DeepInfra MCP by usefulapi is an MCP server published by io.usefulapi, hosted at deepinfra.usefulapi.io. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 18 tools, including deepinfra_get_account, deepinfra_get_rate_limit, deepinfra_list_api_tokens, deepinfra_get_usage, deepinfra_get_usage_tokens.
Run DeepInfra inference, list models and read account rate limits.
4,303 connections through 5 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Get the current DeepInfra account / user details (identity, email, quotas). DeepInfra REST: GET /v1/me.
| Parameter | Type | Description |
|---|---|---|
| checklist | boolean | Include the onboarding checklist state in the response. |
{
"name": "deepinfra_get_account",
"title": "Get account",
"description": "Get the current DeepInfra account / user details (identity, email, quotas). DeepInfra REST: GET /v1/me.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"checklist": {
"type": "boolean",
"description": "Include the onboarding checklist state in the response."
}
}
},
"annotations": {
"title": "Get account",
"readOnlyHint": true
}
}Get the account's current rate limits (per-model / per-endpoint request and token limits). DeepInfra REST: GET /v1/me/rate_limit.
No parameters.
{
"name": "deepinfra_get_rate_limit",
"title": "Get rate limit",
"description": "Get the account's current rate limits (per-model / per-endpoint request and token limits). DeepInfra REST: GET /v1/me/rate_limit.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"annotations": {
"title": "Get rate limit",
"readOnlyHint": true
}
}List the account's API tokens (metadata only, not secret values). DeepInfra REST: GET /v1/api-tokens.
No parameters.
{
"name": "deepinfra_list_api_tokens",
"title": "List API tokens",
"description": "List the account's API tokens (metadata only, not secret values). DeepInfra REST: GET /v1/api-tokens.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"annotations": {
"title": "List API tokens",
"readOnlyHint": true
}
}Get spend / usage for a billing period. DeepInfra REST: GET /payment/usage.
| Parameter | Type | Description |
|---|---|---|
| to | string | Period end (same format as `from`); defaults to the current period. |
| from * | string | Period start (required). Format 'YYYY.MM', or 'current', or 'current(-N)' for N months back, or a unix timestamp in seconds. |
{
"name": "deepinfra_get_usage",
"title": "Get usage",
"description": "Get spend / usage for a billing period. DeepInfra REST: GET /payment/usage.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"from"
],
"properties": {
"to": {
"type": "string",
"description": "Period end (same format as `from`); defaults to the current period."
},
"from": {
"type": "string",
"minLength": 1,
"description": "Period start (required). Format 'YYYY.MM', or 'current', or 'current(-N)' for N months back, or a unix timestamp in seconds."
}
}
},
"annotations": {
"title": "Get usage",
"readOnlyHint": true
}
}Get per-model token usage for a period. DeepInfra REST: GET /payment/usage/tokens.
| Parameter | Type | Description |
|---|---|---|
| to | string | Period end (same format as `from`); defaults to the current period. |
| from * | string | Period start (required). Format 'YYYY.MM', or 'current', or 'current(-N)' for N months back, or a unix timestamp in seconds. |
{
"name": "deepinfra_get_usage_tokens",
"title": "Get token usage",
"description": "Get per-model token usage for a period. DeepInfra REST: GET /payment/usage/tokens.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"from"
],
"properties": {
"to": {
"type": "string",
"description": "Period end (same format as `from`); defaults to the current period."
},
"from": {
"type": "string",
"minLength": 1,
"description": "Period start (required). Format 'YYYY.MM', or 'current', or 'current(-N)' for N months back, or a unix timestamp in seconds."
}
}
},
"annotations": {
"title": "Get token usage",
"readOnlyHint": true
}
}Get GPU rental (dedicated hardware) usage for a time range. DeepInfra REST: GET /payment/usage/rent.
| Parameter | Type | Description |
|---|---|---|
| to | integer | Range end as a unix timestamp in seconds; defaults to now. |
| from * | integer | Range start as a unix timestamp in seconds (required). |
{
"name": "deepinfra_get_usage_rent",
"title": "Get GPU rental usage",
"description": "Get GPU rental (dedicated hardware) usage for a time range. DeepInfra REST: GET /payment/usage/rent.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"from"
],
"properties": {
"to": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Range end as a unix timestamp in seconds; defaults to now."
},
"from": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Range start as a unix timestamp in seconds (required)."
}
}
},
"annotations": {
"title": "Get GPU rental usage",
"readOnlyHint": true
}
}List billing invoices for the account. DeepInfra REST: GET /payment/invoices.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max number of invoices to return. |
| invoice_type | string | Filter by invoice type. |
| starting_after | string | Cursor — return invoices after this invoice id (pagination). |
{
"name": "deepinfra_list_invoices",
"title": "List invoices",
"description": "List billing invoices for the account. DeepInfra REST: GET /payment/invoices.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"limit": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 1,
"description": "Max number of invoices to return."
