> For the complete documentation index, see [llms.txt](https://docs.graphlit.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.graphlit.dev/api-guides/use-cases/specifications/specification-create-custom-model.md).

# Create Custom Model Specification

## User Intent

"How do I configure a custom LLM model? Show me specification creation for different models."

## Operation

**SDK Method**: `createSpecification()` with model config\
**Use Case**: Custom model configuration

***

## Code Example (TypeScript)

```typescript
import { Graphlit } from 'graphlit-client';
import {
  SpecificationTypes,
  ModelServiceTypes,
  OpenAIModels,
  AnthropicModels
} from 'graphlit-client/dist/generated/graphql-types';

const graphlit = new Graphlit();

// GPT-4 specification
const gpt4Spec = await graphlit.createSpecification({
  name: "GPT-4 High Quality",
  type: SpecificationTypes.Completion,
  serviceType: ModelServiceTypes.OpenAi,
  openAI: {
    model: OpenAIModels.Gpt4,
    temperature: 0.7,
    maxTokens: 2000
  }
});

// Claude 3.5 Sonnet specification
const claudeSpec = await graphlit.createSpecification({
  name: "Claude 3.5 Fast",
  type: SpecificationTypes.Completion,
  serviceType: ModelServiceTypes.Anthropic,
  anthropic: {
    model: AnthropicModels.Claude_3_5Sonnet,
    temperature: 0.5,
    maxTokens: 4000
  }
});

// Use in workflow or conversation
const workflow = await graphlit.createWorkflow({
  name: "High Quality Extraction",
  specification: { id: gpt4Spec.createSpecification.id },
  extraction: { /* ... */ }
});
```

***

## Key Parameters

**temperature**: Creativity (0.0-1.0)\
**maxTokens**: Response length limit\
**topP**: Nucleus sampling\
**model**: Specific model version

***


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.graphlit.dev/api-guides/use-cases/specifications/specification-create-custom-model.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.