MiniMax: MiniMax M3
minimax/minimax-m3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks. Trained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution.
Model specifications
- Input
- text, image, video
- Output
- text
- Context
- 1,000,000 tokens
- Max output
- 131,100 tokens
- Input price
- $0.3 / 1M tokens
- Output price
- $1.2 / 1M tokens
- Released
- 2026-06-01
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.
Flex service tier
1 available provider · tier input average $0.28 / 1M tokens · tier output average $1.1 / 1M tokens
Lilac
Tier: Flex
Pricing
- Input
- $0.28 / 1M tokens
- Output
- $1.1 / 1M tokens
- Cache read
- $0.05 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Zero data retention
- Yes
- Data retention
- Zero retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- Yes
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Standard service tier
6 available providers · tier input average $0.3 / 1M tokens · tier output average $1.2 / 1M tokens
AtlasCloud
Tier: Standard · Region: US
Pricing
- Input
- $0.3 / 1M tokens
- Output
- $1.2 / 1M tokens
- Cache read
- $0.06 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- No
- Data retention
- 7-day 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
DeepInfra
Tier: Standard · Region: US
Pricing
- Input
- $0.3 / 1M tokens
- Output
- $1.2 / 1M tokens
- Cache read
- $0.06 / 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
- Yes
- HIPAA compliant
- No
- SOC 2 certified
- Yes
- BYOK supported
- Yes
Privacy policy · Terms · Official website · Documentation · Status · Support
Fireworks
Tier: Standard · Region: US
Pricing
- Input
- $0.3 / 1M tokens
- Output
- $1.2 / 1M tokens
- Cache read
- $0.06 / 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
MiniMax
Tier: Standard · Region: SG
Pricing
- Input
- $0.3 / 1M tokens
- Output
- $1.2 / 1M tokens
- Cache read
- $0.06 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- SG
- Zero data retention
- No
- Data retention
- Unknown retention
- Used for training
- Yes
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Support
Novita
Tier: Standard · Region: US
Pricing
- Input
- $0.3 / 1M tokens
- Output
- $1.2 / 1M tokens
- Cache read
- $0.06 / 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
Together
Tier: Standard · Region: US
Pricing
- Input
- $0.3 / 1M tokens
- Output
- $1.2 / 1M tokens
- Cache read
- $0.06 / 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 · Status · Support
Frequently asked questions
- What is MiniMax: MiniMax M3?
- MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks. Trained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution.
- How much does MiniMax: MiniMax M3 cost?
- Input costs start at $0.3 / 1M tokens and output costs start at $1.2 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of MiniMax: MiniMax M3?
- MiniMax: MiniMax M3 supports a 1,000,000 token context window and up to 131,100 output tokens.
- What capabilities does MiniMax: MiniMax M3 support?
- MiniMax: MiniMax M3 supports Streaming, Function calling, Vision, JSON mode, Playground.
- Which providers offer MiniMax: MiniMax M3?
- MiniMax: MiniMax M3 is available from Lilac, AtlasCloud, DeepInfra, Fireworks, MiniMax, Novita, Together.
- How do providers handle data privacy for MiniMax: MiniMax M3?
- 7 of 7 providers report that customer data is not used for training, and 4 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.