> For the complete documentation index, see [llms.txt](https://docs.parasail.io/parasail-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.parasail.io/parasail-docs/guides/model-recommendations.md).

# Model Selection

Model availability and capabilities change frequently. Instead of relying on a static recommendation table, use this guide to choose a short list of candidates, check availability with the live models endpoint, and evaluate the models against your own prompts before committing to production.

To list currently available serverless models, use the [`/v1/models` endpoint](/parasail-docs/api-reference/models-endpoint.md).

## Start with the workload

| Workload                              | What to optimize for                                                        | Start here                                                                   |
| ------------------------------------- | --------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
| Chat and text generation              | Instruction following, latency, context length, and cost                    | [Chat and text generation](/parasail-docs/use-cases/chat-text-generation.md) |
| RAG and embeddings                    | Embedding quality, retrieval latency, output size, and batch throughput     | [RAG and embeddings](/parasail-docs/use-cases/rag-embeddings.md)             |
| Batch evaluation or offline inference | Throughput, price, retry handling, and output reconciliation                | [Batch processing](/parasail-docs/use-cases/batch-processing.md)             |
| Agents and tool calling               | Tool-call reliability, structured outputs, multi-turn behavior, and latency | [Agents and tool calling](/parasail-docs/use-cases/agents-tool-calling.md)   |
| Vision and multimodal understanding   | Image input quality, input size, and task success                           | [Multi-Modal](/parasail-docs/guides/multi-modal.md)                          |
| Image generation and editing          | Image quality, edit fidelity, batch throughput, and prompt sensitivity      | [Image Generation](/parasail-docs/products/overview-2.md)                    |

## Choose the right product tier

| Tier                | Best fit                                                                                                            | Notes                                                                                                           |
| ------------------- | ------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------- |
| Serverless          | Fast experiments and production traffic on models already hosted by Parasail                                        | Use the models endpoint to check availability before wiring a model into an application.                        |
| Dedicated Instances | Private models, custom Hugging Face models, predictable capacity, or model settings that need full endpoint control | Start in the UI when possible so the compatibility checker can validate model and hardware choices.             |
| Batch               | Large offline jobs, evaluation sets, embeddings, and workloads that do not need immediate responses                 | Use `custom_id` values so outputs can be matched back to inputs and failed requests can be retried selectively. |

## Check live availability

Use the models endpoint before committing to a model name:

```bash
curl https://api.parasail.io/v1/models \
  -H "Authorization: Bearer $PARASAIL_API_KEY"
```

The response lists the serverless models available to your account. For Dedicated Instances, use the deployment flow or the Dedicated compatibility checks to validate public or private Hugging Face model IDs.

## Evaluate candidates

Use the same representative prompts, documents, tool schemas, or images for every candidate. Track these dimensions:

* **Quality:** task success rate, factuality, formatting reliability, and human review scores.
* **Latency:** time to first token for streaming and total response time for non-streaming calls.
* **Cost:** token usage, output length, deployment size, and whether the workload can run through Batch.
* **Context fit:** maximum input size, retrieval chunk size, and expected output length.
* **Feature support:** structured output, tool calling, multimodal input, streaming, and Responses API support where required.
* **Operational fit:** rate limits, quota requirements, retry behavior, and monitoring needs.

## Run a repeatable evaluation

Use one evaluation set for every candidate model.

1. Collect representative prompts, documents, images, tool schemas, or expected JSON schemas from your product.
2. Run the same inputs through each candidate model.
3. Save the raw request, raw response, latency, token usage, and pass/fail result for each input.
4. Review failures by category: wrong answer, bad format, missing tool call, hallucination, timeout, or cost outlier.
5. Promote only models that meet your quality, latency, cost, and feature-support thresholds.

For small evaluations, call Serverless or Dedicated endpoints directly. For large offline evaluations, use [Batch](/parasail-docs/products/quickstart.md) so you can process many requests at lower cost and retry failed rows by `custom_id`.

For private or fine-tuned models, start with [Dedicated Instances](/parasail-docs/products/overview-1.md) and validate the model ID in the deployment flow before running a full evaluation.

## Validate feature-specific requirements

Some workloads need more than general text quality:

* For JSON or schema-constrained output, test the model with [Structured Output](/parasail-docs/guides/structured-output.md).
* For function calling and agent loops, test the model with [Tool/Function Calling](/parasail-docs/guides/tool-function-calling.md) and the [Responses API](/parasail-docs/products/overview/responses-api.md).
* For multimodal prompts, test with the exact image or document types described in [Multi-Modal](/parasail-docs/guides/multi-modal.md).
* For embeddings, measure retrieval quality on your own corpus before scaling through Batch.

## Next steps

* [Models endpoint](/parasail-docs/api-reference/models-endpoint.md)—list available serverless models
* [Serverless overview](/parasail-docs/products/overview.md)—make interactive OpenAI-compatible calls
* [Dedicated Instances overview](/parasail-docs/products/overview-1.md)—deploy public or private models
* [Batch Quickstart](/parasail-docs/products/quickstart.md)—run large offline jobs