> ## Documentation Index
> Fetch the complete documentation index at: https://cli.terramind.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Available Models
> Complete list of AI models available through Terramind
## Model Overview
Terramind provides access to industry-leading AI models from multiple providers. All models are accessed through the same unified interface.
## Claude Models
Anthropic's Claude models, known for excellent coding and reasoning capabilities.
### claude-sonnet-4-5
**Latest and most capable Claude model**
* **Best for**: Complex coding tasks, detailed analysis, long conversations
* **Context**: Up to 200K tokens
* **Strengths**: Code generation, debugging, technical writing, complex reasoning
* **Speed**: Balanced (medium)
```typescript theme={null}
const result = await generateText({
model: terramind("claude-sonnet-4-5"),
prompt: "Refactor this legacy code to use modern TypeScript patterns",
})
```
### claude-sonnet-4
**Previous generation Sonnet**
* **Best for**: General coding and analysis tasks
* **Context**: Up to 200K tokens
* **Strengths**: Code understanding, documentation, technical explanations
* **Speed**: Balanced (medium)
```typescript theme={null}
const result = await generateText({
model: terramind("claude-sonnet-4"),
prompt: "Explain this algorithm",
})
```
### claude-opus-4-1
**Most powerful Claude model**
* **Best for**: Extremely complex tasks requiring deep reasoning
* **Context**: Up to 200K tokens
* **Strengths**: Research, complex problem solving, academic writing
* **Speed**: Slower but more thorough
* **Cost**: Higher
```typescript theme={null}
const result = await generateText({
model: terramind("claude-opus-4-1"),
prompt: "Design a distributed system architecture for...",
})
```
### claude-haiku-4-5
**Fastest Claude model**
* **Best for**: Quick responses, simple tasks, high-volume requests
* **Context**: Up to 200K tokens
* **Strengths**: Speed, efficiency, cost-effectiveness
* **Speed**: Very fast
* **Cost**: Lower
```typescript theme={null}
const result = await generateText({
model: terramind("claude-haiku-4-5"),
prompt: "Fix this syntax error",
})
```
### claude-3-5-haiku
**Previous generation Haiku**
* **Best for**: Fast responses with good quality
* **Context**: Up to 200K tokens
* **Speed**: Fast
* **Cost**: Lower
```typescript theme={null}
const result = await generateText({
model: terramind("claude-3-5-haiku"),
prompt: "Summarize this code",
})
```
***
## GPT Models
OpenAI's GPT models, known for versatility and strong general capabilities.
### gpt-5
**Latest GPT model**
* **Best for**: General tasks, creative writing, reasoning
* **Context**: Up to 128K tokens
* **Strengths**: Versatility, creativity, general knowledge
* **Speed**: Fast
```typescript theme={null}
const result = await generateText({
model: terramind("gpt-5"),
prompt: "Write a technical blog post about WebAssembly",
})
```
### gpt-5-codex
**Code-specialized GPT**
* **Best for**: Code generation and understanding
* **Context**: Up to 128K tokens
* **Strengths**: Code completion, bug fixing, test generation
* **Speed**: Fast
* **Specialization**: Optimized for programming tasks
```typescript theme={null}
const result = await generateText({
model: terramind("gpt-5-codex"),
prompt: "Generate unit tests for this React component",
})
```
***
## Chinese Models
Leading Chinese AI models with excellent multilingual capabilities.
