MiniMax H3
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsMiniMax H3
AI model Released
- API mode
- Video generation*
- Open weights
- Yes
No matched benchmark results are available for this entry yet.
Run it locally
Capabilities
- Reasoning
- No
- Tool calling
- No
- Open weights
- Yes
- API mode
- Video generation*
- Model license
- MiniMax H3 Community License Agreement
Input modalities
- text
- image
- video
- audio
Output modalities
- video
- audio
System configuration
Detailed specifications
Specifications · 11 fields
- input cost per image
- 0.04*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- litellm provider
- minimax*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- metadata
- comment
- V2 async task API. Pay-as-you-go list price $0.08/s at 768P and $0.13/s at 2K, plus $0.04 per input image beyond the first 5. Audio input is free. Reference video input is rejected, since MiniMax bills its duration only after the create call.*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- mode
- video_generation*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per second
- 0.08*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per second 2k
- 0.13*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- output cost per second 768p
- 0.08*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- provider specific entry
- minimax_free_input_images
- 5*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supported endpoints
- /v1/videos*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supported modalities
- text*
- image*
- audio*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
- supported output modalities
- video*
Scope and conditions
- native_context
- provider
- minimax*
- mode
- video_generation*
- full_native_model_id
- minimax/MiniMax-H3*
- pricing_scope
- Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
0 selected Compare 0
* Provisional data