MiniMax H3 API: Pricing, Features & Alternatives
MiniMax H3 is a general-purpose omni-modal generative system that creates 2K video with native stereo audio from text, image, video, and audio inputs. It features 33B dense architecture, open weights, and industry-leading price-performance for AI video generation. For text LLM workloads, see MiniMax M3.
Key specifications
| Provider | MiniMax |
| Context Window | N/A (video model) |
| Max Output | 15 seconds video |
| Modalities | Text, Image, Video, Audio |
| Release Date | 2025-07 |
| Benchmark | Price per second is less than 1/3 of comparable models at 2K resolution. |
MiniMax H3 pricing
Reference pricing for MiniMax H3. Not currently available through BestLLM.
| Tier | Input (per 1M tokens) | Output (per 1M tokens) |
|---|---|---|
| 2K Video | — | $0.13/sec |
| 768P Video | — | $0.08/sec |
| 768P→2K Regen | — | $0.05/sec |
| Context-IR | $0.90 | $3.60 |
Features and capabilities
Key capabilities of MiniMax H3:`
- 2K video with native stereo audio
- 4–15 second clips at 24 FPS
- Multimodal input: text, image, video, audio
- Open weights (BF16) under Community License
- Supports 11 dialogue languages
- First-and-last-frame and reference-to-video modes
API integration example
Direct API access for MiniMax H3:
curl -X POST https://api.minimax.io/v2/video_generation \
-H "Authorization: Bearer $MINIMAX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "MiniMax-H3",
"prompt": "A sunrise over the Pacific Ocean, cinematic wide shot",
"resolution": "2K",
"duration": 10
}'Best for
AI video generation, creative content, marketing materials, and multimodal production pipelines.
Frequently asked questions
Is MiniMax H3 available through BestLLM?
MiniMax H3 is not currently available through the BestLLM API. This page is kept as a reference with pricing and specs. For production workloads, check our supported models — DeepSeek Chat, DeepSeek Reasoner, Qwen3.8 Max — which are live and accessible through the same OpenAI-compatible API.
What is the pricing for MiniMax H3?
MiniMax H3 pricing is 2K Video: / $0.13/sec output, 768P Video: / $0.08/sec output, 768P→2K Regen: / $0.05/sec output, Context-IR: $0.90 input / $3.60 output. This reflects direct provider pricing; availability through BestLLM may differ.
What should I use instead of MiniMax H3?
If you were using MiniMax H3, the closest supported alternative on BestLLM is MiniMax M3. It offers a 1M context window and is accessible through the same OpenAI-compatible API.
Need a live model instead?
BestLLM offers DeepSeek, Qwen, Kimi, GLM, and MiniMax through one OpenAI-compatible API with regional routing, spend controls, and transparent per-token billing.