video.minimax h3.lowvram t2v i2v
NativeOthervideo.minimax_h3.lowvram_t2v_i2v$0.005070per request, network price
−74.29%24h
$0.167324h spent
924h requests
1sellers online
1context
TrustT4✓yes: Business verified✓yes: Model checked✕no: Prompt private
Native T4
2026-10-15 04:00 UTCO $0.005070H $0.005070L $0.005070C $0.005070spent $0.005070Charts by TradingView
| Time | Tier | Buyer | Seller | Checks | Used | Price / request | Cost | Sale |
|---|---|---|---|---|---|---|---|---|
| T4 | acct…5eae | Trac Systems UG | ✓✓· | 1 requests | $0.005070 | $0.00507 | sale_88cab5093e3cbf41 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.01748 | $0.0175 | sale_65fd65ade473c0bc | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02643 | $0.0264 | sale_655acfda793329f1 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02419 | $0.0242 | sale_1362a83d77398418 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02196 | $0.0220 | sale_b3eb160c77e80e11 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.01748 | $0.0175 | sale_e8f8c1c9c87a34cc | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.01748 | $0.0175 | sale_bbcb8496b52b655b | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.01748 | $0.0175 | sale_31cf00193f4ba556 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.01972 | $0.0197 | sale_76666508257525fe | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.01972 | $0.0197 | sale_540b2f03878c12af | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02196 | $0.0220 | sale_a3dce018e123f6b8 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02196 | $0.0220 | sale_87c0db1a6ba970a2 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02448 | $0.0245 | sale_09d58911691f0722 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02448 | $0.0245 | sale_5f228119bd7f9cb2 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02225 | $0.0222 | sale_4cf17ee1f2ba1285 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.03148 | $0.0315 | sale_27abeb918e79c917 | |
| T4 | acct…4ba0 | Trac Systems UG | ✓✓· | 1 requests | $0.05477 | $0.0548 | sale_9a5ee797278b724b | |
| T4 | acct…4ba0 | Trac Systems UG | ✓✓· | 1 requests | $0.04501 | $0.0450 | sale_0a9e16756997f236 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.01748 | $0.0175 | sale_d5f6ebe5575a62b1 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.01748 | $0.0175 | sale_46b5a996da9ede35 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.01748 | $0.0175 | sale_9411780831f281d9 | |
| T4 | acct…4ba0 | Trac Systems UG | ✓✓· | 1 requests | $0.001706 | $0.00171 | sale_d976dc8dd4069edf | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02419 | $0.0242 | sale_8816e95c4755c2dd | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02867 | $0.0287 | sale_9f78c0f439b109cf | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02867 | $0.0287 | sale_70bb977174494e17 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02867 | $0.0287 | sale_ee6774d2b5197365 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02643 | $0.0264 | sale_0d29cd997a41eec0 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02419 | $0.0242 | sale_7e2f200683425e16 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02196 | $0.0220 | sale_528f6d47fee23ccd | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02196 | $0.0220 | sale_b3f36c7808b75ded | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02196 | $0.0220 | sale_b2358287fe3dd242 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02196 | $0.0220 | sale_c1799405d2f174c3 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02646 | $0.0265 | sale_fe7c21088a62777c | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02646 | $0.0265 | sale_bee6a9dbc97f87f4 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02646 | $0.0265 | sale_f435aff65c1db88d | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02762 | $0.0276 | sale_ff587883f2f2d60b | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.02762 | $0.0276 | sale_a3c33b2fd7ff1ee2 | |
