MiniMax

Available Deals (3)Filter deals by category
Deal 1Active
Claim Deal (vercel.com)
Free MiniMax M3 API Access via Vercel AI Gateway
Free API usage
Vercel currently lists a dedicated minimax/minimax-m3-free route with free input, output, and cache pricing.
The free route is served through GMICloud and supports a 1M-token context window and up to 1M-token output.
This is separate from the standard MiniMax M3 route, which can also use paid providers, so use the -free model identifier if you specifically want this offer.
How to Claim this Deal

1. Open the MiniMax M3 Free model page (vercel.com).
2. Sign in to Vercel and create an AI Gateway API key if you do not already have one.
3. Configure your AI SDK or compatible API client to use minimax/minimax-m3-free.
4. Send requests through Vercel AI Gateway; the listed GMICloud provider currently shows free input, output, and cache usage.

Key Benefits
6 items

• Free input tokens
• Free output tokens
• Free cached tokens
• 1M-token context window
• Native image/multimodal input
• Reasoning and tool-use support

Eligibility & Requirements
How to Claim this Deal

1. Open the MiniMax M3 Free page (openrouter.ai).
2. Sign in to OpenRouter and create an API key.
3. Connect through OpenRouter's OpenAI-compatible API or a compatible application.
4. Set the model ID to minimax/:free rather than the regular paid minimax/ endpoint.
5. Send requests within OpenRouter's free-model rate limits.

Key Benefits
6 items

• $0 per 1M input tokens
• $0 per 1M output tokens
• 1,048,576-token context window
• Supports text, image, and video inputs
• Supports function/tool calling
• Supports JSON output via response_format

Eligibility & Requirements
How to Claim this Deal

1. Go to the MiniMax API Platform.
2. Create or sign in to your MiniMax developer account.
3. Create an API key and select

when making API requests.

4. Usage is charged at the currently listed discounted API rates; no The promo code is shown as necessary.

Key Benefits
6 items

• Permanent 50% off currently listed M3 API rates
• $0.30 per 1M input tokens for context up to 512K
• $1.20 per 1M output tokens for context up to 512K
• Supports up to 1M-token context
• Native image and video understanding
• Supports coding, reasoning, agentic workflows and tool use

Eligibility & Requirements

Free API usage
Vercel currently lists a dedicated minimax/minimax-m3-free route with free input, output, and cache pricing.
The free route is served through GMICloud and supports a 1M-token context window and up to 1M-token output.
This is separate from the standard MiniMax M3 route, which can also use paid providers, so use the -free model identifier if you specifically want this offer.
How to Claim this Deal

1. Open the MiniMax M3 Free model page (vercel.com).
2. Sign in to Vercel and create an AI Gateway API key if you do not already have one.
3. Configure your AI SDK or compatible API client to use minimax/minimax-m3-free.
4. Send requests through Vercel AI Gateway; the listed GMICloud provider currently shows free input, output, and cache usage.

Key Benefits

• Free input tokens
• Free output tokens
• Free cached tokens
• 1M-token context window
• Native image/multimodal input
• Reasoning and tool-use support

Free API usage
OpenRouter currently provides a free MiniMax M3 endpoint under the model ID minimax/minimax-m3:free.
Both prompt and completion tokens are priced at $0, with a 1,048,576-token context window.
The catch is that OpenRouter's free endpoints are rate limited, so this is more useful for testing, personal projects, and lighter workloads than guaranteed high-volume production use.
The free endpoint currently supports text, image, and video input, plus function calling.
How to Claim this Deal

1. Open the MiniMax M3 Free page (openrouter.ai).
2. Sign in to OpenRouter and create an API key.
3. Connect through OpenRouter's OpenAI-compatible API or a compatible application.
4. Set the model ID to minimax/minimax-m3:free rather than the regular paid minimax/minimax-m3 endpoint.
5. Send requests within OpenRouter's free-model rate limits.

Key Benefits

• $0 per 1M input tokens
• $0 per 1M output tokens
• 1,048,576-token context window
• Supports text, image, and video inputs
• Supports function/tool calling
• Supports JSON output via response_format

50% Off
MiniMax currently labels M3 API pricing as a permanent 50% discount.
For requests with up to 512K context, the listed discounted rates are $0.30 per 1M input tokens, $1.20 per 1M output tokens, and $0.06 per 1M cached-read tokens.
For 512K–1M context, those rates double to $0.60 input, $2.40 output, and $0.12 cached read.
How to Claim this Deal

1. Go to the MiniMax API Platform.
2. Create or sign in to your MiniMax developer account.
3. Create an API key and select MiniMax-M3 when making API requests.
4. Usage is charged at the currently listed discounted API rates; no The promo code is shown as necessary.

Key Benefits

• Permanent 50% off currently listed M3 API rates
• $0.30 per 1M input tokens for context up to 512K
• $1.20 per 1M output tokens for context up to 512K
• Supports up to 1M-token context
• Native image and video understanding
• Supports coding, reasoning, agentic workflows and tool use