Google: Gemma 4 31B
google/gemma-4-31b-it
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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
Model specifications
- Input
- text, image, video
- Output
- text
- Context
- 262,144 tokens
- Max output
- 131,072 tokens
- Input price
- $0.13 / 1M tokens
- Output price
- $0.38 / 1M tokens
- Released
- 2026-04-03
Capabilities
- Streaming
- Function calling
- Vision
- JSON mode
- Playground
Provider pricing, discounts and data privacy
Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.
Standard service tier
2 available providers · tier input average $0.14 / 1M tokens · tier output average $0.4 / 1M tokens
Novita
Tier: Standard · Region: US · Quantization: fp16
Pricing
- Input
- $0.14 / 1M tokens
- Output
- $0.4 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- Yes
- Data retention
- Zero retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Status · Support
Pearl Compute
Tier: Standard · Region: US · Quantization: int8
Pricing
- Input
- $0.14 / 1M tokens
- Output
- $0.4 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- No
- Data retention
- Unknown retention
- Used for training
- Unknown
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Priority service tier
1 available provider · tier input average $0.13 / 1M tokens · tier output average $0.38 / 1M tokens
Chutes
Tier: Priority · Region: US · Quantization: fp4
Pricing
- Input
- $0.13 / 1M tokens
- Output
- $0.38 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- No
- Data retention
- Unknown retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Support
Frequently asked questions
- What is Google: Gemma 4 31B?
- 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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
- How much does Google: Gemma 4 31B cost?
- Input costs start at $0.13 / 1M tokens and output costs start at $0.38 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of Google: Gemma 4 31B?
- Google: Gemma 4 31B supports a 262,144 token context window and up to 131,072 output tokens.
- What capabilities does Google: Gemma 4 31B support?
- Google: Gemma 4 31B supports Streaming, Function calling, Vision, JSON mode, Playground.
- Which providers offer Google: Gemma 4 31B?
- Google: Gemma 4 31B is available from Novita, Pearl Compute, Chutes.
- How do providers handle data privacy for Google: Gemma 4 31B?
- 3 of 3 providers report that customer data is not used for training, and 1 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.