Skip to content

Listings

All listings for Gemma 4 31B IT

Every priced listing we track for this model. Back to Gemma 4 31B IT

ProviderMax Input TokensInput $/1MOutput $/1MTok/sLatency
Run by the model's maker
 Google
models/gemma-4-31b-itSources: GenAI Prices data, Google Generative AI API data docs, LiteLLM data, Models.dev data
Data from Google Generative AI API
Fields by sourceFrom GenAI Prices: offering name, currency, unit, last updated, input tokens, output tokens, cache-read priceFrom LiteLLM: max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports system messages, supports response schema, supports reasoning, supports vision, max input tokens, max output tokensFrom Models.dev: max completion tokens, supports image input
262K$0.12cache read $0.09$0.36——
 Amazon Web Servicesbedrock_mantle/google.gemma-4-31bSources: LiteLLM data, Models.dev data
Data from LiteLLM
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, supports image input
256K$0.14batch $0.07$0.40batch $0.20——
 Aihubmixgemma-4-31b-it-free · freeSource: AIHubMix data docs
Data from AIHubMix
262K$0.00$0.00——
 Aihubmixgemma-4-31b-itSources: AIHubMix data docs, LiteLLM data
Data from AIHubMix
Fields by sourceFrom LiteLLM: max input tokens, supported output modalities, supports reasoning, supports vision, max input tokens, max output tokens
262K$0.20$0.40——
 Cortecs AIgemma-4-31b-itSources: Cortecs EU Router data, Models.dev data
Data from Cortecs EU Router
Fields by sourceFrom Models.dev: max completion tokens, supports system messages, max input tokens, max output tokens, supports image input
262K
€0.20
≈ $0.2195 USD (compared by USD value)
€0.35
≈ $0.3841 USD (compared by USD value)
——
 Fastroutergoogle/gemma-4-31b-itSources: FastRouter data, Models.dev data
Data from FastRouter
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.10$0.30——
 Flowdotgoogle/gemma-4-31b-it:free · freeSource: FlowDot data
Data from FlowDot
262K$0.00$0.00——
 Flowdotgoogle/gemma-4-31B-itSource: FlowDot data
Data from FlowDot
262K$0.20$0.40——
 Geoddgoogle/gemma-4-31B-itSource: GeoDD
Data from GeoDD
262K$0.13$0.37——
 Hugging FaceInference by Coreweavegoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$0.10$0.34——
 Hugging FaceInference by Primeintellectgoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$0.103$0.173——
 Hugging FaceInference by Venicegoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
256K$0.12$0.36——
 Hugging FaceInference by Nextbitgoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$0.125$0.34——
 Hugging FaceInference by Crusoegoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$0.14$0.40——
 Hugging Facegoogle/gemma-4-31B-itSource: Models.dev data
Data from Models.dev
262K$0.14$0.40——
 Hugging FaceInference by Novita AIgoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$0.14$0.40——
 Hugging FaceInference by Parasailgoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$0.15$0.40——
 Hugging FaceInference by DeepInfragoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$0.20$0.40——
 Hugging FaceInference by Modalgoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
131K$0.34$0.10——
 Hugging FaceInference by SambaNovagoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
131K$0.38$1.15——
 Hugging FaceInference by Modelrungoogle/gemma-4-31B-itSource: Hugging Face Inference Providers data
Data from Hugging Face Inference Providers
262K$0.75$1.00——
 Kilogoogle/gemma-4-31b-itSources: Kilo AI Gateway data, Models.dev data
Data from Kilo AI Gateway
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.10$0.34——
 Llmgatewaygemma-4-31b-itSource: LLMGateway data
Data from LLMGateway
262K$0.10cache read $0.01$0.25——
 LlmgatewayInference by Novita AIgoogle/gemma-4-31b-itSource: LLMGateway data
Data from LLMGateway
Not published by the provider$0.14$0.40——
 LlmgatewayInference by DeepInfragoogle/gemma-4-31b-itSource: LLMGateway data
Data from LLMGateway
Not published by the provider$0.20$0.40——
 LlmgatewayInference by Together AIgoogle/gemma-4-31b-itSource: LLMGateway data
Data from LLMGateway
Not published by the provider$0.39$0.97——
 LlmgatewayInference by Cerebrasgemma-4-31bSource: LLMGateway data
