Now serving 13 models on Amazon Bedrock

The unified API for enterprise AI

Better visibility, one bill, no vendor lock-in. Give every team access to leading models through a single OpenAI-compatible endpoint.

Get API key Explore models

13: Models
7: Model labs
100%: OpenAI-compatible
0: Prompts stored

One API, every model

Swap between Nova, Llama, DeepSeek, Qwen, Mistral and more by changing a single string. Fully OpenAI-compatible.

Prepaid, predictable spend

Buy credits once, pay list price per token. Per-key limits stop runaway costs before they happen.

Bring your own key

Connect your own AWS account to unlock premium models like Claude and pay AWS directly, with unified analytics.

Usage you can explain

Every request is metered: tokens, cost, latency and key. Share exact numbers with finance, not estimates.

Enterprise by default

Accounts are provisioned by our team, prompts are never stored, and inference runs on AWS infrastructure.

Streaming built in

Server-sent events out of the box, with token usage and cost reported on the final chunk.

Drop-in replacement for the OpenAI SDK

Change the base URL and the model name. Streaming, usage and cost reporting work out of the box.

1
Get your account
Our team provisions your organization and invites your developers.
2
Add credits
Top up with a card through Stripe. Credits never expire while your account is active.
3
Create an API key
Point any OpenAI SDK at Open Token and start shipping.

index.ts

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://getopentoken.com/v1",
  apiKey: process.env.OPEN_TOKEN_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "amazon/nova-lite",
  messages: [{ role: "user", content: "What is the meaning of life?" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Featured models

Prices shown per million tokens.

View all 13 →

Amazon: Nova Pro

textimage

Highly capable multimodal model with the best balance of accuracy, speed and cost across a wide range of tasks.

amazon/nova-pro300K context$0.8/M input$3.2/M output

DeepSeek: V3.2

text

Hybrid reasoning model with sparse attention for long contexts. Strong at coding, tool use and agentic workflows.

deepseek/deepseek-v3.2128K context$0.62/M input$1.85/M output

Anthropic: Claude Sonnet 4.5

textimageBYOK

Anthropic's high-intelligence model for complex agents and coding. Available through Bring Your Own Key with your AWS account.

anthropic/claude-sonnet-4.5200K context$3/M input$15/M output

Simple, usage-based pricing

No subscriptions and no minimums. You pay provider list price for every token.

Tokens

List price

Same per-token price as the model provider. No markup on inference.

Credit top-ups

5.5% fee

Charged when you buy credits (min $0.80).

Bring your own key

5% fee

Of the list price, deducted from credits. AWS bills you directly for the rest.

Need invoicing, volume pricing or a private deployment? Talk to sales