One API. Every model. prices.
Access OpenAI, Anthropic, Google, DeepSeek and 230+ models through a single OpenAI-compatible endpoint — a cheap, pay-as-you-go alternative to OpenRouter at the cheapest prices on the market with routing, fallbacks and a free playground built in.
230+
models
Cheapest
vs list price
99.99%
uptime SLA
Supported models
Every frontier lab, one contract
Claude Fable 5.1
Anthropic
Input
$10.00/M
Output
$50.00/M
Context
1M
Claude Opus 5
Anthropic
Input
$5.00/M
Output
$25.00/M
Context
1M
GPT 6 Astra
OpenAI
Input
$10.00/M
Output
$50.00/M
Context
1M
Unified API
Drop-in OpenAI compatibility
Change two lines — baseURL and key — and every model speaks the same Chat Completions dialect. Stream, tool-call and batch exactly like you already do.
- ✓Single key for 40+ models
- ✓Streaming + tools + JSON mode
- ✓Automatic retries & fallbacks
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://newtoken.dev/v1",
apiKey: process.env.NEWTOKEN_KEY,
});
const res = await client.chat.completions.create({
model: "auto", // routed by cost, latency & quality
messages: [{ role: "user", content: "Summarize this release" }],
});Smart routing
Route by price, latency or quality. Set policies per app, fall back automatically when a provider degrades.
auto · cost < $2/M · p99 < 800ms
Usage analytics
Per-key, per-model spend and token breakdowns with daily, weekly and monthly rollups. Export anywhere.
1.2M requests · $842.10 · this week
Developer experience
Playground, request logs, evals and typed SDKs. Ship behind a stable API while labs change underneath.
⌘K palette · logs · traces
The cheapest LLM API for indie hackers
NewToken is a low-cost API for AI wrappers and side projects: one key for GPT-6, Claude, Gemini, DeepSeek, GLM, Kimi, Qwen, Grok and 230+ more models, per-token billing, up to 80% below list price. It works as a discounted OpenAI API key — keep your SDK, change the baseURL, and every chat completions call works with streaming, tools and JSON mode.
A pay-as-you-go alternative to OpenRouter
Instead of separate OpenAI, Anthropic, Google and DeepSeek accounts — or paying OpenRouter's markup — NewToken routes each request to the cheapest online upstream route automatically. Compare live GPT-6 API pricing, cheap Claude API access, Gemini 3, DeepSeek and GLM-5.3 costs per 1M tokens in the catalog, with the discount versus the official list price on every model.
Run multiple LLMs in one place, free
The free AI model playground lets you chat with every model before you integrate — temperature, reasoning effort and max-token controls, streaming responses, per-message cost. In production: per-key spend limits, route pinning, request logs, spend-by-model and latency analytics. A free tier LLM API aggregator selected models cost nothing to call.
Frequently asked questions
- What is the cheapest LLM API provider?
- NewToken is one of the cheapest LLM API providers: it routes every request to the cheapest available upstream route in real time, so you pay up to 80% below the official list price for GPT-6, Claude, Gemini 3, DeepSeek, GLM-5.3, Kimi K3, Qwen and 230+ more models — through a single OpenAI-compatible endpoint, with no platform fee.
- Can I get a discounted OpenAI API key?
- Yes. A NewToken API key works as a discounted OpenAI API key: point the OpenAI SDK's baseURL at https://newtoken.dev/v1 and your chat completions, streaming, function calling and JSON mode calls work unchanged — billed at NewToken's live per-token rates instead of OpenAI's list price.
- Where can I get cheap Claude API access?
- NewToken offers cheap Claude API access for Claude Fable 5.1, Claude Opus 5 and Claude Sonnet 5, with live per-route pricing and the discount versus Anthropic's list price shown on every model card. Top up credits, pay per token, and pin a specific route per key if you want.
- Is NewToken a cheap alternative to OpenRouter?
- Yes — NewToken is an OpenRouter alternative built for cost: automatic cheapest-route routing on every request, live price comparison with the vendor list price on every model card, per-key spend limits, and a free tier with selected models that cost nothing to try.
- Is there a free AI model playground?
- Yes. The NewToken playground lets you run multiple LLMs in one place — chat with any of the 230+ models, tune temperature, max tokens and reasoning effort, attach files, and see streaming responses with live cost per message. Selected models are completely free, so you can try before you write a line of code.
- Which AI models are available on NewToken?
- Over 230 models from OpenAI (GPT-6, GPT-5.6), Anthropic (Claude Fable 5.1, Claude Opus 5, Claude Sonnet 5), Google (Gemini 3 Pro/Flash), DeepSeek, Z.ai (GLM-5.3), Moonshot AI (Kimi K3), Alibaba (Qwen 3.8), xAI (Grok 4.6), Meta (Llama), Mistral, MiniMax, NVIDIA and more. Selected models are free.
- How does pay-as-you-go pricing work?
- NewToken is pay as you go: top up prepaid credits (crypto accepted) and you're billed per 1M input/output tokens at the live rate shown on each model. No seats, no subscriptions, no platform fee — every key has a configurable spend limit, so a leaked key can't ruin your month.