Models and pricing

The runtime source of truth is the authenticated model catalog. For an OpenAI-compatible client, call GET /v1/models with an API-credit key or GET /token/v1/models with an API-token key. It lists only models with active pricing and a configured route.

List live models

GET $CLOUDSERVICE_BASE_URL/models

Set CLOUDSERVICE_BASE_URL to https://api.yourdomain.example/v1 for API credit or https://api.yourdomain.example/token/v1 for API tokens. Native Anthropic clients discover models through their origin plus /v1/models.

curl "$CLOUDSERVICE_BASE_URL/models" \
  -H "Authorization: Bearer YOUR_CLOUDSERVICE_API_KEY"

Current pricing

Prices are customer-facing USD rates per 1M tokens. GPT-5.6 and Fable rows use the current CloudService standard rate; other rows show the current CloudService configured rate. Uncached input and cache writes bill at the published input rate. Provider-reported cached-read input bills at the model’s cached input rate where one is published (a flat $1.00 per 1M on the models priced above it, and the per-model rate listed under Cached input rates for the Gemini, Grok, and Qwen models); on models with no cached rate, cached input bills at that model’s ordinary input rate. The ledger split behind that rule is described in Pricing and accounting architecture, and pack prices are listed in Billing, API credits & token packs.

Swipe horizontally to compare every price column.

Cached input rates

These models publish their own flat cached-read rate instead of the $1.00 per 1M that applies to the models priced above it. The rate covers provider-reported cached-read input only: cache writes and uncached input bill at the model’s ordinary input rate, and the cached rate does not change with context length.

Swipe horizontally to see the cached rate column.

GPT-5.6 long-context pricing

These models have a 1,050,000-token context window and a 128,000-token maximum output. When a request contains more than 272K input tokens, long-context rates apply to the entire request—not only the tokens above the threshold.

Swipe horizontally to compare long-context rates.

Above the threshold, uncached input and output move to the long-context rates; a published cached-input rate is flat and does not change with context length. Internal provider cache prices remain separate from customer billing. Fable standard rows above have no long-context tier.

Choose a model

Use the exact IDs returned by the API. Capability details can vary by provider route, so test the model in your workload before a large rollout.