Data from LLMGateway
Not published by the provider$0.99$1.49——
 Meganovagoogle/gemma-4-31b-itSource: MegaNova data
Data from MegaNova
131K$0.13$0.38——
 Meliousgemma-4-31bSources: Melious API data, Melious Pricing
Data from Melious API
Fields by sourceFrom Melious Pricing: supported input modalities, supported output modalities, currency, unit, last updated, input tokens, output tokens
Not published by the provider
€0.10
≈ $0.1097 USD (compared by USD value)
€0.30
≈ $0.3292 USD (compared by USD value)
——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by Sail ResearchRegions: GLBgoogle/gemma-4-31b-it · standard · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0735cache read $0.0525$0.4234.82,944ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by Sail ResearchRegions: GLBgoogle/gemma-4-31b-it:thinking · standard, thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0735cache read $0.0525$0.4234.82,944ms
 NanoGPT
logs training unknown, per NanoGPT
Data privacy: logs_training_unknown · retains prompts Source: NanoGPT
policy notes
privacy: logs_training_unknown; distillation: License permits distillation — NanoGPT privacy policy
Inference by KitaniRegions: GLBgoogle/gemma-4-31b-it · int4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0945cache read $0.0473$0.4515——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by CreeksideRegions: GLBgoogle/gemma-4-31b-it · nvfp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0954cache read $0.0112$0.2806103.51,487ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by CreeksideRegions: GLBgoogle/gemma-4-31b-it:thinking · thinking · nvfp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.0954cache read $0.0112$0.2806102.52,375ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by RunwareRegions: UNKgoogle/gemma-4-31b-itSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.0964cache read $0.0113$0.280769.41,010ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by RunwareRegions: UNKgoogle/gemma-4-31b-it:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.0964cache read $0.0113$0.280769.41,010ms
 NanoGPTgoogle/gemma-4-31b-it:thinking · thinkingSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.10$0.34——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by AoruRegions: 🇰🇷 KRgoogle/gemma-4-31b-it · NVFP4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.105cache read $0.0525$0.4725——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by CoreweaveRegions: 🇺🇸 USgoogle/gemma-4-31b-it · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.105$0.35777.2822ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by CoreweaveRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.105$0.35735.720,316ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: License permits distillation — NanoGPT privacy policy
Inference by PrimeintellectRegions: UNKgoogle/gemma-4-31b-it · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1082cache read $0.0546$0.181730.22,038ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: License permits distillation — NanoGPT privacy policy
Inference by PrimeintellectRegions: UNKgoogle/gemma-4-31b-it:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1082cache read $0.0546$0.181719.82,086ms
 NanoGPTgoogle/gemma-4-31b-itSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.11cache read $0.05$0.33——
 NanoGPT
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
TEE/gemma4-31b:thinking · tee, thinkingSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.12cache read $0.012$0.37——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by NextbitRegions: 🇪🇺 EUgoogle/gemma-4-31b-it · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1313cache read $0.0788$0.357——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by NextbitRegions: 🇪🇺 EUgoogle/gemma-4-31b-it:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1313cache read $0.0788$0.357——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by HyperfusionRegions: 🇦🇪 AEgoogle/gemma-4-31b-it · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365$0.39939.71,444ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by HyperfusionRegions: 