},
"invoice_type": {
"type": "string",
"description": "Filter by invoice type."
},
"starting_after": {
"type": "string",
"description": "Cursor — return invoices after this invoice id (pagination)."
}
}
},
"annotations": {
"title": "List invoices",
"readOnlyHint": true
}
}List the account's dedicated deployments. DeepInfra REST: GET /deploy/list.
| Parameter | Type | Description |
|---|---|---|
| status | string | Comma-separated statuses to filter by, e.g. 'running,initializing'. |
{
"name": "deepinfra_list_deployments",
"title": "List deployments",
"description": "List the account's dedicated deployments. DeepInfra REST: GET /deploy/list.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"status": {
"type": "string",
"description": "Comma-separated statuses to filter by, e.g. 'running,initializing'."
}
}
},
"annotations": {
"title": "List deployments",
"readOnlyHint": true
}
}Get one dedicated deployment by id (config + current status). DeepInfra REST: GET /deploy/{deploy_id}.
| Parameter | Type | Description |
|---|---|---|
| deploy_id * | string | The deployment id (required). |
{
"name": "deepinfra_get_deployment",
"title": "Get deployment",
"description": "Get one dedicated deployment by id (config + current status). DeepInfra REST: GET /deploy/{deploy_id}.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"deploy_id"
],
"properties": {
"deploy_id": {
"type": "string",
"minLength": 1,
"description": "The deployment id (required)."
}
}
},
"annotations": {
"title": "Get deployment",
"readOnlyHint": true
}
}Get time-series stats (throughput / latency / replicas) for a dedicated deployment. DeepInfra REST: GET /deploy/{deploy_id}/stats2.
| Parameter | Type | Description |
|---|---|---|
| to | string | Range end — unix timestamp or relative expression; defaults to now. |
| from * | string | Range start (required) — a unix timestamp or a relative expression like 'now-5h' (units: s, m, h, d, w). |
| deploy_id * | string | The deployment id (required). |
{
"name": "deepinfra_get_deployment_stats",
"title": "Get deployment stats",
"description": "Get time-series stats (throughput / latency / replicas) for a dedicated deployment. DeepInfra REST: GET /deploy/{deploy_id}/stats2.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"deploy_id",
"from"
],
"properties": {
"to": {
"type": "string",
"description": "Range end — unix timestamp or relative expression; defaults to now."
},
"from": {
"type": "string",
"minLength": 1,
"description": "Range start (required) — a unix timestamp or a relative expression like 'now-5h' (units: s, m, h, d, w)."
},
"deploy_id": {
"type": "string",
"minLength": 1,
"description": "The deployment id (required)."
}
}
},
"annotations": {
"title": "Get deployment stats",
"readOnlyHint": true
}
}Get GPU availability for LLM deployments (which hardware can currently be provisioned). DeepInfra REST: GET /deploy/llm/gpu_availability.
| Parameter | Type | Description |
|---|---|---|
| source | string | Filter by source. |
| base_model | string | Filter by base model. |
{
"name": "deepinfra_get_gpu_availability",
"title": "Get GPU availability",
"description": "Get GPU availability for LLM deployments (which hardware can currently be provisioned). DeepInfra REST: GET /deploy/llm/gpu_availability.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"source": {
"type": "string",
"description": "Filter by source."
},
"base_model": {
"type": "string",
"description": "Filter by base model."
}
}
},
"annotations": {
"title": "Get GPU availability",
"readOnlyHint": true
}
}List the DeepInfra model catalog (all available models). DeepInfra REST: GET /models/list.
No parameters.
{
"name": "deepinfra_list_models",
"title": "List models",
"description": "List the DeepInfra model catalog (all available models). DeepInfra REST: GET /models/list.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"annotations": {
"title": "List models",
"readOnlyHint": true
}
}Get one model's catalog entry (pricing, context length, capabilities). DeepInfra REST: GET /models/{model_name}.
| Parameter | Type | Description |
|---|---|---|
| version | string | A specific model version (defaults to latest). |
| model_name * | string | The model name (required). May contain a slash, e.g. 'meta-llama/Meta-Llama-3-8B' — the slash is preserved in the path. |
{
"name": "deepinfra_get_model",
"title": "Get model",
"description": "Get one model's catalog entry (pricing, context length, capabilities). DeepInfra REST: GET /models/{model_name}.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model_name"
],
"properties": {
"version": {
"type": "string",
"description": "A specific model version (defaults to latest)."
},
"model_name": {
"type": "string",
"minLength": 1,
"description": "The model name (required). May contain a slash, e.g. 'meta-llama/Meta-Llama-3-8B' — the slash is preserved in the path."
