Models/Google/Gemma 4 31B

Gemma 4 31B

Name: Gemma 4 31B API access
Brand: Google

Google · Open weights · Released Apr 2, 2026 · google/gemma-4-31b-it

Compare Estimate cost

262K contextVisionToolsReasoningStructured outputPrompt cachingOpen weights

Available from 18 providersUSD / MTOK · VERIFIED 12 HOURS AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	SMOKE	UPTIME
OPOpenInference	$0.08	$0.35	$0.01	262K	bf16	2.3s	21 tok/s	4/5	98.0%
DeepInfradeepinfra/turbo	$0.09	$0.34	$0.05	262K	fp4	0.84s	56 tok/s	5/5	99.9%
CWCoreWeave	$0.10	$0.34	$0.10	262K	bf16	1.6s	38 tok/s	5/5	98.3%
Venice	$0.12	$0.36	$0.09	256K	bf16	1.5s	81 tok/s	5/5	99.7%
CHChutes	$0.12	$0.37	$0.012	131K	fp4	9s	30 tok/s	5/5	96.5%
DeepInfradeepinfra/fp8	$0.13	$0.38	—	262K	fp8	—	—	—	99.3%
SiliconFlow	$0.13	$0.40	—	262K	fp8	2.7s	82 tok/s	5/5	83.4%
Crusoe	$0.14	$0.40	$0.14	262K	—	1.3s	62 tok/s	—	99.4%
Friendli	$0.14	$0.40	—	262K	—	2.3s	95 tok/s	—	99.8%
Novita	$0.14	$0.40	—	262K	bf16	1.2s	37 tok/s	—	98.5%
Parasail	$0.15	$0.40	$0.06	262K	fp8	1.4s	91 tok/s	—	99.6%
PHPhala	$0.15	$0.46	$0.075	262K	—	1.2s	104 tok/s	—	99.4%
DeepInfradeepinfra/ultra	$0.27	$0.76	—	131K	fp8	—	—	—	99.4%
Togethertogether	$0.28	$0.86	—	262K	—	2.2s	25 tok/s	—	95.0%
SambaNova	$0.38	$1.15	—	131K	—	2.2s	200 tok/s	—	100.0%
Togethertogether	$0.39	$0.97	—	262K	—	—	—	—	98.9%
MOModelRun	$0.75	$1.00	$0.75	262K	fp4	0.31s	205 tok/s	—	100.0%
Cerebras	$0.99	$1.49	$0.99	131K	fp16	0.43s	665 tok/s	—	99.9%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.1 · methodology v1.1 · measured 43 hours ago

Pricing variants · USD / MTok in / out

STANDARD

$0.08 / $0.35

per MTok in / out

FREE

Free / Free

per MTok in / out

CACHE READ $0.01

About

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Specifications

Context window262,144

Max output262,144

Modalities inimage, text, video

Modalities outtext

LicenseOpen weights

ReleasedApr 2, 2026

TokenizerGemma

WeightsHugging Face ↗

Open weights

Hugging Facegoogle/gemma-4-31B-it ↗

Downloads8.8M

Likes3.6K

Licenseapache-2.0

safetensors

Gemini 3.7 Flash$0.188 / $0.938 Gemini 3.6 Flash$0.375 / $1.88 Gemini 3.5 Flash Lite$0.15 / $1.25 Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)$0.25 / $1.50

Embed badge

[![Gemma 4 31B](https://modelindex.ai/badge/google/gemma-4-31b-it)](https://modelindex.ai/models/google/gemma-4-31b-it)

Sources

OpenRouter API12 hours ago

AGGREGATOR

Hugging Face12 hours ago

COMMUNITY

ModelIndex benchmarks43 hours ago

MEASURED

Verified 12 hours ago · list prices, not negotiated rates.