One API for calling
every model

Point your SDK to one base URL. Manage scoped keys, prepaid credits, model access, usage, and reliability from one Tokener.ai account.

Compatible with OpenAI & Anthropic APIs · change only the base URL

first_request.py
from openai import OpenAI

client = OpenAI(
    base_url="https://api.tokener.ai/v1",
    api_key="sk-tk-••••••••••••",
)

response = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{"role": "user", "content": "Summarize this ticket."}],
)
What you run

The control plane, not the chat window.

Keys, credits, and usage are first-class. The model call stays on your gateway — Tokener.ai owns everything around it.

Access

Scoped API keys

Create keys per app or environment. Reveal them again until revoked; disable or revoke instantly.

repeat revealrevokelast used
Credits

Prepaid, enforced

Top up credits; spend is drawn from an append-only ledger. Budget syncs to your gateway so exhausted balances stop.

ledgerbudget syncreconciled
Usage

Spend by model

Requests, tokens, and cost settle within minutes of each call — aggregated by day, model, and key.

by modelby keytabular
Catalog

Models

Explore model metadata and public prices with explicit units. Prices are billed against prepaid credits.

Get an API key
ModelCategoryContextInputCache readOutputStatus
claude-fable-5AnthropicReasoning1M$10.00$1.00$50.00Available
claude-fable-5-1AnthropicReasoning1M$10.00$0.25$50.00Available
claude-fable-5-2AnthropicReasoning1M$8.00$0.20$40.00Available
claude-haiku-4-5-20251001AnthropicReasoning200K$1.00$0.10$5.00Available
claude-haiku-5-5AnthropicReasoning1M

Input < 100,001 tokens

Input
$0.10/ 1M tokens
Cache read
$0.01/ 1M tokens
Output
$0.50/ 1M tokens

Input ≥ 100,001 tokens

Input
$0.50/ 1M tokens
Cache read
$0.05/ 1M tokens
Output
$2.50/ 1M tokens

Input counts include cached tokens. The matching range sets the prices for all input, cached input, and output tokens in the request. Prices are USD per 1M tokens.

Available
claude-opus-4-5-20251101AnthropicReasoning200K$5.00$0.50$25.00Available
claude-opus-4-6AnthropicReasoning1M$5.00$0.50$25.00Available
claude-opus-4-7AnthropicReasoning1M$5.00$0.50$25.00Available
8 models · prices in USD · billed against prepaid creditsView all models →

Cache prices are for reads of previously cached input; embedding models are priced on input only. Context is the largest input plus output window the model accepts. Prices are in USD. Prices without a unit are per 1M tokens. Speech-to-text duration and token rates are alternatives, not added together. When a model has both, this list shows its token rates and the model details show its duration rate.

Start with one endpoint

Create an account, add a key, send your first request in minutes.