MiniMax's flagship H3 video model with native synchronized audio, supporting text-to-video and first/last-frame image-to-video from 4 to 15 seconds at 768p or 2K.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.
MiniMax's flagship H3 video model with native synchronized audio, supporting text-to-video and first/last-frame image-to-video from 4 to 15 seconds at 768p or 2K. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for MiniMax H3 on LLM Gateway starts at $0.00 per million input tokens and $0.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
MiniMax H3 supports a context window of up to 7,000 tokens on its largest provider deployment.
MiniMax H3 is served by MiniMax through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
No. MiniMax H3 does not currently support tool calling or structured JSON outputs through LLM Gateway.
MiniMax H3 was released on September 8, 2026.
MiniMax M3.1 Flash
1,048,576 context$0.10 in / $0.50 out per 1M
MiniMax H3 Max
7,000 context$0.00 in / $0.00 out per 1M
MiniMax M3
1,000,000 context$0.28 in / $1.10 out per 1M
MiniMax M2.7 Highspeed
204,800 context$0.60 in / $2.40 out per 1M
MiniMax M2.7
204,800 context$0.30 in / $1.20 out per 1M
MiniMax M2.5 Highspeed
204,800 context$0.60 in / $2.40 out per 1M