| T4 | acct…bccc | Trac Systems UG | ✓✓· | 1 requests | $0.03071 | $0.0307 | sale_8ba7b00c61b3ca50 | |
| T4 | acct…bccc | Trac Systems UG | ✓✓· | 1 requests | $0.03071 | $0.0307 | sale_f0f369dfdb0b3e5f | |
| T4 | acct…bccc | Trac Systems UG | ✓✓· | 1 requests | $0.02243 | $0.0224 | sale_5066c8cf035cd237 | |
| T4 | acct…bccc | Trac Systems UG | ✓✓· | 1 requests | $0.01540 | $0.0154 | sale_bcd159c0062cefab | |
| T4 | acct…5eae | Trac Systems UG | ✓✓· | 1 requests | $0.004421 | $0.00442 | sale_0d55721b8508aa44 | |
| T4 | acct…5eae | Trac Systems UG | ✓✓· | 1 requests | $0.004421 | $0.00442 | sale_c33a8d7c28c33d6f | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.06098 | $0.0610 | sale_8b1e98601b6e7c17 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.06098 | $0.0610 | sale_85bc4d99becc3f10 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.004300 | $0.00430 | sale_3cd84a694b1af97a | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.2457 | $0.246 | sale_80377935b3acb6c9 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.2457 | $0.246 | sale_c21f6b8f47435020 | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.2457 | $0.246 | sale_677effb9ea62841e | |
| T4 | acct…4285 | Trac Systems UG | ✓✓· | 1 requests | $0.2457 | $0.246 | sale_3a5aef1044d3bbd2 |
| Tier | Seller | Checks | Status | Share of 7 days | Network price / request | Context | Pays with | Requests | Avg. latency | Last seen |
|---|---|---|---|---|---|---|---|---|---|---|
| T4 | Trac Systems UG0116fb2c…bd8b | ✓✓· | Online | 100.0% | – | 1 | tap · tnk · usd | 293 | 392 s | Oct 15 |
Performance
Measured from real, settled requests over the last 30 days. No synthetic benchmarks.
- Job duration
- 158 s
- median · p95 1,158 s · 293 requests
- Success rate
- 89.1%
- 329 finished requests, 30 days
This week: 75 requests.
Availability
Provider availability polled every minute by the platform itself, replayed hour by hour.
100% online over the last 3 days
3 days ago online down no dataNow
Usage per day
What actually ran on the platform, per day over the last 30 days. Settled usage from receipts; nothing synthetic.
Show as table
| Day | pixel-frames | Requests |
|---|---|---|
| Oct 15 | 65,617,920 | 2 |
| Oct 14 | 477,757,440 | 9 |
| Oct 13 | 863,109,120 | 16 |
| Oct 12 | 877,584,384 | 16 |
| Oct 11 | 0 | 0 |
| Oct 10 | 25,067,520 | 2 |
| Oct 9 | 106,168,320 | 3 |
| Oct 8 | 6,370,099,200 | 33 |
| Oct 7 | 2,454,233,088 | 37 |
| Oct 6 | 159,252,480 | 12 |
| Oct 5 | 159,252,480 | 3 |
| Oct 4 | 78,151,680 | 3 |
| Oct 3 | 159,252,480 | 3 |
| Oct 2 | 477,757,440 | 9 |
| Oct 1 | 3,201,245,184 | 46 |
| Sep 30 | 5,419,878,912 | 71 |
| Sep 29 | 677,044,224 | 15 |
| Sep 28 | 212,336,640 | 4 |
| Sep 27 | 226,099,200 | 2 |
| Sep 26 | 53,084,160 | 1 |
| Sep 25 | 142,909,440 | 3 |
| Sep 24 | 0 | 0 |
| Sep 23 | 1,102,970,880 | 11 |
| Sep 22 | 1,356,595,200 | 7 |
| Sep 21 | 0 | 0 |
| Sep 20 | 37,601,280 | 3 |
| Sep 19 | 25,681,920 | 1 |
| Sep 18 | 229,171,200 | 2 |
| Sep 17 | 0 | 0 |
| Sep 16 | 226,099,200 | 2 |
API
The API is OpenAI-compatible and uses the same price and sellers as shown here.
curl https://api.openmayhem.ai/v1/workflows \
-H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "video.minimax_h3.lowvram_t2v_i2v",
"workflow": {"<node-id>": {"class_type": "<allowed-node>", "inputs": {}}}
}'MCP
OpenMayhem runs its own MCP server, so Claude, Codex, Cursor and other AI apps can call this model and pay from your credit.
claude mcp add --transport http openmayhem \ https://mcp.openmayhem.ai/mcp \ --header "X-OpenMayhem-API-Key: $OPENMAYHEM_API_KEY"
Then ask your app, for example: "Use OpenMayhem video.minimax h3.lowvram t2v i2v to answer this." It calls run_workflow with video.minimax_h3.lowvram_t2v_i2v. Apps that support sign-in connect without a key, and you approve spending limits once.