🇦🇪 AEgoogle/gemma-4-31b-it:thinking · thinking · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1365$0.39939.71,444ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by CrusoeRegions: 🇺🇸 USgoogle/gemma-4-31b-it · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.147$0.4257.91,270ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by CrusoeRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinking · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.147$0.4235.23,940ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by Friendli AIRegions: 🇺🇸 USgoogle/gemma-4-31b-itSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.147$0.42199.1670ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by Friendli AIRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.147$0.42199.1670ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by Novita AIRegions: 🇺🇸 USgoogle/gemma-4-31b-it · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.147$0.42110.110,599ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by Novita AIRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinking · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.147$0.4299.75,363ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by OllamaRegions: UNKgoogle/gemma-4-31b-itSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.147cache read $0.0525$0.42305.9732ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by OllamaRegions: UNKgoogle/gemma-4-31b-it:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.147cache read $0.0525$0.42305.9732ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by Sail ResearchRegions: GLBgoogle/gemma-4-31b-it · asap · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.147cache read $0.0735$0.42——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by Sail ResearchRegions: GLBgoogle/gemma-4-31b-it:thinking · asap, thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.147cache read $0.0735$0.42——
 NanoGPT
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
TEE/gemma-4-31b-it · teeSources: Models.dev data, NanoGPT
Data from NanoGPT
Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.15cache read $0.075$0.46——
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by NeuralwattRegions: 🇺🇸 USgoogle/gemma-4-31b-it · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1512cache read $0.0151$0.44167.42,442ms
 NanoGPT
no training, per NanoGPT
Data privacy: not used for training · retains prompts · no training on prompts Source: NanoGPT
policy notes
privacy: no_training; distillation: License permits distillation — NanoGPT privacy policy
Inference by NeuralwattRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1512cache read $0.0151$0.44167.42,442ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Distillation status unknown — NanoGPT privacy policy
Inference by GreenferenceRegions: 🇪🇺 EUgoogle/gemma-4-31b-it · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1559cache read $0.0606$0.44139.8402ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by ParasailRegions: 🇺🇸 USgoogle/gemma-4-31b-it · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1575cache read $0.063$0.42——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by ParasailRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.1575cache read $0.063$0.4237.74,742ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms permit output use — NanoGPT privacy policy
Inference by ArliaiRegions: 🇮🇩 IDgoogle/gemma-4-31b-itSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.189$0.189——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by DeepInfraRegions: 🇺🇸 USgoogle/gemma-4-31b-it · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.21cache read $0.021$0.4250.52,004ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by UomiRegions: GLBgoogle/gemma-4-31b-it · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.3056$0.5316——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by UomiRegions: GLBgoogle/gemma-4-31b-it:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.3056$0.5316——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by ScxRegions: GLBgoogle/gemma-4-31b-it · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.315$0.9555551.62,969ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by ScxRegions: GLBgoogle/gemma-4-31b-it:thinking · thinking · bf16Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.315$0.9555667.13,316ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by ModalRegions: 🇺🇸 USgoogle/gemma-4-31b-itSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.357cache read $0.105$0.105183.4799ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by ModalRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.357cache read $0.105$0.105367.9798ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by SambaNovaRegions: 🇺🇸 USgoogle/gemma-4-31b-itSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.399$1.2075——
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: Provider terms restrict distillation — NanoGPT privacy policy
Inference by SambaNovaRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.399$1.2075——
 NanoGPT
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
policy notes
distillation: License permits distillation — NanoGPT privacy policy
Inference by TinfoilRegions: 🇺🇸 USgoogle/gemma-4-31b-itSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.42$1.0567.13,918ms
 NanoGPT
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
policy notes
distillation: License permits distillation — NanoGPT privacy policy
Inference by TinfoilRegions: 🇺🇸 USTEE/gemma4-31b · teeSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.42$1.0567.13,918ms
 NanoGPT
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
policy notes
distillation: License permits distillation — NanoGPT privacy policy
Inference by TinfoilRegions: 🇺🇸 USTEE/gemma4-31b:thinking · tee, thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.42$1.0577.12,207ms
 NanoGPT
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
policy notes
distillation: License permits distillation — NanoGPT privacy policy
Inference by TinfoilRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinkingSource: NanoGPT
Data from NanoGPT
Not published by the provider$0.42$1.0577.12,207ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by ModelrunRegions: 🇺🇸 USgoogle/gemma-4-31b-it · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.7875cache read $0.21$1.05227684ms
 NanoGPT
zero retention, per NanoGPT
Data privacy: zero data retention · prompts not retained · no training on prompts Source: NanoGPT
policy notes
privacy: zdr; distillation: License permits distillation — NanoGPT privacy policy
Inference by ModelrunRegions: 🇺🇸 USgoogle/gemma-4-31b-it:thinking · thinking · fp4Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.7875cache read $0.21$1.05266.31,158ms
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: License permits distillation — NanoGPT privacy policy
Inference by SiliconFlowRegions: 🇸🇬 SGgoogle/gemma-4-31b-it · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.7875cache read $0.2625$1.05——
 NanoGPT
retention training unknown, per NanoGPT
Data privacy: retention_training_unknown Source: NanoGPT
policy notes
privacy: retention_training_unknown; distillation: License permits distillation — NanoGPT privacy policy
Inference by SiliconFlowRegions: 🇸🇬 SGgoogle/gemma-4-31b-it:thinking · thinking · fp8Source: NanoGPT
Data from NanoGPT
Not published by the provider$0.7875cache read $0.2625$1.05——
 Nous Portalgoogle/gemma-4-31b-itSource: Nous Portal Inference Gateway data
Data from Nous Portal Inference Gateway
262K$0.20$0.40——
 OpenRouterInference by Googlegoogle/gemma-4-31b-it:free · freeSource: OpenRouter data docs
Data from OpenRouter
262K$0.00$0.00261,372.5ms
 OpenRoutergoogle/gemma-4-31b-it:free · freeSources: Models.dev data, OpenRouter data docs
Data from OpenRouter
Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.00$0.00——
 OpenRouterInference by Coreweavegoogle/gemma-4-31b-it · fp4Source: OpenRouter data docs
Data from OpenRouter
262K$0.10$0.3462361ms
 OpenRouterInference by Ktgoogle/gemma-4-31b-itSource: OpenRouter data docs
Data from OpenRouter
262K$0.10$0.34154582ms
 OpenRouterInference by Venicegoogle/gemma-4-31b-it · fp4Source: OpenRouter data docs
Data from OpenRouter
