AALLM Docs

Calculate pricing

Calculate a deterministic token quote using the current rate card for one deployment.

Request

POST/v1/pricing/calculateAuthentication: Required
cURL
curl https://api.use-allm.com/v1/pricing/calculate \
  -X POST \
  -H "Authorization: Bearer $ALLM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "deployment_id": "dep_openai_gpt_5_1_responses_global",
    "usage": { "input_tokens": 1000000, "output_tokens": 100000 }
  }'
TypeScript
const quote = await allm.pricing.calculate({
  deployment: "dep_openai_gpt_5_1_responses_global",
  inputTokens: 1_000_000,
  outputTokens: 100_000,
});

console.log(quote.totalUsd); // "2.250000"
Python
quote = allm.pricing.calculate(
    deployment="dep_openai_gpt_5_1_responses_global",
    input_tokens=1_000_000,
    output_tokens=100_000,
)

print(quote["data"]["total_usd"])  # 2.250000

Request body

deployment_id
stringrequired
Deployment whose current rate card should be applied.
usage.input_tokens
integer ≥ 0required
All input tokens, including the cached subset.
usage.output_tokens
integer ≥ 0required
Generated output tokens.
usage.cached_input_tokens
integer ≥ 0
Subset of input tokens charged at the cached rate.Default: 0

Response

JSON · 200
{
  "data": {
    "deployment_id": "dep_openai_gpt_5_1_responses_global",
    "currency": "USD",
    "total_usd": "2.250000",
    "line_items": [
      { "dimension": "input_tokens", "quantity": 1000000, "amount_usd": "1.250000" },
      { "dimension": "cached_input_tokens", "quantity": 0, "amount_usd": "0.000000" },
      { "dimension": "output_tokens", "quantity": 100000, "amount_usd": "1.000000" }
    ],
    "rate_card": {
      "currency": "USD",
      "unit": "million_tokens",
      "input_micro_usd": 1250000,
      "cached_input_micro_usd": 125000,
      "output_micro_usd": 10000000,
      "source_url": "https://developers.openai.com/api/docs/models/gpt-5.1",
      "observed_at": "2026-07-14T00:00:00Z"
    }
  }
}

Cached tokens

cached_input_tokens must not exceed input_tokens. The response always includes three line items—even when one has a quantity and amount of zero—so downstream billing code can remain structurally stable.

Errors

StatusCodeWhen it happens
400INVALID_REQUESTThe body is invalid or contains negative or non-integer token counts.
404DEPLOYMENT_NOT_FOUNDThe deployment ID does not exist.
422PRICING_UNAVAILABLENo token rate card applies, or cached input exceeds total input.

Response metadata

Every successful response includes x-allm-catalog-release, x-request-id, and an ETag. Store the request ID in logs and the catalog release beside any persisted decision.