Full request reference
POST /v1/workflowsWORKFLOWS · mayhem_comfy_workflows +
Working request
curl https://api.openmayhem.ai/v1/workflows \
-H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "video.minimax_h3.lowvram_t2v_i2v",
"workflow": {},
"response_format": "artifact",
"timeout_ms": 900000
}'Parameters
| Parameter | Required | Type | Default | Allowed values | Limits and shape |
|---|---|---|---|---|---|
model | Required | string | — | — | — |
workflow | Required | object | — | — | {"node-id":{"class_type":"AllowedNode","inputs":{}}} |
input_files | Optional | array | — | — | min items 1; max items 16 [{"filename":"refs/input.png","kind":"image","content_type":"image/png","encoding":"base64","data":"<BASE64_IMAGE>"}] |
outcome_class | Optional | string | — | — | min length 1; max length 128 |
response_format | Optional | string | artifact | artifact, json | {"type":"json_object"} |
runtime_id | Optional | string | — | — | min length 1; max length 128 |
timeout_ms | Optional | integer | 900000 | — | min 1000; max 3600000 |
user | Optional | string | — | — | min length 1; max length 512 |
Input shapes
input_files
{
"model": "video.minimax_h3.lowvram_t2v_i2v",
"input_files": [
{
"filename": "refs/input.png",
"kind": "image",
"content_type": "image/png",
"encoding": "base64",
"data": "<BASE64_IMAGE>"
}
]
}Jobs are asynchronous. The submit call returns a job. Poll GET /v1/jobs/{job_id}; when it succeeds, download each artifact from its artifact URL.
Workflow surface
Use the complete starter. Node roles, classes, inputs, presets and add-ons below are the values admitted for this workflow.
Complete starter request
{
"model": "video.minimax_h3.lowvram_t2v_i2v",
"workflow": {
"1": {
"class_type": "MiniMaxH3EasyLoader",
"inputs": {
"audio_vae": "minimax_h3_audio_vae_fp32.safetensors",
"fl2va_model": "minimax_h3_fl2va_pruned_w4a8_mixed.safetensors",
"ref2va_model": "None",
"text_encoder": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"video_vae": "minimax_h3_video_vae_int8_convrot.safetensors"
}
},
"2": {
"class_type": "MiniMaxH3Easy",
"inputs": {
"advanced": false,
"aspect_ratio": "9:16",
"fps": 24,
"h3_bundle": [
"1",
0
],
"height": 1280,
"keyframe_role": "first",
"mode": "image",
"prompt": "A compact cinematic product demo of a small robot chef flipping pancakes in a tiny neon diner, clear motion, native cafe ambience, no subtitles, no watermark.",
"prompt_optimizer_scene_guide": "none",
"prompt_optimizer_settings": false,
"ref_image_size": "match",
"reference_mention_mode": "index",
"resolution": "720P",
"seconds": 10,
"width": 736
}
},
"4": {
"class_type": "BasicGuider",
"inputs": {
"conditioning": [
"13",
0
],
"model": [
"27",
0
]
}
},
"5": {
"class_type": "BasicScheduler",
"inputs": {
"denoise": 1,
"model": [
"27",
0
],
"scheduler": "simple",
"steps": 4
}
},
"6": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 4242424242
}
},
"7": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
}
},
"8": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"4",
0
],
"latent_image": [
"13",
1
],
"noise": [
"6",
0
],
"sampler": [
"7",
0
],
"sigmas": [
"5",
0
]
}
},
"9": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"8",
0
],
"vae": [
"13",
2
]
}
},
"10": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"8",
1
],
"vae": [
"13",
3
]
}
},
"11": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"10",
0
],
"bit_depth": 8,
"fps": 24,
"images": [
"9",
0
]
}
},
"12": {
"class_type": "SaveVideo",
"inputs": {
"codec": "auto",
