Opsmeter
AI Cost & Inference Control
Integration docs
Developer Docs
Ship telemetry fast with LLM cost tracking and OpenAI cost monitoring. Request-level budget alerts are available on Pro+ plans.
Provider and model catalog
Before sending ingest payload, always fetch GET /v1/public/pricing-models and use the provider/model strings exactly as returned.
Rule: 1) Pull catalog, 2) copy provider/model exactly, 3) send payload.
If provider/model is not found in catalog, ingest falls back to unknown and costUsd = 0 until pricing is added.
OpenAI
| Model | Input Price | Output Price | Effective from | Action |
|---|---|---|---|---|
gpt-4o-mini | $0.150 | $0.600 | 2026-02-06 13:38 | |
gpt-4-1 | $2.000 | $8.000 | 2026-02-06 13:38 | |
gpt-4-1-mini | $0.400 | $1.600 | 2026-02-06 13:38 | |
gpt-4o | $2.500 | $10.000 | 2026-02-06 13:38 | |
ada | $0.400 | $0.400 | 2026-02-06 13:38 | |
ada-batch | $0.200 | $0.200 | 2026-02-06 13:38 | |
babbage | $0.500 | $0.500 | 2026-02-06 13:38 | |
babbage-batch | $0.250 | $0.250 | 2026-02-06 13:38 |
Showing 1-8 of 160