Skip to content
English

Switch theme

// Google

Gemma 4 31B

A Google model. 9 prices across 9 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.

Official in/out per 1M
—
Lowest (Chutes)
$0.12 / $0.37
Context
131K
AA index
14.7

Prices checked 2026-10-22Official sources linked on every rowNo estimatesCheapest LLM APIs →

01Specs at a glance

Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.

VendorGoogle
Context window131K (131,072 tokens)
Max output66K
InputImage · Text · Video
OutputText
Tool calling / JSONYes / Yes
Weights & licenceOpen weights · Apache-2.0 · Hugging Face
Parameters31.3B (from weight files)
ReleasedApr 2, 2026
Model IDsgoogle/gemma-4-31b-it · gemma-4-31b

02Prices on 9 channels

Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.

ChannelSourceInputOutputCache hitBlended $ContextNotes
Chutes · fp4
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.12 $0.37 $0.012 0.182 131K Chutes price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against Chutes's own page
Crusoe · bf16
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.14 $0.4 $0.14 0.205 262K Crusoe price as listed on OpenRouter (pass-through; quantization=bf16; discount field=0); not checked against Crusoe's own page
Friendli · unknown
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.14 $0.4 — 0.205 262K Friendli price as listed on OpenRouter (pass-through; quantization=unknown; discount field=0); not checked against Friendli's own page
Novita · bf16
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.14 $0.4 — 0.205 262K Novita price as listed on OpenRouter (pass-through; quantization=bf16; discount field=0); not checked against Novita's own page
Parasail · fp8
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.15 $0.4 $0.06 0.212 262K Parasail price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against Parasail's own page
DeepInfra · fp8
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.2 $0.4 — 0.25 262K DeepInfra price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against DeepInfra's own page
Together
Inference platform (own price page)
Platform 10-10 $0.39 $0.97 — 0.535 262K Together AI own pricing page
SambaNova · unknown
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.38 $1.15 — 0.573 131K SambaNova price as listed on OpenRouter (pass-through; quantization=unknown; discount field=0); not checked against SambaNova's own page
SiliconFlow · fp8
Via OpenRouter / provider listed there
OpenRouter 10-22 $0.75 $1 $0.25 0.813 262K SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SiliconFlow's own page

“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.

03Where you can use it

Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.

04Performance

Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.

AA indexGemma 4 31B (Reasoning)
14.7
Output speed (median)
36 tok/s
Time to first token
1.08s
AA index per $ (blended)
80.38
BenchmarkBest scoreSourceDate
LMArena Text1452official2026-10-08
LMArena WebDev1366official2026-10-08
LMArena Vision1262official2026-10-02

05Price changes we recorded

All price changes →

From our daily re-checks of the sources above.

No price change recorded since we started tracking (2026-10-10).

06More from Google

FAQ

How much does the Gemma 4 31B API cost?

There is no official pay-as-you-go price in our data. The lowest listed price is $0.12 / $0.37 on Chutes.

What is the context window of Gemma 4 31B?

131K tokens of context, up to 66K output tokens. Platforms may cap it lower – see the table.

Is Gemma 4 31B open source?

Yes, the weights are published on Hugging Face (google/gemma-4-31B-it). Licence: Apache-2.0.

Data updated: Model API prices · HF model metadata(UTC+8)