InferIndex
Language, English, EN
Account

ProvidersBerget

Berget

The 4 models Berget serves, direct and through aggregators, with the price and conditions of each offer.

Provider page We read Berget'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.
4 / 4 offers
Cheapest on InferIndexModels for which this provider has the lowest price on InferIndex.
0 / 4 models

Offers

AllAt the lowestAbove the lowest 4 of 4 offers
Berget: 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. Offer
Gemma 4 31B (google/gemma-4-31b-it)bf16How 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. $0.349 $0.279 $0.559 2.4× Lowest on InferIndex: $0.138. See pricing at Berget (opens in a new tab)
Mistral Small 3.2 24B (mistralai/mistral-small-3.2-24b-instruct)bf16 $0.335 $0.335 $0.335 Not compared: different precision. Lowest blended: $0.106, in fp8. See pricing at Berget (opens in a new tab)
Kimi K3 (moonshotai/kimi-k3)fp4 $6.70  $3.35  $16.76  3.3× Lowest on InferIndex: $1.90. See pricing at Berget (opens in a new tab)
GLM 5.3 Flash (z-ai/glm-5.3-flash)fp8 $0.349 $0.279 $0.559 5.9× Lowest on InferIndex: $0.059. See pricing at Berget (opens in a new tab)

direct Every offer of this provider is sold directly by it.

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.