256K$0.12cache read $0.09$0.3644587ms
 OpenRouterInference by Nextbitgoogle/gemma-4-31b-it · fp4Source: OpenRouter data docs
Data from OpenRouter
262K$0.125cache read $0.075$0.34104425.5ms
 OpenRouterInference by DeepInfragoogle/gemma-4-31b-it · turbo · fp4Source: OpenRouter data docs
Data from OpenRouter
262K$0.135cache read $0.075$0.5156347ms
 OpenRouterInference by Crusoegoogle/gemma-4-31b-it · bf16Source: OpenRouter data docs
Data from OpenRouter
262K$0.14$0.4048491ms
 OpenRouterInference by Friendli AIgoogle/gemma-4-31b-itSource: OpenRouter data docs
Data from OpenRouter
262K$0.14$0.40128328ms
 OpenRouterInference by Novita AIgoogle/gemma-4-31b-it · bf16Source: OpenRouter data docs
Data from OpenRouter
262K$0.14$0.4023781ms
 OpenRouterInference by Parasailgoogle/gemma-4-31b-it · fp8Source: OpenRouter data docs
Data from OpenRouter
262K$0.15cache read $0.06$0.40371,570ms
 OpenRouterInference by DeepInfragoogle/gemma-4-31b-it · fp8/flex · fp8Source: OpenRouter data docs
Data from OpenRouter
262K$0.16$0.32142,310ms
 OpenRouterInference by DeepInfragoogle/gemma-4-31b-it · fp8Source: OpenRouter data docs
Data from OpenRouter
262K$0.20$0.40171,166ms
 OpenRoutergoogle/gemma-4-31b-itSources: GenAI Prices data, Models.dev data, OpenRouter data docs
Data from OpenRouter
Fields by sourceFrom GenAI Prices: offering name, cache-read priceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.20cache read $0.09$0.40——
 OpenRouterInference by Primeintellectgoogle/gemma-4-31b-it · fp8Source: OpenRouter data docs
Data from OpenRouter
262K$0.20cache read $0.10$0.335201,875ms
 OpenRouterInference by DeepInfragoogle/gemma-4-31b-it · fp8/priority · fp8Source: OpenRouter data docs
Data from OpenRouter
262K$0.30$0.6020542ms
 OpenRouterInference by Modalgoogle/gemma-4-31b-itSource: OpenRouter data docs
Data from OpenRouter
131K$0.34cache read $0.10$0.1084516ms
 OpenRouterInference by Modelrungoogle/gemma-4-31b-it · fp4Source: OpenRouter data docs
Data from OpenRouter
262K$0.75cache read $0.20$1.00225133ms
 OpenRouterInference by SiliconFlowgoogle/gemma-4-31b-it · fp8Source: OpenRouter data docs
Data from OpenRouter
262K$0.75cache read $0.25$1.00341,055.5ms
 Redpill
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
google/gemma-4-31b-itSource: RedPill data
Data from RedPill
262K$0.15$0.46——
 RequestyInference by DeepInfradeepinfra/google/gemma-4-31B-itSource: Requesty data
Data from Requesty
262K$0.13$0.38——
 RequestyInference by Googlegoogle/gemma-4-31b-itSource: Requesty data
Data from Requesty
262K————
 Vercel
policy notes
AI Gateway uses zero data retention by default — Vercel AI Gateway security & compliance documentation It permanently deletes your prompts and responses after requests complete. — Vercel AI Gateway security & compliance documentation requests only route to providers with verified ZDR agreements — Vercel AI Gateway security & compliance documentation The provider allowlist lets team owners restrict which AI providers can serve requests through AI Gateway — Vercel AI Gateway security & compliance documentation Vercel may store, process and transmit your information outside of your country of residence, which may have different data protection laws and may not offer the same level of protection or guarantees as in your country or the country where you initially provided the information. — Vercel privacy policy Sources: Vercel AI Gateway security & compliance documentation, Vercel privacy policy
google/gemma-4-31b-itSources: Models.dev data, Vercel AI Gateway data
Data from Vercel AI Gateway
Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports function calling, supports system messages, max input tokens, max output tokens, supports image input
262K$0.14$0.40——
 Wavespeedgoogle/gemma-4-31b-itSource: WaveSpeed AI data
Data from WaveSpeed AI
262K$0.14cache read $0.05$0.40——
 Zenmuxgoogle/gemma-4-31b-itSource: ZenMux data
Data from ZenMux
262K$0.14$0.40——
 Abacusgoogle/gemma-4-31b-itSource: Models.dev data
Data from Models.dev
262K$0.14$0.40——
 Adaptiongemma-4-31b-itSource: Models.dev data
Data from Models.dev
256K$0.09cache read $0.05$0.34——
 Aiandgoogle/gemma-4-31b-itSource: Models.dev data