### glm-4.6
**Zhipu AI's GLM model**
* **Best for**: Chinese language tasks, bilingual content
* **Strengths**: Chinese understanding, translation, cultural context
* **Languages**: Chinese, English, and more
```typescript theme={null}
const result = await generateText({
model: terramind("glm-4.6"),
prompt: "用中文解释这个算法",
})
```
### kimi-k2
**Moonshot AI's Kimi model**
* **Best for**: Long context understanding
* **Context**: Very large context window
* **Strengths**: Long document analysis, Chinese language
```typescript theme={null}
const result = await generateText({
model: terramind("kimi-k2"),
prompt: "分析这个长文档",
})
```
### qwen3-coder
**Alibaba's Qwen coding model**
* **Best for**: Code generation in Chinese/English
* **Strengths**: Programming, Chinese code comments
* **Specialization**: Coding tasks
```typescript theme={null}
const result = await generateText({
model: terramind("qwen3-coder"),
prompt: "编写一个排序算法",
})
```
***
## Specialized Models
### grok-code
**xAI's Grok code model**
* **Best for**: Code analysis and generation
* **Strengths**: Programming tasks, technical analysis
* **Specialization**: Software development
```typescript theme={null}
const result = await generateText({
model: terramind("grok-code"),
prompt: "Analyze this codebase architecture",
})
```
### big-pickle
**Specialized model for specific tasks**
* **Best for**: Domain-specific applications
* **Use case**: Custom enterprise needs
```typescript theme={null}
const result = await generateText({
model: terramind("big-pickle"),
prompt: "Process this domain-specific data",
})
```
***
## Model Comparison
This table helps you choose the right model for your use case.
| Model | Best For | Speed | Cost | Context Window |
| ------------------- | ------------------------ | ------ | ------ | -------------- |
| `claude-sonnet-4-5` | Complex coding, analysis | Medium | Medium | 200K |
| `claude-opus-4-1` | Deep reasoning | Slow | High | 200K |
| `claude-haiku-4-5` | Quick tasks | Fast | Low | 200K |
| `gpt-5` | General tasks | Fast | Medium | 128K |
| `gpt-5-codex` | Code generation | Fast | Medium | 128K |
| `glm-4.6` | Chinese language | Medium | Medium | Large |
| `kimi-k2` | Long documents | Medium | Medium | Very Large |
| `qwen3-coder` | Chinese coding | Fast | Medium | Large |
| `grok-code` | Code analysis | Medium | Medium | Large |
## Choosing the Right Model
### For Coding Tasks
**Complex refactoring or architecture:**
* Use `claude-sonnet-4-5` or `claude-opus-4-1`
**Quick fixes or simple generation:**
* Use `claude-haiku-4-5` or `gpt-5-codex`
**Test generation:**
* Use `gpt-5-codex` or `claude-sonnet-4-5`
### For Chinese Language
**Chinese content:**
* Use `glm-4.6` for general tasks
* Use `qwen3-coder` for coding
* Use `kimi-k2` for long documents
### For Cost Optimization
**High volume, simple tasks:**
* Use `claude-haiku-4-5`
**Important, complex tasks:**
* Use `claude-sonnet-4-5` or `gpt-5`
**Maximum capability:**
* Use `claude-opus-4-1`
## Model-Specific Features
### Long Context
Models with large context windows are better for:
* Analyzing entire codebases
* Processing long documents
* Maintaining conversation history
Best models for long context:
* `claude-sonnet-4-5` (200K)
* `claude-opus-4-1` (200K)
* `kimi-k2` (very large)
### Streaming
All models support streaming for real-time responses:
```typescript theme={null}
const result = await streamText({
model: terramind("claude-sonnet-4-5"),
prompt: "Explain async programming",
})
for await (const chunk of result.textStream) {
process.stdout.write(chunk)
}
```
### Tool Calling
All models support tool/function calling:
```typescript theme={null}
const result = await generateText({
model: terramind("claude-sonnet-4-5"),
prompt: "Calculate the area of a circle with radius 5",
tools: {
calculator: tool({
description: "Perform calculations",
parameters: z.object({ expression: z.string() }),
execute: async ({ expression }) => eval(expression),
}),
},
})
```
## Pricing
Pricing varies by model. Contact Terramind for detailed pricing information.
Generally:
* **Fast models** (Haiku): Lower cost
* **Balanced models** (Sonnet, GPT-5): Medium cost
* **Powerful models** (Opus): Higher cost
Track your usage with:
```bash theme={null}
terramind stats
```
## Model Updates
Models are regularly updated with improvements. To use the latest version, ensure your Terramind package is up to date:
```bash theme={null}
terramind upgrade
```
Or update via npm:
```bash theme={null}
npm update -g terramind
```
## Next Steps
See practical examples for each model
Use models from the command line