---
title: "Deploy Detailed Stats"
method: GET
path: "/deploy/{deploy_id}/stats2"
tags: ["Dedicated Models"]
---

# Deploy Detailed Stats

`GET /deploy/{deploy_id}/stats2`

## Path parameters

- `deploy_id` string, required

## Query parameters

- `from` string, required — start of period, unix ts or 'now-5h', supported units s, m, h, d, w
- `to` string — end of period, unix ts or now-relative, check from, defaults to now

## Headers

- `xi-api-key` string, nullable
- `x-api-key` string, nullable

## Response `200`

Successful Response

- DetailedDeploymentStatsOut
  - `llm` LLMDeploymentStatsOut
    - `requests` integer, required — number of inference requests in the provided interval
    - `input_tokens` integer, required — number of input tokens generated
    - `output_tokens` integer, required — number of output tokens generated
    - `avg_ttft_ms` number, required — average millisecond time to first token
    - `avg95_ttft_ms` number, required — 95th percentile time to first token (estimated)
    - `avg_tpt_ms` number, required — average millisecond time per token
    - `avg95_tpt_ms` number, required — 95th percentile time per token (estimated)
    - `total_amount_cents` integer, required — total number of cents spent
    - `errors` integer, required — number of errors
  - `embeddings` EmbeddingsDeploymentStatsOut
    - `requests` integer, required — number of inference requests in the provided interval
    - `input_tokens` integer, required — number of input tokens generated
    - `avg_tpt_ms` number, required — average millisecond time per token
    - `avg95_tpt_ms` number, required — 95th percentile time per token (estimated)
    - `total_amount_cents` integer, required — total number of cents spent
    - `errors` integer, required — number of errors
  - `time` TimeDeploymentStatsOut
    - `requests` integer, required — number of inference requests in the provided interval
    - `total_time_s` integer, required — total number of seconds spend in inference
    - `total_amount_cents` integer, required — total number of cents spent
    - `avg_time_ms` number, required — average millisecond inference time
    - `avg95_time_ms` number, required — 95th percentile inference time (estimated)
    - `errors` integer, required — number of errors

## Other responses

- `404` — Not Found
- `410` — Gone
- `422` — Validation Error

---

[API](https://skmtc.net/deepinfra/apis/deepinfra-api.md) · [All operations](https://skmtc.net/deepinfra/apis/deepinfra-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/deepinfra/deepinfra-api/versions/51b817b3f80f/schema)