Data from Models.dev
262K$0.20cache read $0.05$0.50——
 Aimlapigoogle/gemma-4-31b-itSource: Models.dev data
Data from Models.dev
256K$1.0474$1.5764——
 Apertusgemma4-31bSource: Apertus LLM Hosting
Data from Apertus LLM Hosting
Not published by the provider
€0.20
≈ $0.2195 USD (compared by USD value)
€0.40
≈ $0.439 USD (compared by USD value)
——
 Berget AIgoogle/gemma-4-31B-it · BF16Sources: Berget AI data, Models.dev data
Data from Berget AI
Fields by sourceFrom Models.dev: context length, max completion tokens, supports reasoning, supports system messages, max input tokens, max output tokens, supports image input
128K
€0.25
≈ $0.2743 USD (compared by USD value)
€0.50
≈ $0.5487 USD (compared by USD value)
——
 Bothubgemma-4-31b-it:free · freeSource: Models.dev data
Data from Models.dev
262K$0.00$0.00——
 Cerebrascerebras/gemma-4-31b · fp16Source: LiteLLM data
Data from LiteLLM
131K$0.99$1.49——
 CrusoeGemma 4 31B · text-imageSource: Crusoe Managed Inference
Data from Crusoe Managed Inference
Not published by the provider$0.14$0.40——
 Crusoegoogle/gemma-4-31b-it · bf16Source: Models.dev data
Data from Models.dev
262K$0.14$0.40——
 DeepInfragoogle/gemma-4-31B-it · fp8Sources: DeepInfra data, LiteLLM data, Models.dev data
Data from DeepInfra
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, supports reasoning, supports vision, max input tokens, max output tokens, currency, last updated, input tokens, output tokensFrom Models.dev: max completion tokens, supports system messages, supports image input
262K$0.20$0.40——
 Digitaloceangemma-4-31B-itSource: Models.dev data
Data from Models.dev
256K$0.18cache read $0.036$0.50——
 Doublewordgoogle/gemma-4-31B-itSources: GenAI Prices data, Models.dev data
Data from GenAI Prices
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, cache-read price, cache-write price
262K$0.14cache read $0.12$0.40cache write $0.15——
 Featherless AIgoogle/gemma-4-31B-itSource: Featherless data
Data from Featherless
33K$0.12$0.36——
 FlexaiRegions: 🇪🇺 eugemma-4-31b-itSources: flex.ai API data, flex.ai Pricing
Data from flex.ai API
Fields by sourceFrom flex.ai Pricing: cache-read price
262K$0.14cache read $0.021$0.40——
 Friendli AIgoogle/gemma-4-31B-itSources: FriendliAI data, Models.dev data
Data from FriendliAI
Fields by sourceFrom Models.dev: context length, max completion tokens, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.14$0.40——
 Gmicloudgmi/google/gemma-4-31b-itSource: LiteLLM data
Data from LiteLLM
262K$0.14cache read $0.10$0.40——
 InfercomRegions: 🇪🇺 EUgemma-4-31B-itSource: Infercom data
Data from Infercom
131K
€0.20
≈ $0.2195 USD (compared by USD value)
€0.35
≈ $0.3841 USD (compared by USD value)
——
 Infomaniakgoogle/gemma-4-31B-itSource: Models.dev data
Data from Models.dev
100K$0.25$0.50——
 Ionetgoogle/gemma-4-31b-itSource: IO Intelligence (io.net) data
Data from IO Intelligence (io.net)
262K$0.349cache read $0.1745$0.6320.5891,356.38ms
 Kelngoogle/gemma-4-31b-itSource: Models.dev data
Data from Models.dev
262K$0.15$0.46——
 Libertailibertai/gemma-4-31b-itSource: LiteLLM data
Data from LiteLLM
262K$0.15$0.40——
 Libertailibertai/gemma-4-31b-it-thinking · thinkingSource: LiteLLM data
Data from LiteLLM
262K$0.15$0.40——
 Llmgateway Providersrunware/gemma-4-31b-itSource: Models.dev data
Data from Models.dev
262K$0.102cache read $0.012$0.297——
 Maragemma-4-31B-itSource: MARA data
Data from MARA
131K$0.38$1.15——
 Merge Gatewaygoogle/gemma-4-31b-itSource: Models.dev data
Data from Models.dev
262K$0.14$0.40——
 Modulargoogle/gemma-4-31b-itSource: Models.dev data
Data from Models.dev
262K$0.25cache read $0.08$0.65——
 Moneogemma-4-31b:web · webSource: Models.dev data
Data from Models.dev
256K$0.15$0.40——
 Neuralwattgemma-4-31b · fp4Sources: Models.dev data, NeuralWatt data
Data from NeuralWatt
Fields by sourceFrom Models.dev: max completion tokens, max input tokens, max output tokens, supports image input
262K$0.144cache read $0.0144$0.42——
 Nextbitgemma4:31b · fp4Source: NextBit data
Data from NextBit
262K$0.125cache read $0.075$0.34——
 Novita AIgoogle/gemma-4-31b-it · bf16Sources: LiteLLM data, Models.dev data, Novita AI data
