Tokenless
50% of provider list price

A cheaper OpenRouter alternative

If you use a router to reach many models with one key, Tokenless does the same with frontier Claude and GPT, but bills every token at 50% of the provider's list price instead of passing list price through with a markup.

Frontier models at 50% of list

ModelInput / 1MOutput / 1MContext
Claude Fable 5Anthropic$5.00 $10.00$25.00 $50.001,000,000
GPT-5.6 SolOpenAI$2.50 $5.00$15.00 $30.001,000,000
GPT-5.6 TerraOpenAI$1.25 $2.50$7.50 $15.00400,000
GPT-5.6 LunaOpenAI$0.50 $1.00$3.00 $6.00400,000
Claude Sonnet 5Anthropic$1.50 $3.00$7.50 $15.001,000,000
GPT-5.5OpenAI$2.50 $5.00$15.00 $30.001,000,000
GPT-5.5 ProOpenAI$15.00 $30.00$90.00 $180.001,000,000
Claude Opus 4.8Anthropic$2.50 $5.00$12.50 $25.001,000,000
GPT-5.4OpenAI$1.25 $2.50$7.50 $15.00400,000
GPT-5.4 ProOpenAI$15.00 $30.00$90.00 $180.00400,000
GPT-5.4 miniOpenAI$0.38 $0.75$2.25 $4.50400,000
GPT-5.4 nanoOpenAI$0.10 $0.20$0.63 $1.25200,000
Claude Opus 4.7Anthropic$2.50 $5.00$12.50 $25.001,000,000
GPT-5.3 CodexOpenAI$0.88 $1.75$7.00 $14.00400,000
Claude Opus 4.6Anthropic$2.50 $5.00$12.50 $25.001,000,000
Claude Sonnet 4.6Anthropic$1.50 $3.00$7.50 $15.001,000,000
Claude Haiku 4.5Anthropic$0.50 $1.00$2.50 $5.00200,000
Gemini 3.1 ProGoogle$1.00 $2.00$6.00 $12.001,000,000
Gemini 3.5 FlashGoogle$0.25 $0.50$1.75 $3.501,000,000
Gemini 3.1 Flash-LiteGoogle$0.08 $0.15$0.30 $0.601,000,000
Gemini 2.5 ProGoogle$0.63 $1.25$5.00 $10.001,000,000
Gemini 2.5 FlashGoogle$0.15 $0.30$1.25 $2.501,000,000
Gemini 2.5 Flash-LiteGoogle$0.05 $0.10$0.20 $0.401,000,000

Prices are USD per million tokens. Struck-through figures are the provider's official list price; the bold figure is the Tokenless rate at 50% of list.

Drop in, change one line

Tokenless is OpenAI-compatible. Keep your existing SDK and code, swap the base URL, and every request bills at half of list price. The same key reaches every Claude and GPT model.

quickstart.py
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_TOKENLESS_KEY",
    base_url="https://api.tokenless.store/api/v1",  # the only line you change
)

resp = client.chat.completions.create(
    model="opus-4.8",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Frequently asked

How is Tokenless different from a model router?

Both give you one key and one OpenAI-compatible endpoint for many models. The difference is price: Tokenless charges 50% of the provider's list price per token rather than passing list price through with an added margin.

Which models are available?

The frontier Claude and GPT families, including Claude Fable 5, Opus 4.8, and Sonnet, plus the GPT-5.6, GPT-5.5, and GPT-5.4 lines. See the full list on the models page.

Do I need to change my code?

No. Tokenless is OpenAI-compatible. Point your existing SDK at the Tokenless base URL and keep your requests as they are.

Are my prompts logged?

No. Tokenless does not log prompts or completions and does not use your data for training. Keys are hashed at rest.

Is billing prepaid?

Yes. You prepay a balance and draw it down per token. Requests stop at zero balance, so there is no debt. Your first $1 is free.

Ship the same work for half the cost

Create a key, add the base URL, and your first $1 of usage is free. No subscription, no minimums.