All models

Gemma 4 31B IT

GoogleOpen weights262K contextVisionReasoningTool calling

Lowest price, from W&B Inference

Pricing page

Per million tokens

Input
$0.10
Output
$0.34
Cached input
—
Batch input / output
—

Estimate your monthly cost

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From W&B Inference: $1.68 a month.

Where to buy it (9)

Sorted by your monthly estimate. Prices per million tokens.

  • W&B InferenceCheapest

    Input / output
    $0.10 / $0.34
    Context
    262K
    Per month
    $1.68

    wandb/google/gemma-4-31B-it

  • DeepInfra

    Input / output
    $0.13 / $0.38
    Context
    262K
    Per month
    $2.06

    deepinfra/google/gemma-4-31B-it

  • AIHubMix

    Input / output
    $0.14 / $0.40
    Context
    262K
    Per month
    $2.20

    aihubmix/gemma-4-31b-it

  • FriendliAI

    Input / output
    $0.14 / $0.40
    Context
    262K
    Per month
    $2.20

    friendliai/google/gemma-4-31B-it

  • Novita AI

    Input / output
    $0.14 / $0.40
    Context
    262K
    Per month
    $2.20

    novita/google/gemma-4-31b-it

  • Libertai

    Input / output
    $0.15 / $0.40
    Context
    262K
    Per month
    $2.30

    libertai/gemma-4-31b-it

  • Tensormesh

    Input / output
    $0.14 / $0.56
    Context
    33K
    Per month
    $2.52

    tensormesh/google/gemma-4-31B-it

  • Sail

    Input / output
    $0.40 / $0.60
    Context
    256K
    Per month
    $5.20

    sail/google/gemma-4-31B-it

  • SambaNova

    Input / output
    $0.38 / $1.15
    Context
    131K
    Per month
    $6.10

    sambanova/gemma-4-31B-it

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Vision, Reasoning, Tool calling.

Similar models

About this data

Prices come from LiteLLM's model cost map (MIT licence), checked Oct 14, 2026; confirm on the seller's pricing page before you rely on a number.