One API key for every AI model, usually below list price.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Your MartLLM API key, sent as a Bearer token. Create one at https://martllm.com/dashboard/keys
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Your balance in US dollars: what you can spend now and what is held for requests and jobs still running.
This tool takes no arguments.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http mcp https://api.martllm.com/mcp \ --header 'Authorization: Bearer YOUR_TOKEN'
Headers
Authorization (required): Your MartLLM API key, sent as a Bearer token. Create one at https://martllm.com/dashboard/keysYour balance in US dollars: what you can spend now and what is held for requests and jobs still running.
No arguments.
{
"type": "object",
"additionalProperties": false
}Change a picture you give (image_url or input_images, as https:// links or data: URIs) following a prompt, with an editing model. Spends from your balance.
| Argument | Type | Description |
|---|---|---|
| n | integer | How many pictures, 1 to 10. Default 1. |
| size | string | Width x height, e.g. 1024x1024, when the model lists sizes. |
| model* | string | An image model id. |
| prompt* | string | What to make. |
| options | object | Any other option from get_model's parameters schema. |
| max_cost | number | The most you will pay in US dollars; a request that can cost more is refused before anything is spent. |
| image_url | string | The picture to change: an https:// link or a data: URI. |
| aspect_ratio | string | Shape, e.g. 16:9, when the model lists aspect ratios. |
| input_images | null | array | Several pictures to work from (https:// links or data: URIs). |
| return_image | boolean | Also return the pictures themselves in the answer, so you can look at them. |
{
"type": "object",
"required": [
"model",
"prompt"
],
"properties": {
"n": {
"type": "integer",
"description": "How many pictures, 1 to 10. Default 1."
},
"size": {
"type": "string",
"description": "Width x height, e.g. 1024x1024, when the model lists sizes."
},
"model": {
"type": "string",
"description": "An image model id."
},
"prompt": {
"type": "string",
"description": "What to make."
},
"options": {
"type": "object",
"description": "Any other option from get_model's parameters schema.",
"additionalProperties": true
},
"max_cost": {
"type": "number",
"description": "The most you will pay in US dollars; a request that can cost more is refused before anything is spent."
},
"image_url": {
"type": "string",
"description": "The picture to change: an https:// link or a data: URI."
},
"aspect_ratio": {
"type": "string",
"description": "Shape, e.g. 16:9, when the model lists aspect ratios."
},
"input_images": {
"type": [
"null",
"array"
],
"items": {
"type": "string"
},
"description": "Several pictures to work from (https:// links or data: URIs)."
},
"return_image": {
"type": "boolean",
"description": "Also return the pictures themselves in the answer, so you can look at them."
}
},
"additionalProperties": false
}Make pictures from a prompt. Spends from your balance; the answer carries the links and what it cost (usage.cost_usd).
| Argument | Type | Description |
|---|---|---|
| n | integer | How many pictures, 1 to 10. Default 1. |
| size | string | Width x height, e.g. 1024x1024, when the model lists sizes. |
| model* | string | An image model id. |
| prompt* | string | What to make. |
| options | object | Any other option from get_model's parameters schema. |
| max_cost | number | The most you will pay in US dollars; a request that can cost more is refused before anything is spent. |
| aspect_ratio | string | Shape, e.g. 16:9, when the model lists aspect ratios. |
| return_image | boolean | Also return the pictures themselves in the answer, so you can look at them. |
{
"type": "object",
"required": [
"model",
"prompt"
],
"properties": {
"n": {
"type": "integer",
"description": "How many pictures, 1 to 10. Default 1."
},
"size": {
"type": "string",
"description": "Width x height, e.g. 1024x1024, when the model lists sizes."
},
"model": {
"type": "string",
"description": "An image model id."
},
"prompt": {
"type": "string",
"description": "What to make."
},
"options": {
"type": "object",
"description": "Any other option from get_model's parameters schema.",
"additionalProperties": true
},
"max_cost": {
"type": "number",
"description": "The most you will pay in US dollars; a request that can cost more is refused before anything is spent."
},
"aspect_ratio": {
"type": "string",
"description": "Shape, e.g. 16:9, when the model lists aspect ratios."
},
"return_image": {
"type": "boolean",
"description": "Also return the pictures themselves in the answer, so you can look at them."
}
},
"additionalProperties": false
}The status of a video or music job, its progress and, once it succeeded, the links to its files and what it cost.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | The job id start_video returned. |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"description": "The job id start_video returned."
