Run DeepInfra inference, list models and read account rate limits. Hosted by usefulapi — connect from Claude, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"deepinfra": {
"url": "https://deepinfra.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"deepinfra": {
"type": "http",
"url": "https://deepinfra.usefulapi.io/mcp"
}
}
}Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
The login page asks for your DeepInfra API key.
Create one in DeepInfra → Settings → API. Your token is used only to call the API on your behalf and to derive a private account id; it is never shown to anyone.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your DeepInfra API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the DeepInfra connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
deepinfra_get_account | read | Get account Get the current DeepInfra account / user details (identity, email, quotas). DeepInfra REST: GET /v1/me. |
deepinfra_get_rate_limit | read | Get rate limit Get the account's current rate limits (per-model / per-endpoint request and token limits). DeepInfra REST: GET /v1/me/rate_limit. |
deepinfra_list_api_tokens | read | List API tokens List the account's API tokens (metadata only, not secret values). DeepInfra REST: GET /v1/api-tokens. |
deepinfra_get_usage | read | Get usage Get spend / usage for a billing period. DeepInfra REST: GET /payment/usage. |
deepinfra_get_usage_tokens | read | Get token usage Get per-model token usage for a period. DeepInfra REST: GET /payment/usage/tokens. |
deepinfra_get_usage_rent | read | Get GPU rental usage Get GPU rental (dedicated hardware) usage for a time range. DeepInfra REST: GET /payment/usage/rent. |
deepinfra_list_invoices | read | List invoices List billing invoices for the account. DeepInfra REST: GET /payment/invoices. |
deepinfra_list_deployments | read | List deployments List the account's dedicated deployments. DeepInfra REST: GET /deploy/list. |
deepinfra_get_deployment | read | Get deployment Get one dedicated deployment by id (config + current status). DeepInfra REST: GET /deploy/{deploy_id}. |
deepinfra_get_deployment_stats | read | Get deployment stats Get time-series stats (throughput / latency / replicas) for a dedicated deployment. DeepInfra REST: GET /deploy/{deploy_id}/stats2. |
deepinfra_get_gpu_availability | read | Get GPU availability Get GPU availability for LLM deployments (which hardware can currently be provisioned). DeepInfra REST: GET /deploy/llm/gpu_availability. |
deepinfra_list_models | read | List models List the DeepInfra model catalog (all available models). DeepInfra REST: GET /models/list. |
deepinfra_get_model | read | Get model Get one model's catalog entry (pricing, context length, capabilities). DeepInfra REST: GET /models/{model_name}. |
deepinfra_get_hardware | read | Get hardware Get the hardware options / GPU configuration available for a given model. DeepInfra REST: GET /v2/hardware. |
deepinfra_query_logs | read | Query logs Query inference request logs for a dedicated deployment over a time window. DeepInfra REST: GET /v1/logs/query. |
deepinfra_get_live_metrics | read | Get live metrics Get global live inference metrics across the account (real-time throughput / activity). DeepInfra REST: GET /v1/metrics/live. |
deepinfra_start_deployment | write | Start deployment 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. |
deepinfra_stop_deployment | write | Stop deployment Stop (pause) a running dedicated deployment. This halts inference and stops accruing GPU charges for it. DeepInfra REST: POST /deploy/{deploy_id}/stop. |
deepinfra_usage_status | Usage status (free-tier meter) Report the caller's current free-tier usage this month: calls used, monthly limit, remaining, and whether the cap is reached. Read-only; does not count against the meter. | |
deepinfra_request_feature | Request a missing feature Tell usefulapi that the user needs something the DeepInfra tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
deepinfra_upgrade | Upgrade to Pro (unlimited) Subscribe to the Pro plan for UNLIMITED DeepInfra tool calls (the free tier caps monthly usage). Choose monthly ($9/month) or yearly ($90/year — 2 months free) billing. Returns a Stripe Checkout link to open in your browser; after payment your account upgrades automatically. Does not count against the meter. | |
deepinfra_cancel_subscription | Cancel the Pro subscription Cancel the caller's DeepInfra Pro subscription at the end of the paid period (no refund for the current period; unlimited calls continue until then, then the free tier applies). Requires confirm: true. Run deepinfra_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 100 tool calls / month |
| Pro | $9/mo · $90/yr | Unlimited |
Pro covers this DeepInfra server only. Subscribe with deepinfra_upgrade (it returns a Stripe Checkout link). Cancel any time with deepinfra_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running deepinfra_upgrade before then undoes the cancel. Or write to [email protected].
No. usefulapi is an independent service. It is not affiliated with or endorsed by DeepInfra. The server calls the DeepInfra API with your own DeepInfra access, so it sees only the data that your account can see.
The login page asks for your DeepInfra API key. See Before you connect for where to find it.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your DeepInfra API key. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the DeepInfra API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in DeepInfra.
Yes, if you approve it. 2 of the 18 DeepInfra tools can create or change data. The other 16 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 100 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls, for this DeepInfra server only. Run deepinfra_usage_status to see how many calls you used.
Ask the AI to run deepinfra_upgrade: it returns a Stripe Checkout link. To cancel, run deepinfra_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with deepinfra_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.