Data from Novita AI
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports function calling, supports tool choice, supports response schema, supports reasoning, supports vision, max input tokens, max output tokensFrom Models.dev: max completion tokens, supports system messages, supports image input
262K$0.14$0.40——
 Ollamagemma4:31bSource: Models.dev data
Data from Models.dev
262K$0.14cache read $0.05$0.40——
 Oppergemma-4-31b-itSource: Models.dev data
Data from Models.dev
256K$0.4649$2.4406——
 Orcaroutergoogle/gemma-4-31b-itSource: Models.dev data
Data from Models.dev
262K$0.13cache read $0.02$0.38——
 Phala
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
google/gemma-4-31b-itSource: Models.dev data
Data from Models.dev
262K$0.15cache read $0.075$0.46——
 Powerspringgemma-4-31bSource: Models.dev data
Data from Models.dev
262K$0.2321$0.4062——
 Regologemma4-31bSources: Models.dev data, Regolo data
Data from Regolo
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports reasoning, supports system messages, max input tokens, max output tokens, supports image input
100K$0.40$0.60——
 SambaNovaRegions: globalgemma-4-31B-itSources: LiteLLM data, Models.dev data, SambaNova API data
Data from SambaNova API
Fields by sourceFrom LiteLLM: max input tokens, max output tokens, supported input modalities, supported output modalities, supports vision, max input tokens, max output tokensFrom Models.dev: supports function calling, supports reasoning, supports system messages, supports image input
131K$0.38$1.15——
 SiliconFlowgoogle/gemma-4-31B-it · fp8Sources: Models.dev data, SiliconFlow data
Data from SiliconFlow
Fields by sourceFrom Models.dev: context length, max completion tokens, supported input modalities, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input, input tokens, output tokens, cache-read price, currency, currency basis, last updated
262K$0.75cache read $0.25$1.00——
 Stepping Stonegoogle/gemma-4-31B-itSource: Models.dev data
Data from Models.dev
164K$0.2975cache read $0.0446$1.19——
 T Systemsgemma-4-31B-it-FP8 · fp8Source: T-Systems LLM Hub
Data from T-Systems LLM Hub
102K
€0.60cache read €0.09
≈ $0.6584 USD (compared by USD value)
€1.20
≈ $1.3169 USD (compared by USD value)
——
 Tensormeshgoogle/gemma-4-31B-itSources: LiteLLM data, Tensormesh data
Data from Tensormesh
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports system messages, supports response schema, supports prompt caching, supports reasoning, max input tokens, max output tokens, currency, last updated, input tokens, output tokens, cache-read price
33K$0.14$0.56——
 Tinfoil
TEE
The provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data.
gemma4-31bSources: Models.dev data, Tinfoil data
Data from Tinfoil
Fields by sourceFrom Models.dev: max completion tokens, supported input modalities, supported output modalities, supports system messages, supports vision, max input tokens, max output tokens, supports image input
262K$0.40$1.00——
 Together AIgoogle/gemma-4-31B-itSources: LiteLLM data, Together AI data
Data from Together AI
Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, max input tokens, max output tokens
262K$0.39$0.97——
 Unoroutergemma-4-31b-it:free · freeSource: Models.dev data
Data from Models.dev
262K$0.00$0.00——
 Venice
private, per Venice.ai
Data privacy: private Source: Venice.ai
policy notes
privacy classification: private — Venice privacy documentation
google-gemma-4-31b-it · fp4Source: Venice.ai data
Data from Venice.ai
256K$0.12cache read $0.09$0.36——
 Weights & Biasesgoogle/gemma-4-31B-itSources: LiteLLM data, Models.dev data, Weights & Biases Inference data
Data from Weights & Biases Inference
Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports reasoning, supports vision, max input tokens, max output tokens, currency, last updated, input tokens, output tokensFrom Models.dev: max completion tokens, supports function calling, supports system messages, supports image input, cache-read price
262K$0.10$0.34——

14 listings without a price are hidden.

Select any dotted value, label or icon to see where it comes from and how it is measured. How this data works