Network stats — /v1/stats, /v1/leaderboard

These three endpoints expose public, read-only statistics about the Darkbloom network. No authentication is required. They power the network dashboard on darkbloom.dev and are suitable for building external monitoring tools or status pages.

GET /v1/stats

Returns aggregate platform statistics for all currently connected providers, including hardware totals, token counts, and a 30-minute time series. Cached for 60 seconds.

Response

integer

Cumulative number of inference requests served across the network lifetime.

integer

Cumulative input tokens consumed across all requests.

integer

Cumulative output tokens generated across all requests.

integer

Sum of prompt and completion tokens.

number

Average token count per request.

integer

Number of providers currently connected.

integer

Total GPU cores across all connected providers.

integer

Total CPU cores across all connected providers.

integer

Total unified memory in GB across all connected providers.

number

Total memory bandwidth in GB/s across all connected providers.

object[]

Array of per-provider hardware and stats snapshots.

Show provider fields

string

Internal provider identifier.

string

Apple Silicon chip name, e.g. "Apple M3 Max".

string

Chip family, e.g. "M3".

integer

Unified memory size in GB.

integer

GPU core count.

string

Provider status. "online" when available for requests.

string

Attestation trust level: "self_signed" or "hardware".

number

Most recently observed decode throughput in tokens per second.

integer

Requests served by this provider in the current session.

integer

Tokens generated by this provider in the current session.

string[]

Model IDs this provider is serving.

string

The model currently loaded on this provider.

object[]

Aggregated per-model provider counts.

Show model fields

string

Model ID.

integer

Number of providers currently serving this model.

object[]

Per-minute request and token counts for the last 30 minutes.

Show time series fields

string

ISO 8601 UTC timestamp for the minute bucket.

integer

Requests completed in this minute.

integer

Input tokens consumed in this minute.

integer

Output tokens generated in this minute.

integer

Total tokens in this minute.

GET /v1/leaderboard

Returns the top providers ranked by earnings, tokens generated, or jobs completed. Provider identities are pseudonymized — raw account IDs are never exposed. Cached for 5 minutes.

Query parameters

string

default:"earnings"

The ranking metric. One of "earnings", "tokens", or "jobs".

string

default:"all"

The time window for rankings. One of "24h", "7d", "30d", or "all".

integer

default:"50"

Maximum number of entries to return. Between 1 and 200.

Response

string

The metric used for ranking.

string

The time window used.

object[]

Ranked list of providers.

Show entry fields

integer

Position in the leaderboard (1-indexed).

string

Pseudonymized provider identifier derived deterministically from the account ID.

integer

Total earnings in micro-USD for the selected window.

integer

Total tokens generated for the selected window.

integer

Total inference jobs completed for the selected window.

string

ISO 8601 timestamp of when this response was generated.

GET /v1/network/totals

Returns aggregate network metrics (earnings, tokens, jobs, active accounts) for a given time window. Cached for 1 minute.

Query parameters

string

default:"all"

The time window. One of "24h", "7d", "30d", or "all".

Response

string

The time window used.

integer

Total provider earnings in micro-USD for the window.

integer

Total tokens generated for the window.

integer

Total inference jobs completed for the window.

integer

Number of distinct accounts active in the window.

string

ISO 8601 timestamp of when this response was generated.

Examples

curl https://api.darkbloom.dev/v1/stats

curl "https://api.darkbloom.dev/v1/leaderboard?metric=earnings&window=7d&limit=10"

curl "https://api.darkbloom.dev/v1/network/totals?window=24h"

Example /v1/stats response

{
  "total_requests": 142893,
  "total_prompt_tokens": 89234120,
  "total_completion_tokens": 31047880,
  "total_tokens": 120282000,
  "avg_tokens_per_request": 841.7,
  "active_providers": 12,
  "total_gpu_cores": 480,
  "total_cpu_cores": 192,
  "total_memory_gb": 768,
  "total_bandwidth_gbs": 9828.0,
  "providers": [...],
  "models": [
    {"id": "qwen3.5-27b-claude-opus-8bit", "providers": 4},
    {"id": "mlx-community/gemma-4-26b-a4b-it-8bit", "providers": 5}
  ],
  "time_series": [...]
}

Example /v1/leaderboard response

{
  "metric": "earnings",
  "window": "7d",
  "entries": [
    {
      "rank": 1,
      "pseudonym": "SwiftFalcon",
      "earnings_micro_usd": 8420000,
      "tokens": 91234567,
      "jobs": 4821
    },
    {
      "rank": 2,
      "pseudonym": "IronHawk",
      "earnings_micro_usd": 6150000,
      "tokens": 67012345,
      "jobs": 3640
    }
  ],
  "updated_at": "2025-04-30T15:00:00Z"
}

Example /v1/network/totals response

{
  "window": "24h",
  "earnings_micro_usd": 12480000,
  "tokens": 148203450,
  "jobs": 7923,
  "active_accounts": 38,
  "updated_at": "2025-04-30T15:01:00Z"
}

Inference

Account

Network

Network stats — /v1/stats, /v1/leaderboard

GET /v1/stats

Response

GET /v1/leaderboard

Query parameters

Response

GET /v1/network/totals

Query parameters

Response

Examples

Example /v1/stats response

Example /v1/leaderboard response

Example /v1/network/totals response

​GET /v1/stats

​Response

​GET /v1/leaderboard

​Query parameters

​Response

​GET /v1/network/totals

​Query parameters

​Response

​Examples

​Example /v1/stats response

​Example /v1/leaderboard response

​Example /v1/network/totals response

GET /v1/stats

Response

GET /v1/leaderboard

Query parameters

Response

GET /v1/network/totals

Query parameters

Response

Examples

Example /v1/stats response

Example /v1/leaderboard response

Example /v1/network/totals response