"filename_prefix": "mayhem-h3-lowvram/t2v-4step-seed4242424242",
"format": "mp4",
"video": [
"11",
0
]
}
},
"13": {
"class_type": "MiniMaxH3EasyOutput",
"inputs": {
"h3_context": [
"2",
1
]
}
},
"24": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_resized_avg_rank_21_bf16.safetensors",
"model": [
"2",
0
],
"strength_model": 1
}
},
"26": {
"class_type": "MiniMaxLowVRAMAttention",
"inputs": {
"head_chunks": 4,
"model": [
"30",
0
]
}
},
"27": {
"class_type": "MiniMaxChunkFeedForward",
"inputs": {
"chunks": 2,
"model": [
"26",
0
],
"seq_threshold": 4096
}
},
"30": {
"class_type": "MiniMaxH3SigmaShift",
"inputs": {
"model": [
"24",
0
],
"shift_audio": 3,
"shift_video": 6
}
}
},
"outcome_class": "video.minimax_h3.lowvram_t2v_i2v",
"response_format": "artifact"
}Starter with a reference file
{
"outcome_class": "video.minimax_h3.lowvram_t2v_i2v",
"response_format": "artifact",
"workflow": {
"1": {
"class_type": "MiniMaxH3EasyLoader",
"inputs": {
"audio_vae": "minimax_h3_audio_vae_fp32.safetensors",
"fl2va_model": "minimax_h3_fl2va_pruned_w4a8_mixed.safetensors",
"ref2va_model": "None",
"text_encoder": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"video_vae": "minimax_h3_video_vae_int8_convrot.safetensors"
}
},
"2": {
"class_type": "MiniMaxH3Easy",
"inputs": {
"advanced": false,
"aspect_ratio": "9:16",
"fps": 24,
"h3_bundle": [
"1",
0
],
"height": 1280,
"keyframe_role": "first",
"mode": "image",
"prompt": "Use the reference image as the main character. The character bounces forward like a playful boxer doing quick air-boxing moves, small hops, energetic motion, native room ambience, no subtitles, no watermark.",
"prompt_optimizer_scene_guide": "none",
"prompt_optimizer_settings": false,
"ref_image_size": "match",
"reference_mention_mode": "index",
"resolution": "720P",
"seconds": 10,
"width": 736,
"media": [
"29",
0
]
}
},
"4": {
"class_type": "BasicGuider",
"inputs": {
"conditioning": [
"13",
0
],
"model": [
"27",
0
]
}
},
"5": {
"class_type": "BasicScheduler",
"inputs": {
"denoise": 1,
"model": [
"27",
0
],
"scheduler": "simple",
"steps": 8
}
},
"6": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 4242424243
}
},
"7": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
}
},
"8": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"4",
0
],
"latent_image": [
"13",
1
],
"noise": [
"6",
0
],
"sampler": [
"7",
0
],
"sigmas": [
"5",
0
]
}
},
"9": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"8",
0
],
"vae": [
"13",
2
]
}
},
"10": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"8",
1
],
"vae": [
"13",
3
]
}
},
"11": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"10",
0
],
"bit_depth": 8,
"fps": 24,
"images": [
"9",
0
]
}
},
"12": {
"class_type": "SaveVideo",
"inputs": {
"codec": "auto",
"filename_prefix": "mayhem-h3-lowvram/i2v-8step-seed4242424242",
"format": "mp4",
"video": [
"11",
0
]
}
},
"13": {
"class_type": "MiniMaxH3EasyOutput",
"inputs": {
"h3_context": [
"2",
1
]
}
},
"24": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "minimax_h3_fl2v_turbo_8step_v1.0_comfyui_resized_avg_rank_21_bf16.safetensors",
"model": [
"2",
0
],
"strength_model": 1
}
},
"26": {
"class_type": "MiniMaxLowVRAMAttention",
"inputs": {
"head_chunks": 4,
"model": [
"30",
0
]
}
},
"27": {
"class_type": "MiniMaxChunkFeedForward",
"inputs": {
"chunks": 2,
"model": [
"26",
0
],
"seq_threshold": 4096
}
},
"29": {
"class_type": "LoadImage",
"inputs": {
"image": "refs/h3-lowvram-reference.png"
}
},
"30": {
"class_type": "MiniMaxH3SigmaShift",
"inputs": {
"model": [