}
},
"additionalProperties": false
}One model: its price, what it makes and, for an image, video, music or speech model, a JSON Schema of the options a request takes (parameters).
| Argument | Type | Description |
|---|---|---|
| model* | string | The model id, e.g. bytedance/seedance-2-0-fast-image-to-video. |
{
"type": "object",
"required": [
"model"
],
"properties": {
"model": {
"type": "string",
"description": "The model id, e.g. bytedance/seedance-2-0-fast-image-to-video."
}
},
"additionalProperties": false
}Models you can call right now, with their price. Filter by type (chat, image, video, music, speech, transcription) and by words in the id or name.
| Argument | Type | Description |
|---|---|---|
| type | string | Only models of this type: chat, image, video, music, speech or transcription. |
| search | string | Only models whose id or name contains these words, e.g. seedance or kling. |
{
"type": "object",
"properties": {
"type": {
"enum": [
"chat",
"image",
"video",
"music",
"speech",
"transcription"
],
"type": "string",
"description": "Only models of this type: chat, image, video, music, speech or transcription."
},
"search": {
"type": "string",
"description": "Only models whose id or name contains these words, e.g. seedance or kling."
}
},
"additionalProperties": false
}Check an image, video, music or text-to-speech request against the model and price it, without making anything or spending. Returns the listed price (cost_usd; the bill is what the provider charges, which can be less or more) and what is held while it runs (max_cost_usd: it is never billed more).
| Argument | Type | Description |
|---|---|---|
| model* | string | The model id. |
| prompt | string | What to make. |
| options | object | The rest of the request, as get_model's parameters schema describes it, e.g. {"duration_seconds": 5, "image_url": "https://..."}. |
{
"type": "object",
"required": [
"model"
],
"properties": {
"model": {
"type": "string",
"description": "The model id."
},
"prompt": {
"type": "string",
"description": "What to make."
},
"options": {
"type": "object",
"description": "The rest of the request, as get_model's parameters schema describes it, e.g. {\"duration_seconds\": 5, \"image_url\": \"https://...\"}.",
"additionalProperties": true
}
},
"additionalProperties": false
}Start making a video. Returns a job; call wait_job with its id until it is done. Spends from your balance when the video is made; a failed job costs nothing.
| Argument | Type | Description |
|---|---|---|
| model* | string | A video model id. |
| prompt* | string | What to make. |
| options | object | Any other option from get_model's parameters schema. |
| max_cost | number | The most you will pay in US dollars; a job that can cost more is refused before anything is spent. |
| image_url | string | The first frame (https:// link or data: URI); needed by image-to-video models. |
| resolution | string | e.g. 720p, when the model lists resolutions. |
| aspect_ratio | string | e.g. 16:9, when the model lists aspect ratios. |
| end_image_url | string | The last frame, for models that make a transition. |
| idempotency_key | string | Send the same key when you retry, so a retry never starts or pays for a second video. |
Wait until a video or music job ends, for at most timeout_seconds (50 at most). Returns the job; if done is false, call wait_job again.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | The job id start_video returned. |
| timeout_seconds | integer | How long to wait, 1 to 50 seconds. Default 50. |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"description": "The job id start_video returned."
},
"timeout_seconds": {
"type": "integer",
"description": "How long to wait, 1 to 50 seconds. Default 50."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 22, 2026.
| duration_seconds | number | Length in seconds; one of the lengths get_model lists. |
{
"type": "object",
"required": [
"model",
"prompt"
],
"properties": {
"model": {
"type": "string",
"description": "A video model id."
},
"prompt": {
"type": "string",
"description": "What to make."
},
"options": {
"type": "object",
"description": "Any other option from get_model's parameters schema.",
"additionalProperties": true
},
"max_cost": {
"type": "number",
"description": "The most you will pay in US dollars; a job that can cost more is refused before anything is spent."
},
"image_url": {
"type": "string",
"description": "The first frame (https:// link or data: URI); needed by image-to-video models."
},
"resolution": {
"type": "string",
"description": "e.g. 720p, when the model lists resolutions."
},
"aspect_ratio": {
"type": "string",
"description": "e.g. 16:9, when the model lists aspect ratios."
},
"end_image_url": {
"type": "string",
"description": "The last frame, for models that make a transition."
},
"idempotency_key": {
"type": "string",
"description": "Send the same key when you retry, so a retry never starts or pays for a second video."
},
"duration_seconds": {
"type": "number",
"description": "Length in seconds; one of the lengths get_model lists."
}
},
"additionalProperties": false
}