# tinker.types.SampleResponse

## _class_ [**tinker.types.SampleResponse**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/sample_response.py#L18)()

Response from a sampling request.

Contains generated sequences and optional prompt-level log probabilities.
Numpy fields provide direct array access without format conversion.
The corresponding Python-list properties convert lazily on first access.

**Fields:**

- [**sequences**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/sample_response.py#L26) ( _Sequence[ [SampledSequence](https://tinker-docs.thinkingmachines.ai/tinker/api-reference/types/sampledsequence/)_ ) – Generated sequences. Each contains token IDs, optional logprobs, and stop reason.
- [**prompt_logprobs_np**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/sample_response.py#L29) ( _Optional[np.ndarray]_ ) – Per-token log probabilities for the prompt as a 1-D float32 numpy array, shape `(prompt_length,)`. `NaN` at positions where logprobs were not computed (e.g. the first prompt token). None if prompt logprobs were not requested.
- [**topk_prompt_logprobs_np**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/sample_response.py#L35) ( _Optional[ [TopkPromptLogprobs](https://tinker-docs.thinking-machines.ai/tinker/api-reference/types/topkpromptlogprobs/)_ ) – Top-k prompt logprobs as a pair of dense matrices (see [`TopkPromptLogprobs`](https://tinker-docs.thinking-machines.ai/tinker/api-reference/types/topkpromptlogprobs/)). None if top-k was not requested.
- [**prompt_cache_hit_tokens**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/sample_response.py#L40) ( _int_ ) – Number of prompt tokens billed as prefix-cache hits.

Counted on the prompt itself: for `num_samples > 1` the prompt is shared, so this is not multiplied across samples. Prefill on the shared prompts samples (the remaining `num_samples - 1`) is billed as cache hits.

### [**prompt_logprobs**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/sample_response.py#L54)()

Per-token log probabilities for the prompt as a Python list.

If prompt_logprobs was set to true in the request, logprobs are computed for every token in the prompt. Each entry is a float, or `None` for positions where logprobs were not computed (e.g. the first prompt token). Returns `None` if prompt logprobs were not requested.

Converted from `prompt_logprobs_np` on first access (cached afterwards).

**Returns:** _Optional[List[Optional[float]]]_

### [**topk_prompt_logprobs**](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/types/sample_response.py#L75)()

Top-k prompt logprobs as nested Python lists.

If topk_prompt_logprobs was set to a positive integer k in the request, the top-k logprobs are computed for every token in the prompt.
For each prompt position: a list of up to k `(token_id, logprob)` tuples, or `None` for positions where logprobs were not computed. Returns `None` if top-k was not requested.

Converted from `topk_prompt_logprobs_np` on first access (cached afterwards).

**Returns:** _Optional[ [list](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/cli/commands/run.py#L221)[Optional[ [list](https://github.com/thinking-machines-lab/tinker/blob/main/src/tinker/cli/commands/run.py#L221)[tuple[int, float]]]]_