Model · Google

Gemma 4 31B GRIDB4

by GooglePrices checked 1 Sep 2026

Gemma 4 31B costs $0.09 per 1M input tokens and $0.34 per 1M output tokens on the standard tier. It holds 262,144 tokens of context.On the atlas: grid B4. 6 other models share the square; the cheapest is Nemotron 3 Nano 30B A3B at $0.06 per 1M input.
Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Gemma 4 31B”. Retrieved 1 Sep 2026. https://modelsatlas.com/models/google/gemma-4-31b-it
Input / 1M
$0.09
observed We measured
Source
Our catalogue
Retrieved
1 Sep 2026

Standard tier

Output / 1M
$0.34
observed We measured
Source
Our catalogue
Retrieved
1 Sep 2026

Standard tier

Context
262K
observed We measured
Source
Our catalogue
Retrieved
17 Aug 2026
tokens

≈ 197,000 words

Offers
3 offers

1 host · standard, free, batch

Hosts and pricing

3 offers · tiers are rows, not pagesSuggest a correction
Host · tierInput / 1MOutput / 1M
Our catalogueStandardchecked 1 Sep 2026
$0.09
observed We measured
Source
Our catalogue
Retrieved
1 Sep 2026
$0.34
observed We measured
Source
Our catalogue
Retrieved
1 Sep 2026
Our catalogueFreechecked 17 Aug 2026
Free
observed We measured
Source
Our catalogue
Retrieved
17 Aug 2026
Free
observed We measured
Source
Our catalogue
Retrieved
17 Aug 2026
Our catalogueBatch · unavailablechecked 1 Sep 2026
$0.39
observed We measured
Source
Our catalogue
Retrieved
1 Sep 2026
$0.97
observed We measured
Source
Our catalogue
Retrieved
1 Sep 2026
USD per 1M tokens; each price opens its source and date. Highlighted: lowest input price among available offers. Offers marked unavailable are kept for the record and never set the headline price.
Paying too much? Models near Gemma 4 31B on the atlas.Cheaper alternatives to Gemma 4 31B →

What it costs for your workload

Estimated monthly cost$16.26
Per request$0.0005
Input / month$8
Output / month$8

Σ Derived from the standard-tier prices above. 30-day month. Excludes caching discounts.

Find a cheaper model →

Specifications

Tap src for a sourceSuggest a correction
Catalogue idgoogle-gemma-4-31b-it
CreatorGoogle
Context window262,144 tokensObserved
ModalitiesNot disclosed
LicenceNot disclosed
WeightsNot disclosed
VariantsOne (base)
Record checked2026-08-17

Capabilities

“Not disclosed” means our records do not say, not that the model lacks it.

  • Vision inputNot disclosed
  • AudioNot disclosed
  • Open weightsNot disclosed
  • Free tierOffered
  • Batch tierNone listed

We hold no data yet on tool calling, structured output or benchmark scores, so none are shown.

Cheaper alternatives to Gemma 4 31B

All 15 alternatives →
ModelGridInput / 1MOutput / 1MContext
Nemotron 3 Nano 30B A3BNVIDIAGRIDB4$0.06$0.24262KCompare
Gemma 4 26B A4BGoogleGRIDB4$0.07$0.23262KCompare
Qwen3 Coder 30B A3B InstructQwen (Alibaba)GRIDB4$0.07$0.28262KCompare
Nemotron 3 SuperNVIDIAGRIDB4$0.08$0.45262KCompare
Qwen3.5-35B-A3BQwen (Alibaba)GRIDB4$0.08$0.75262KCompare
The closest models on the atlas, not a capability match: we hold no capability data to rank by. Highlighted: lowest input price in the list.
Ranked by distance from grid B4, then price.See all 15 alternatives →

Head-to-head comparisons

Works with

Where Gemma 4 31B connects across the atlas

◆Hosts serving it

◉Tools built on it

Questions about Gemma 4 31B

How much does Gemma 4 31B cost?
On the cheapest standard-tier offer in our catalogue, input costs $0.09 per 1M tokens and output costs $0.34 per 1M tokens.
What is the Gemma 4 31B context window?
262,144 tokens, roughly 197,000 English words in one request.
Is there a free tier for Gemma 4 31B?
Yes. A free-tier offer is listed in our catalogue (Free input, Free output). Check the host's rate limits and terms before depending on it.
What is the cheapest alternative to Gemma 4 31B?
Among the models nearest it on the atlas, gpt-oss-20b is the cheapest: $0.02 per 1M input tokens, 80% less, with 131K of context.
What does grid B4 mean for Gemma 4 31B?
Grid B4 is input <$0.10 per 1M tokens with context 256K–1M. 6 other models share that square: Nemotron 3 Nano 30B A3B, Gemma 4 26B A4B, Qwen3 Coder 30B A3B Instruct and 3 more. It describes price and context, not quality.

Sources

Every number on this page, where it came from

  • Our catalogue — context window, modalities, licenceObserved · 17 Aug 2026
  • Our catalogue — prices and tiersObserved · 1 Sep 2026
  • Our calculation — grid reference, monthly cost and percentage comparisonsDerived · 1 Sep 2026

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.