"24",
0
],
"shift_audio": 3,
"shift_video": 6
}
}
},
"input_files": [
{
"filename": "refs/h3-lowvram-reference.png",
"kind": "image",
"content_type": "image/png",
"encoding": "base64",
"data": "$REFERENCE_FILE_BASE64"
}
]
}Direct controls
| Control | Type | Required | Default | Values and bounds |
|---|---|---|---|---|
prompt | text | Required | A compact cinematic product demo of a small robot chef flipping pancakes in a tiny neon diner, clear motion, native cafe ambience, no subtitles, no watermark. | min length 1; max length 4096 |
seconds | number | Required | 10 | min 1; max 10; step 1 |
resolution | select | Required | 720P | 360P, 416P, 480P, 540P, 640P, 720P, custom |
aspectRatio | select | Required | 9:16 | 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9 |
width | number | Required | 736 | min 256; max 1472; step 32 |
height | number | Required | 1280 | min 256; max 1280; step 32 |
seed | number | Required | 4242424242 | min 0; max 4294967295; step 1 |
Use this model through MCP
These calls use this model’s exact live request contract. First estimate the unchanged request, then pass the returned estimate ID and maximum cost to the paid tool. Read the complete MCP guide.
run_workflowWORKFLOWS +
Send this object to estimate_request. Review the result, then send the next object to the named paid tool without changing request.
estimate_request · WORKFLOWS
{
"endpoint": "WORKFLOWS",
"model": "video.minimax_h3.lowvram_t2v_i2v",
"request": {
"outcome_class": "video.minimax_h3.lowvram_t2v_i2v",
"response_format": "artifact",
"workflow": {
"1": {
"class_type": "MiniMaxH3EasyLoader",
"inputs": {
"audio_vae": "minimax_h3_audio_vae_fp32.safetensors",
"fl2va_model": "minimax_h3_fl2va_pruned_w4a8_mixed.safetensors",
"ref2va_model": "None",
"text_encoder": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"video_vae": "minimax_h3_video_vae_int8_convrot.safetensors"
}
},
"2": {
"class_type": "MiniMaxH3Easy",
"inputs": {
"advanced": false,
"aspect_ratio": "9:16",
"fps": 24,
"h3_bundle": [
"1",
0
],
"height": 1280,
"keyframe_role": "first",
"mode": "image",
"prompt": "A compact cinematic product demo of a small robot chef flipping pancakes in a tiny neon diner, clear motion, native cafe ambience, no subtitles, no watermark.",
"prompt_optimizer_scene_guide": "none",
"prompt_optimizer_settings": false,
"ref_image_size": "match",
"reference_mention_mode": "index",
"resolution": "720P",
"seconds": 10,
"width": 736
}
},
"4": {
"class_type": "BasicGuider",
"inputs": {
"conditioning": [
"13",
0
],
"model": [
"27",
0
]
}
},
"5": {
"class_type": "BasicScheduler",
"inputs": {
"denoise": 1,
"model": [
"27",
0
],
"scheduler": "simple",
"steps": 4
}
},
"6": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 4242424242
}
},
"7": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
}
},
"8": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"4",
0
],
"latent_image": [
"13",
1
],
"noise": [
"6",
0
],
"sampler": [
"7",
0
],
"sigmas": [
"5",
0
]
}
},
"9": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"8",
0
],
"vae": [
"13",
2
]
}
},
"10": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"8",
1
],
"vae": [
"13",
3
]
}
},
"11": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"10",
0
],
"bit_depth": 8,
"fps": 24,
"images": [
"9",
0
]
}
},
"12": {
"class_type": "SaveVideo",
"inputs": {
"codec": "auto",
"filename_prefix": "mayhem-h3-lowvram/t2v-4step-seed4242424242",
"format": "mp4",
"video": [
"11",
0
]
}
},
"13": {
"class_type": "MiniMaxH3EasyOutput",
