Pricing and Billing

Inference Space bills by capability. Prices are based on the system price catalog, currently the CNY version 2026-06-17. Organization contract price > activation discount price > system price: when an organization has a dedicated price for a model, that price applies; otherwise, billing uses the public activation price or system catalog price.

Private deployment uses the same billing dimensions and pricing strategy; only replace the Base domain → Enterprise private deployment.

Billing dimensions

LLM rules

• The context tier is determined by the input tokens in the request: ≤128k, ≤256k, or >256k. Each tier has a different unit price.
• prompt_tokens counts non-cached input only; cache hits are counted in cached_prompt_tokens.
• Cached input is billed at a lower price: use the explicit cache price when available; otherwise, charge 10% (0.1× input) of the input price for the same tier.
• Output is billed through completion_tokens. Reasoning (extended thinking), tool results, and retrieved context ultimately appear in input or output tokens.

See the “Prompt caching” and “Billing” sections of the Claude Messages API.

Image rules (gpt-image-2)

gpt-image-2 is billed per image by resolution and quality tier; image tokens are not billed separately. Actual prices are shown in the console, with organization-specific prices taking precedence.

See GPT-Image 2 image generation and editing for API details.

Real-time organization pricing lookup

Use a gateway API key to query the current effective price catalog for its organization. The response merges organization-specific prices into the system catalog, so the returned prices are the prices used for billing.

GET https://ai.inf.space/v1/pricing/lookup

• Host: This control-plane endpoint is available at https://ai.inf.space/v1/pricing/lookup.
• Authentication: HTTP header Authorization: Bearer <gk_...>. A valid gateway API key is required; its organization defines the query scope.
• Optional query parameters: capability (llm / image / asr / tts / ocr), provider, and model for dimension-based filtering.
• Response shape: { currency, entries, version }, with additional display fields such as models and labels.

  curl "https://ai.inf.space/v1/pricing/lookup?capability=llm" \
  -H "Authorization: Bearer $TOS_API_KEY"

import os, requests

resp = requests.get(
    "https://ai.inf.space/v1/pricing/lookup",
    params={"capability": "llm"},
    headers={"Authorization": f"Bearer {os.environ['TOS_API_KEY']}"},
)
data = resp.json()
print(data["currency"], data["version"])
for entry in data["entries"]:
    print(entry)

const resp = await fetch(
  "https://ai.inf.space/v1/pricing/lookup?capability=llm",
  { headers: { Authorization: `Bearer ${process.env.TOS_API_KEY}` } },
);
const data = await resp.json();
console.log(data.currency, data.version);
console.log(data.entries);

Example response (illustrative structure; the entries contents depend on the organization's effective catalog):

{
  "currency": "CNY",
  "entries": [
    {
      "capabilityId": "llm",
      "providerId": "dashscope",
      "model": "qwen-plus",
      "meters": { "prompt_tokens": "...", "completion_tokens": "..." }
    }
  ],
  "version": "2026-06-17"
}

Effective prices

This page does not maintain a static price table. Use the console or /v1/pricing/lookup to query the current effective prices for an organization. After organization contract prices, activation discounts, and the system catalog are merged, the API response and billing statement are authoritative.

For Chinese speech, estimate 250 characters/min ≈ 425 tokens/min. For voice-agent input tokens, a starting estimate is 3× the output tokens.

Cost calculation