Run DeepInfra inference, list models and read account rate limits. Hosted by usefulapi: connect it to Claude, ChatGPT, Cursor or any MCP client.
Turn on the DeepInfra connector, then ask in plain words. The AI picks the tools.
For developers and ML engineers who run models and dedicated GPU deployments on DeepInfra.
The AI reads spend for a billing period and token usage per model. It also reads GPU rental usage for a time range and lists invoices, so you see where the cost comes from.
The AI lists the model catalog and reads one model entry with its pricing, context length and capabilities. You can compare models for a task such as embeddings.
The AI reads a dedicated deployment with its config and status, plus time-series stats for throughput, latency and replicas. It can also query the request logs of a time window.
The AI reads which GPUs can be provisioned for LLM deployments now, and the hardware options for a given model. It helps you plan a new deployment.
The AI stops a running dedicated deployment to end GPU charges, or starts a stopped one. Starting a deployment may add GPU charges while it runs.
Changes dataThe 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.
Team and Enterprise: an Owner adds the connector for the organization first.
No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
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"
}
}
} Run these commands. The second one opens the login page:
Windsurf, Cline, Zed and other MCP clients: add this URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser.
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.
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro | $9/mo · $90/yr | 10,000 tool calls / month |
| Pro+ | $39/mo · $390/yr | 100,000 tool calls / month |
Each paid plan covers this DeepInfra server only. Ask your AI to run deepinfra_upgrade and choose Pro or Pro+, billed monthly or yearly (it returns a Stripe Checkout link). If you already have Pro, ask to change it to Pro+. The change requires your confirmation, keeps your billing interval and charges the price difference for the rest of the period immediately. Cancel any time with deepinfra_cancel_subscription: your paid plan continues to the end of the paid period, with no refund for the current period, and asking to resume the same plan with deepinfra_upgrade before then undoes the cancel. Or write to [email protected].
deepinfra_get_accountdeepinfra_get_rate_limitdeepinfra_list_api_tokensdeepinfra_get_usagedeepinfra_get_usage_tokensdeepinfra_get_usage_rentdeepinfra_list_invoicesdeepinfra_list_deploymentsdeepinfra_get_deploymentdeepinfra_get_deployment_statsdeepinfra_get_gpu_availabilitydeepinfra_list_modelsdeepinfra_get_modeldeepinfra_get_hardwaredeepinfra_query_logsdeepinfra_get_live_metricsdeepinfra_start_deploymentdeepinfra_stop_deploymentdeepinfra_usage_statusdeepinfra_request_featuredeepinfra_upgradedeepinfra_cancel_subscriptionCheck spend and token usage for a billing period. Find models and compare their price and context length. Check how a dedicated deployment is doing. Check GPU availability and hardware for a deployment. Start or stop a dedicated deployment. See what you can do for the details.
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.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
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 50 tool calls / month. Pro costs $9/mo or $90/yr, with 10,000 tool calls / month. Pro+ costs $39/mo or $390/yr, with 100,000 tool calls / month. Each subscription covers this DeepInfra server only. Cancel any time: your paid plan then runs to the end of the paid period. Run deepinfra_usage_status to see how many calls you used.
Ask the AI to run deepinfra_upgrade and choose Pro or Pro+, billed monthly or yearly: it returns a Stripe Checkout link. If you already have Pro, ask to change it to Pro+. After you confirm, your existing subscription changes in place, keeps its billing interval and charges the price difference for the rest of the period immediately. To cancel, run deepinfra_cancel_subscription. Your paid plan 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, ChatGPT, Codex, 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.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.