingual model for larger prompts and polished product experiences.

Input: $0.40
Output: $1.20

Low-cost volume

GLM-4

glm-4

A practical low-cost option for prototypes, agents, and high-volume background jobs.

Input: $0.20
Output: $0.60

Quick start

Change the base URL. Keep the rest.

Glideflow follows the OpenAI request shape for chat completions and model listing. Point your existing client at https://api.glideflowai.com/v1.

curl https://api.glideflowai.com/v1/chat/completions \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-chat",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxx",
    base_url="https://api.glideflowai.com/v1",
)

r = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello"}],
)

print(r.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-xxx",
  baseURL: "https://api.glideflowai.com/v1",
});

const r = await client.chat.completions.create({
  model: "deepseek-chat",
  messages: [{ role: "user", content: "Hello" }],
});

console.log(r.choices[0].message.content);

Pricing

USD per million tokens, by model.

Final launch prices can be replaced in config without touching page markup.

Model	Best for	Input	Output
DeepSeek Chat`deepseek-chat`	Coding and general chat	$0.14 / 1M tokens	$0.28 / 1M tokens
DeepSeek Reasoner`deepseek-reasoner`	Reasoning and debugging	$0.55 / 1M tokens	$2.19 / 1M tokens
Qwen Max`qwen-max`	Multilingual apps	$0.40 / 1M tokens	$1.20 / 1M tokens
GLM-4`glm-4`	Low-cost volume	$0.20 / 1M tokens	$0.60 / 1M tokens

Data & privacy

Clear about the path your requests take.

Glideflow is for developers who value cost and compatibility, and who can choose what data is appropriate for third-party model routing.

Transparent routing

Requests are received by the Glideflow gateway, authenticated, metered, and forwarded to the selected upstream model provider.

Built for indie workloads

Use it for prototypes, coding tools, side projects, and early products where practical cost matters more than enterprise procurement.

Not for regulated data

Do not send medical, financial, government, or other regulated enterprise data unless your own review approves the full provider chain.

FAQ

Straight answers before you switch traffic.

How does the pricing compare?+

Glideflow routes OpenAI-compatible calls to efficient DeepSeek, Qwen, and GLM models, so you keep the familiar API shape while paying closer to open-model economics. See the pricing and comparison tables for current numbers.

Is my data safe?+

Your request passes through our gateway and then to the upstream model provider you choose. That data flow is intentional and documented so you can decide what belongs here.

How do payments work?+

Payments are not live in this static site yet. The planned flow is card payment or redeemable credit codes, with no Chinese phone number, Alipay account, or local identity flow required.

How is this different from OpenRouter?+

Glideflow is narrower by design: a small set of high-value Chinese and open models, OpenAI-compatible endpoints, USD billing, and copy-paste setup for independent developers.

Which SDKs are supported?+

Any OpenAI-compatible client should work. The docs show curl, the official Python openai SDK, and the official Node openai SDK.