Live data

Pricing

The live price list: every model and every service, read where the charge reads it.

Prices in CHF, excluding VAT. Your balance is in CHF and each request is paid from it: CHF 2.00 when you confirm your e-mail address, and more by card from the dashboard, through Stripe. No subscription. Audio, pictures and video have a fixed price per unit.

Chat models

Chat completions, completions, the Responses API and the answers of knowledge bases are counted in tokens, per model, with input and output counted separately: generating tokens costs far more than reading them. CHF per million tokens.

Model	Input (CHF / 1M tok)	Output (CHF / 1M tok)
`apertus-70b-instruct` Apertus 70B	`CHF 0.40`	`CHF 1.50`
`gemma-4-26b` Gemma 4 26B	`CHF 0.10`	`CHF 0.30`
`qwen3.6-35b` Qwen3.6 35B	`CHF 0.10`	`CHF 0.70`
`qwen3.8-27b` Qwen3.8 27B	`CHF 0.30`	`CHF 1.75`
`qwen3-coder-30b` Qwen3-Coder 30B	`CHF 0.08`	`CHF 0.40`
`ministral-3-14b` Ministral 3 14B	`CHF 0.10`	`CHF 0.20`
`qwen2.5:32b` Qwen 2.5 32B	`CHF 0.15`	`CHF 0.40`
`gpt-oss-120b` gpt-oss-120b	`CHF 0.10`	`CHF 0.40`
`qwen2.5:14b` Qwen 2.5 14B	`CHF 0.10`	`CHF 0.25`
`qwen2.5:1.5b` Qwen 2.5 1.5B	`CHF 0.02`	`CHF 0.05`

An image sent to a model that reads images becomes input tokens, at the input price of the model.

Other services

Service	Price	Notes
Embeddings `POST /v1/embeddings`	`CHF 0.02` per million input tokens	Tokens are estimated at about four characters each, the same count you see in `usage`. Multiplied by the tier.
Rerank `POST /v1/rerank`	not charged	The candidates, plus the query once for each candidate, estimated as for embeddings.
Knowledge bases: a question `POST /v1/knowledge-bases/{slug}/ask, and the app API`	the chat model's prices	The prices of the chat model that writes the answer, above: the question and the passages are its input. The search itself is not charged.
Knowledge bases: indexing a document `upload in the dashboard or the app API`	`CHF 0.02` per million tokens of text indexed	Multiplied by the tier.
Transcription `POST /v1/audio/transcriptions`	`CHF 0.00005` per second of audio an hour of audio: CHF 0.18	The duration of the file, as the engine measures it.
Speech `POST /v1/audio/speech`	`CHF 0.000005` per character of the text 1,000 characters: CHF 0.005
Pictures `POST /v1/images/generations`	`CHF 0.01` per picture delivered	With `n` above 1, each picture delivered.
Video `POST /v1/videos`	`CHF 0.02` per second of a completed clip a 5-second clip: CHF 0.10	Charged when the clip is completed.

What is not charged

A request refused before it runs: any 4xx, for a parameter, the key, a rate limit, credits, or a prompt refused by the content check.
A request that fails on our side: a 502 or a 503, a stream that breaks before its first piece of text, a video job that fails, a question to a knowledge base whose documents could not be searched or that has no document ready.
A picture or a video clip refused by the check after it was made.
A silent WAV file, answered with empty text without asking the model.

What is charged although it is incomplete: an answer cut at the token cap, with the tokens it used; a stream you close early, or that breaks after its text has started, with the tokens the engine reported or, when it did not, an estimate of about four characters per token; and with n above 1, every answer.

How a request is counted

For a request with P prompt tokens and C completion tokens, on a model with input price in and output price out per million tokens, at tier T:

cost = (P × in + C × out) / 1_000_000 × multiplier[T]

Embeddings, rerank and indexing have input tokens only. Audio, pictures and video are counted in their own units, in the table above, and the tier does not change their price. What each request cost is in your usage records, in the dashboard.

Tiers

One level for every key: 120 requests per minute on every /v1 endpoint, and no multiplier: the prices above are what you pay, whatever the tier of the request.

Dedicated capacity

For continuous workloads or guaranteed throughput we reserve capacity for your exclusive use, with absolute priority and no contention with other customers, for a monthly fee set on the model and capacity required.

Write to info@daikolab.ch for a quote.

Prices exclude VAT: Swiss VAT at 8.1% is added on the invoice from the day Daiko Lab SA is registered for VAT.