> ## Documentation Index
> Fetch the complete documentation index at: https://docs.geekhub.mx/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat models

> 17 models for conversation and reasoning

| ID                            | Provider  | Context | Input \$/1M | Output \$/1M | Best for                      |
| ----------------------------- | --------- | ------- | ----------- | ------------ | ----------------------------- |
| `anthropic/claude-opus-4-8`   | Anthropic | 200k    | \$15        | \$75         | Deep reasoning, complex code  |
| `anthropic/claude-sonnet-4-6` | Anthropic | 200k    | \$3         | \$15         | Sweet spot price/quality      |
| `anthropic/claude-haiku-4-5`  | Anthropic | 200k    | \$1         | \$5          | Simple tasks, high volume     |
| `google/gemini-2.5-pro`       | Google    | 1M      | \$1.25      | \$5          | Long context, multimodal      |
| `google/gemini-2.5-flash`     | Google    | 1M      | \$0.15      | \$0.60       | Cheapest in catalog           |
| `openai/gpt-5`                | OpenAI    | 400k    | \$1.25      | \$10         | General reasoning             |
| `openai/gpt-4.1`              | OpenAI    | 1M      | \$2         | \$8          | Long context                  |
| `openai/gpt-4.1-mini`         | OpenAI    | 1M      | \$0.40      | \$1.60       | Cheap OpenAI                  |
| `openai/o4-mini`              | OpenAI    | 200k    | \$1.10      | \$4.40       | Reasoning (CoT)               |
| `deepseek/deepseek-chat`      | DeepSeek  | 64k     | \$0.27      | \$1.10       | Open-weight, very cheap       |
| `deepseek/deepseek-reasoner`  | DeepSeek  | 64k     | \$0.55      | \$2.19       | Open-weight reasoning         |
| `moonshot/kimi-k2`            | Moonshot  | 256k    | \$0.60      | \$2.50       | Chinese model, strong at code |
| `moonshot/moonshot-v1-128k`   | Moonshot  | 128k    | \$1.66      | \$1.66       | Symmetric cost                |
| `xai/grok-4`                  | xAI       | 256k    | \$3         | \$15         | Access to X data              |
| `xai/grok-3`                  | xAI       | 131k    | \$3         | \$15         | Previous gen                  |
| `xai/grok-3-mini`             | xAI       | 131k    | \$0.30      | \$0.50       | Cheap xAI                     |

## When to use each

### For critical tasks with budget

**Claude Opus 4.8** or **GPT-5**. Top of class in reasoning.

### For production at scale

**Claude Sonnet 4.6**. Price/quality balance. You'd pick it blind if you didn't know the rest.

### For high volume / low cost

**Gemini 2.5 Flash** or **DeepSeek Chat**. Sub-dollar per 1M tokens.

### For reasoning (chain of thought, step-by-step)

**DeepSeek Reasoner** or **o4-mini**. Specifically designed for structured reasoning.

### For very long context

**Gemini 2.5 Pro/Flash** (1M tokens) or **GPT-4.1** (1M). Process entire documents.

### For code

**Kimi K2** or **Claude Sonnet 4.6**. Strong code performance.

## Natural failover

Because all models share the same endpoint and SDK, **failover across providers is trivial**:

```python theme={null}
def call_with_fallback(messages):
    for model in ["anthropic/claude-sonnet-4-6", "openai/gpt-5", "google/gemini-2.5-pro"]:
        try:
            return client.chat.completions.create(model=model, messages=messages)
        except Exception:
            continue
    raise RuntimeError("All providers failed")
```