InferIndex
Language, English, EN
Account

ProvidersAmbient

Ambient

The 6 models Ambient serves, direct and through aggregators, with the price and conditions of each offer.

Provider page We read Ambient's own price page.

No training on promptsNumber of this provider's offers whose published policy says prompts are not used for training, out of all its offers.
6 / 6 offers
Cheapest on InferIndexModels for which this provider has the lowest price on InferIndex.
2 / 6 models

Offers

AllAt the lowestAbove the lowest 3 of 6 offers
Ambient: LLM API prices
Model BlendedA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.$/1M In$/1M Out$/1M ObservationGap to the lowest price we track for this model. CtxThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut. Offer
Qwen3.6 27B (qwen/qwen3.6-27b)directfp8How finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say.https://ambient.xyz/privacy $1.04  $0.32 $3.20 2.8× Lowest on InferIndex: $0.36. 33k See pricing at Ambient (opens in a new tab)
Qwen3.6 35B A3B (qwen/qwen3.6-35b-a3b)directfp8https://ambient.xyz/privacy $0.363 $0.15 $1.00 2.3× Lowest on InferIndex: $0.158. 262k See pricing at Ambient (opens in a new tab)
Qwen3.8 27B (qwen/qwen3.8-27b)directfp8https://ambient.xyz/privacy $1.04  $0.32 $3.20 7.4× Lowest on InferIndex: $0.14. 33k See pricing at Ambient (opens in a new tab)

No training on promptsTraining terms not published

One row per offer, at its cheapest route at this provider; the other routes (hosted API, aggregators) open on the row. Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.