}
}
},
"annotations": {
"title": "Get model",
"readOnlyHint": true
}
}Get the hardware options / GPU configuration available for a given model. DeepInfra REST: GET /v2/hardware.
| Parameter | Type | Description |
|---|---|---|
| model * | string | The model name to query hardware for (required). |
{
"name": "deepinfra_get_hardware",
"title": "Get hardware",
"description": "Get the hardware options / GPU configuration available for a given model. DeepInfra REST: GET /v2/hardware.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model"
],
"properties": {
"model": {
"type": "string",
"minLength": 1,
"description": "The model name to query hardware for (required)."
}
}
},
"annotations": {
"title": "Get hardware",
"readOnlyHint": true
}
}Query inference request logs for a dedicated deployment over a time window. DeepInfra REST: GET /v1/logs/query.
| Parameter | Type | Description |
|---|---|---|
| to | string | Window end — fractional-seconds unix timestamp, exclusive. |
| from | string | Window start — fractional-seconds unix timestamp, inclusive. |
| limit | integer | Max log lines to return (default 100, range 1..1000). |
| deploy_id * | string | The deployment id to query logs for (required). |
{
"name": "deepinfra_query_logs",
"title": "Query logs",
"description": "Query inference request logs for a dedicated deployment over a time window. DeepInfra REST: GET /v1/logs/query.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"deploy_id"
],
"properties": {
"to": {
"type": "string",
"description": "Window end — fractional-seconds unix timestamp, exclusive."
},
"from": {
"type": "string",
"description": "Window start — fractional-seconds unix timestamp, inclusive."
},
"limit": {
"type": "integer",
"maximum": 1000,
"minimum": 1,
"description": "Max log lines to return (default 100, range 1..1000)."
},
"deploy_id": {
"type": "string",
"minLength": 1,
"description": "The deployment id to query logs for (required)."
}
}
},
"annotations": {
"title": "Query logs",
"readOnlyHint": true
}
}Get global live inference metrics across the account (real-time throughput / activity). DeepInfra REST: GET /v1/metrics/live.
No parameters.
{
"name": "deepinfra_get_live_metrics",
"title": "Get live metrics",
"description": "Get global live inference metrics across the account (real-time throughput / activity). DeepInfra REST: GET /v1/metrics/live.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"annotations": {
"title": "Get live metrics",
"readOnlyHint": true
}
}Start (resume) a dedicated deployment. WARNING: this resumes a dedicated deployment and may incur GPU charges while it runs. DeepInfra REST: POST /deploy/{deploy_id}/start.
| Parameter | Type | Description |
|---|---|---|
| deploy_id * | string | The deployment id to start (required). |
{
"name": "deepinfra_start_deployment",
"title": "Start deployment",
"description": "Start (resume) a dedicated deployment. WARNING: this resumes a dedicated deployment and may incur GPU charges while it runs. DeepInfra REST: POST /deploy/{deploy_id}/start.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"deploy_id"
],
"properties": {
"deploy_id": {
"type": "string",
"minLength": 1,
"description": "The deployment id to start (required)."
}
}
},
"annotations": {
"title": "Start deployment",
"destructiveHint": true
}
}Stop (pause) a running dedicated deployment. This halts inference and stops accruing GPU charges for it. DeepInfra REST: POST /deploy/{deploy_id}/stop.
| Parameter | Type | Description |
|---|---|---|
| deploy_id * | string | The deployment id to stop (required). |
{
"name": "deepinfra_stop_deployment",
"title": "Stop deployment",
"description": "Stop (pause) a running dedicated deployment. This halts inference and stops accruing GPU charges for it. DeepInfra REST: POST /deploy/{deploy_id}/stop.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"deploy_id"
],
"properties": {
"deploy_id": {
"type": "string",
"minLength": 1,
"description": "The deployment id to stop (required)."
}
}
},
"annotations": {
"title": "Stop deployment",
"destructiveHint": true
}
}Tools for DeepInfra, hosted by usefulapi.io. If the user is new or asks what this server can do, suggest requests such as: "Show my spending for the current billing month."; "Which models can I use for text embeddings?"; "Show my deployments and stop the ones that have no traffic.". Read-only tools never change data; ask the user before a tool that creates, changes or deletes DeepInfra data. Free plan: 50 tool calls per month. Run deepinfra_usage_status to see the calls used this month. If the user asks for something none of these tools can do, tell the user and, with their OK, run deepinfra_request_feature to record the request. Paid plans: Pro (10,000 tool calls a month, $9/month or $90/year, for normal use) and Pro+ (100,000 tool calls a month, $39/month or $390/year, for automations and heavy use). A plan can be cancelled at any time and then runs to the end of the paid period, so it also suits a one-time job. When the user wants more calls or reaches the limit, run deepinfra_upgrade without a plan: it returns both plans, each with a payment link for the user to open. deepinfra_cancel_subscription cancels Pro at the end of the paid period.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.