AxAIOpenAIUsage

type AxAIOpenAIUsage = object;

Defined in: https://github.com/ax-llm/ax/blob/3d5aa8dac28a2637e4150f022dcd02e6fc3309f0/src/ax/ai/openai/chat_types.ts#L129

Properties

completion_tokens

completion_tokens: number;

Defined in: https://github.com/ax-llm/ax/blob/3d5aa8dac28a2637e4150f022dcd02e6fc3309f0/src/ax/ai/openai/chat_types.ts#L131

completion_tokens_details?

optional completion_tokens_details: object;

Defined in: https://github.com/ax-llm/ax/blob/3d5aa8dac28a2637e4150f022dcd02e6fc3309f0/src/ax/ai/openai/chat_types.ts#L143

reasoning_tokens?

optional reasoning_tokens: number;

prompt_tokens

prompt_tokens: number;

Defined in: https://github.com/ax-llm/ax/blob/3d5aa8dac28a2637e4150f022dcd02e6fc3309f0/src/ax/ai/openai/chat_types.ts#L130

prompt_tokens_details?

optional prompt_tokens_details: object;

Defined in: https://github.com/ax-llm/ax/blob/3d5aa8dac28a2637e4150f022dcd02e6fc3309f0/src/ax/ai/openai/chat_types.ts#L134

cache_write_tokens?

optional cache_write_tokens: number;

Prompt tokens written to the cache on this request, billed at a premium over uncached input. Sits alongside cached_tokens, and prompt_tokens includes both — see usage.ts, which subtracts them back out.

cached_tokens?

optional cached_tokens: number;

service_tier?

optional service_tier: string;

Defined in: https://github.com/ax-llm/ax/blob/3d5aa8dac28a2637e4150f022dcd02e6fc3309f0/src/ax/ai/openai/chat_types.ts#L133

total_tokens

total_tokens: number;

Defined in: https://github.com/ax-llm/ax/blob/3d5aa8dac28a2637e4150f022dcd02e6fc3309f0/src/ax/ai/openai/chat_types.ts#L132