"inputs": {
"h3_context": [
"2",
1
]
}
},
"24": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_resized_avg_rank_21_bf16.safetensors",
"model": [
"2",
0
],
"strength_model": 1
}
},
"26": {
"class_type": "MiniMaxLowVRAMAttention",
"inputs": {
"head_chunks": 4,
"model": [
"30",
0
]
}
},
"27": {
"class_type": "MiniMaxChunkFeedForward",
"inputs": {
"chunks": 2,
"model": [
"26",
0
],
"seq_threshold": 4096
}
},
"30": {
"class_type": "MiniMaxH3SigmaShift",
"inputs": {
"model": [
"24",
0
],
"shift_audio": 3,
"shift_video": 6
}
}
}
}
}run_workflow
{
"model": "video.minimax_h3.lowvram_t2v_i2v",
"request": {
"outcome_class": "video.minimax_h3.lowvram_t2v_i2v",
"response_format": "artifact",
"workflow": {
"1": {
"class_type": "MiniMaxH3EasyLoader",
"inputs": {
"audio_vae": "minimax_h3_audio_vae_fp32.safetensors",
"fl2va_model": "minimax_h3_fl2va_pruned_w4a8_mixed.safetensors",
"ref2va_model": "None",
"text_encoder": "qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
"video_vae": "minimax_h3_video_vae_int8_convrot.safetensors"
}
},
"2": {
"class_type": "MiniMaxH3Easy",
"inputs": {
"advanced": false,
"aspect_ratio": "9:16",
"fps": 24,
"h3_bundle": [
"1",
0
],
"height": 1280,
"keyframe_role": "first",
"mode": "image",
"prompt": "A compact cinematic product demo of a small robot chef flipping pancakes in a tiny neon diner, clear motion, native cafe ambience, no subtitles, no watermark.",
"prompt_optimizer_scene_guide": "none",
"prompt_optimizer_settings": false,
"ref_image_size": "match",
"reference_mention_mode": "index",
"resolution": "720P",
"seconds": 10,
"width": 736
}
},
"4": {
"class_type": "BasicGuider",
"inputs": {
"conditioning": [
"13",
0
],
"model": [
"27",
0
]
}
},
"5": {
"class_type": "BasicScheduler",
"inputs": {
"denoise": 1,
"model": [
"27",
0
],
"scheduler": "simple",
"steps": 4
}
},
"6": {
"class_type": "RandomNoise",
"inputs": {
"noise_seed": 4242424242
}
},
"7": {
"class_type": "KSamplerSelect",
"inputs": {
"sampler_name": "euler"
}
},
"8": {
"class_type": "SamplerCustomAdvanced",
"inputs": {
"guider": [
"4",
0
],
"latent_image": [
"13",
1
],
"noise": [
"6",
0
],
"sampler": [
"7",
0
],
"sigmas": [
"5",
0
]
}
},
"9": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"8",
0
],
"vae": [
"13",
2
]
}
},
"10": {
"class_type": "VAEDecodeAudio",
"inputs": {
"samples": [
"8",
1
],
"vae": [
"13",
3
]
}
},
"11": {
"class_type": "CreateVideo",
"inputs": {
"audio": [
"10",
0
],
"bit_depth": 8,
"fps": 24,
"images": [
"9",
0
]
}
},
"12": {
"class_type": "SaveVideo",
"inputs": {
"codec": "auto",
"filename_prefix": "mayhem-h3-lowvram/t2v-4step-seed4242424242",
"format": "mp4",
"video": [
"11",
0
]
}
},
"13": {
"class_type": "MiniMaxH3EasyOutput",
"inputs": {
"h3_context": [
"2",
1
]
}
},
"24": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"lora_name": "minimax_h3_fl2v_turbo_4step_v1.0_768p_comfyui_resized_avg_rank_21_bf16.safetensors",
"model": [
"2",
0
],
"strength_model": 1
}
},
"26": {
"class_type": "MiniMaxLowVRAMAttention",
"inputs": {
"head_chunks": 4,
"model": [
"30",
0
]
}
},
"27": {
"class_type": "MiniMaxChunkFeedForward",
"inputs": {
"chunks": 2,
"model": [
"26",
0
],
"seq_threshold": 4096
}
},
"30": {
"class_type": "MiniMaxH3SigmaShift",
"inputs": {
"model": [
"24",
0
],
"shift_audio": 3,
"shift_video": 6
}
}
}
},
"estimate_id": "<estimate_id from estimate_request>",
"max_cost_usd": "<maximum_cost_usd from estimate_request>"
}This model returns a job. Poll it until completion, then create a short-lived artifact link.
