Pricing

ai& bills inference per token, deducted from your prepaid credit balance after each request completes. Top-up via Credits & Top-Up.

The formula

cost_usd = (input_tokens  / 1_000_000) × input_per_1m
        + (output_tokens / 1_000_000) × output_per_1m

Both input_per_1m and output_per_1m are USD per 1 million tokens, served on each model row via GET /v1/models.

Every response carries the exact computed cost:

Non-streaming: X-AiAnd-Cost-USD header. See Response Headers.
Streaming: event: aiand.metadata after the model’s terminal event. See Streaming Events.

You can also query usage and cost retrospectively via the Analytics and Request Logs endpoints.

Outcome	Charged?
2xx response with output	Yes — `(input × rate) + (output × rate)`
4xx before model dispatch (validation, auth, rate limit, no credit)	No
5xx after partial output streamed	Yes for what was billed; the cost reflects what was produced
Stream cancelled mid-flight	Yes for tokens already produced

Cost is deducted atomically when the request settles — concurrent requests can’t overdraw.

Token rates are the same across tiers. What differs is throughput — see Rate Limits for per-tier RPM/TPM caps.