Skip to main content
1API Club

For agents, n8n workflows, and scripts

1API Club

One API for AI agents, coding CLIs, and workflow automation.

Connect your tools once. Routed prompts and responses are not stored by our platform; usage metadata stays available for billing and audit.

View pricing

Workspace console

Keys, credits, usage, and checkout in one workspace.

Use OpenAI-compatible, Anthropic, or Gemini request shapes from one workspace. Start with documented endpoints and public model ids.

# One request enters your workspace
✓ Key and workspace checked
✓ Model and usage recorded
200 OK  { "content": "Hello!" }

Workspace console

One workspace for workload control.

Keep the things a developer can act on in one place: keys, credits, usage records, and delivery lanes.

Scoped keysIssue separate keys for agents, apps, workflows, and scripts.Prepaid creditsTop up a wallet before sustained traffic reaches production workloads.Usage recordsReview metadata by model, key, outcome, tokens, latency, and charge status without stored prompt or response content.Delivery lanesDescribe workload intent with public models, lanes, and service modes.

Docs start

Start with the protocol your tools already know.

Use OpenAI-compatible, Anthropic Messages, or Gemini v1beta request shapes from one workspace, then manage keys, credits, usage rows, and delivery lanes from the console.

Open API docs

  • OpenAI-compatible

    /v1

    Use existing OpenAI SDK clients with a scoped workspace key.

  • Anthropic native

    /v1/messages

    Run Messages, token counts, and model reads where available.

  • Gemini native

    /v1beta/models

    Use generate, stream, count-token, and embedding shapes for supported models.

Usage and credits

Info status: Example records

See what each billable API call used and cost.

Top up prepaid credits, send requests with OpenAI-compatible, Anthropic, or Gemini protocols, then review billable usage receipts by receipt id, model, token usage, pricing snapshot, and credits.

  • Credits are deducted from visible usage rows, not a black-box balance change.
  • Public model rates stay connected to the model and billable quantities.
  • Receipts remain readable before you move a workload into sustained traffic.
View pricing
Sample data only
Request TimeAPI KEYModelDelivery LaneUsagePerformanceBreakdownCharge Details
gpt-5.4
Request Time
API KEY
Premium Key
Model
gpt-5.4
Delivery Lane
premium 1x
UsageInput tokens 980; Output tokens 360; Reasoning tokens 640; Total tokens 1,980
Performance
TTFT
Fast latency: 320ms
Output Duration
1920ms
Throughput
187.50tok/s
Breakdown$0.017450
Sample only
gpt-5.5
Request Time
API KEY
Premium Key
Model
gpt-5.5
Delivery Lane
premium 1x
UsageInput tokens 1,420; Output tokens 520; Cached input 8,192; Total tokens 10,132
Performance
TTFT
Fast latency: 240ms
Output Duration
1620ms
Throughput
320.99tok/s
Breakdown$0.026796
Sample only
claude-opus-4.8
Request Time
API KEY
Standard Key
Model
claude-opus-4.8
Delivery Lane
standard 0.35x
UsageInput tokens 2,450; Output tokens 740; Cached input 1,280; Cache write 320; Total tokens 4,790
Performance
TTFT
Fast latency: 410ms
Output Duration
3510ms
Throughput
210.83tok/s
Breakdown$0.011687
Sample only
gemini-3.1-pro
Request Time
API KEY
Economy Key
Model
gemini-3.1-pro
Delivery Lane
economy 0.2x
UsageInput tokens 620; Output tokens 280; Total tokens 900
Performance
TTFT
Fast latency: 180ms
Output Duration
1000ms
Throughput
280.00tok/s
Breakdown$0.000920
Sample only

Ready path

Start one workload, then review usage records.

Create a scoped key, connect one agent or workflow, and keep credits, usage, and billing records in view.

View pricing