get_job
{
"job_id": "<job_id from the paid tool>"
}get_artifact
{
"artifact_id": "<artifact_id from get_job>",
"download": false
}Agent drop-ins
This is a media endpoint, so it cannot replace the text model that drives a coding agent. Call the request above from the agent’s HTTP or tool layer.
About this model
A MiniMax Hailuo 3 video workflow served as a network graph; variants cover text-to-video, image-to-video and reference-guided generation.
- Family
- comfy-minimax-h3
How it is served
- Registered tiers
- T4
- Live tiers
- T4
- Quantizations
- unknown
- Live routes
- 1
- Live providers
- 1
- Prompt processing
- Provider-visible
- Context capacity
- 1
- Concurrent requests
- 2
Routing providers
0116fb2c…bd8b
Accepted request parameters
From the network's signed model contract; anything else is rejected before a provider runs.
input_filesmodeloutcome_classresponse_formatruntime_idtimeout_msuserworkflowPrice versions
| Version | From | Until |
|---|---|---|
| v777 | 2026-10-15 05:36 UTC | current |
| v776 | 2026-10-15 04:13 UTC | 2026-10-15 05:36 UTC |
| v775 | 2026-10-15 03:14 UTC | 2026-10-15 04:13 UTC |
| v774 | 2026-10-15 02:14 UTC | 2026-10-15 03:14 UTC |
| v773 | 2026-10-15 01:13 UTC | 2026-10-15 02:14 UTC |
| v772 | 2026-10-15 00:13 UTC | 2026-10-15 01:13 UTC |
| v771 | 2026-10-14 23:13 UTC | 2026-10-15 00:13 UTC |
| v770 | 2026-10-14 22:13 UTC | 2026-10-14 23:13 UTC |
| v769 | 2026-10-14 21:13 UTC | 2026-10-14 22:13 UTC |
| v768 | 2026-10-14 20:12 UTC | 2026-10-14 21:13 UTC |
| v767 | 2026-10-14 19:13 UTC | 2026-10-14 20:12 UTC |
| v766 | 2026-10-14 18:13 UTC | 2026-10-14 19:13 UTC |
Questions and answers
What does video.minimax h3.lowvram t2v i2v cost on OpenMayhem?
video.minimax h3.lowvram t2v i2v currently costs $0.000306086 per megapixel-frame. There is no subscription: you buy credit and every request settles against a signed receipt for exactly what it used. Prices are versioned, and the full price history is published on this page.
Is video.minimax h3.lowvram t2v i2v available right now?
Yes. 1 provider serving video.minimax h3.lowvram t2v i2v right now, and it was online 100% of the last 3 days as measured by our own polling.
How do I use video.minimax h3.lowvram t2v i2v?
Send an OpenAI-compatible request to https://api.openmayhem.ai/v1/workflows with "model": "video.minimax_h3.lowvram_t2v_i2v" and your API key. Existing OpenAI SDKs work by changing the base URL. Create an account to get a key and starting credit.
Who serves video.minimax h3.lowvram t2v i2v?
Independent providers on the OpenMayhem network run the model on their own hardware. Over the last 30 days, 1 provider served it; the providers table on this page is attributed from signed receipts, not self-reporting.
Are my prompts stored?
OpenMayhem does not persist prompt or completion text. Requests are proxied to the serving provider and only billing metadata is retained: usage counts, the price applied, and the provider's signed receipt. Generated media files are stored temporarily so you can download them, then expire. The provider that serves a request necessarily processes its content.