No. Customer-cost tracking and budgets work without it. Where you share revenue data, Spendline compares revenue with attributed AI cost over the same period.
No. Where you share revenue data, this view subtracts attributed AI cost from revenue. Hosting, support, payment fees and other delivery costs are not included.
Spendline checks estimated request cost before forwarding. Final usage can cost more than the estimate. Controls cover supported requests routed through Spendline; we check the configured behavior during the pilot.
LiteLLM already offers cost attribution and budget enforcement. Spendline brings customer-cost records, revenue comparison where you share revenue data, and budget decisions into a workflow for engineering and finance. The call establishes what you need beyond the tools you already use.
No additional SDK is required for supported routes. Your engineer changes the relevant endpoint configuration and supplies attribution labels. The integration guide lists supported APIs and their limits.
Spendline processes supported requests and responses as it forwards them. Our data posture explains the current processing, storage and retention details.
Paid pricing combines a platform fee with a capped charge based on managed AI spend. We agree included features and paid terms before you start, and nothing is billed unless you choose to continue. You decide at the day-30 review.
| Request shape | Providers | SDK base | Streaming |
|---|---|---|---|
/v1/chat/completions | OpenAI, Google Gemini, xAI, Mistral, DeepSeek, Qwen, Together AI, Fireworks AI, Groq | https://www.spendline.ai/v1 | Supported |
/v1/messages | Anthropic | https://www.spendline.ai | Supported |
/v1/responses | OpenAI | https://www.spendline.ai/v1 | Non-streaming only |
/v1/chat/completionshttps://www.spendline.ai/v1/v1/messageshttps://www.spendline.ai/v1/responseshttps://www.spendline.ai/v1Three request shapes are supported: /v1/chat/completions for OpenAI, Google Gemini, xAI, Mistral, DeepSeek, Qwen, Together AI, Fireworks AI, Groq (SDK base https://www.spendline.ai/v1; streaming: supported); /v1/messages for Anthropic (SDK base https://www.spendline.ai; streaming: supported); /v1/responses for OpenAI (SDK base https://www.spendline.ai/v1; streaming: non-streaming only). Embeddings, images, audio and speech, vector or knowledge-base search, and Google’s native generateContent API are not supported. Leave those requests pointed at the provider; they are outside Spendline’s controls and records.
We review your current request path during the call. Compatibility depends on the APIs, routing and controls in that path.
Set customer IDs on your server from authenticated request context. Spendline records the supplied customer ID and server time. Pass the customer ID on each request rather than fixing one value in a shared client. A request without a customer ID is still recorded and costed, but it is not assigned to a customer, so it shows up as a gap in customer reporting. Attribution enforcement can be configured to refuse requests that are missing required labels.
A budget refusal (HTTP 402) or a policy refusal (HTTP 403) is a deliberate control decision made before the request reaches the provider. Your application should show it and must not retry the request directly against the provider. A proxy or network error (a 5xx response, a timeout or no connection) is different: the integration guide describes the documented failure behavior, including an optional single retry directly to the provider. A request sent directly to the provider is outside Spendline’s budget checks and cost records.
Read the integration guide · Status codes and troubleshooting
Yes. Customer-cost records and budgets work on their own. Revenue is an optional input you enter or import; it is needed only to compare revenue with attributed AI cost for the same period, where you share revenue data. You enter one monthly revenue figure per customer, so a period that reaches into past months applies today’s figure and is marked as an estimate.
Our data posture page is the single description of what Spendline processes, stores and keeps.
Book a 30-minute call · Explore a sample account
Prefer email? fida@spendline.ai