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

# Flatkey Model Directory: All 160+ Supported Models

> Browse all AI models available through Flatkey including GPT, Claude, Gemini, DeepSeek, Qwen, and GLM — with official and after-bonus pricing per million tokens.

Flatkey provides access to 160+ official models across all major AI providers. Prices shown are per 1 million input tokens. The **after-bonus** column reflects effective pricing when you top up at the $200 tier (which includes $100 free bonus credit on top of model discounts).

<Note>
  Model availability and pricing may change as vendors update their APIs. For the most current list including latency and health data, visit [flatkey.ai/models](https://flatkey.ai/models).
</Note>

## OpenAI

| Model          | Official (\$/1M in) | After-bonus (\$/1M in) | Best for                              |
| -------------- | ------------------- | ---------------------- | ------------------------------------- |
| `gpt-4o`       | \$2.50              | \$1.50                 | Complex reasoning, vision, multimodal |
| `gpt-4o-mini`  | \$0.15              | \$0.09                 | Fast, cost-efficient text tasks       |
| `gpt-4.1-mini` | \$0.40              | \$0.24                 | Balanced quality and speed            |
| `gpt-5.5`      | \$5.00              | \$3.00                 | Frontier reasoning and generation     |
| `gpt-5.4`      | \$2.50              | \$1.50                 | Latest-generation GPT                 |
| `gpt-5-mini`   | \$0.04              | \$0.024                | Ultra-low-cost simple tasks           |
| `gpt-image-2`  | \$6.65              | \$3.99                 | Image generation                      |

## Anthropic

| Model                       | Official (\$/1M in) | After-bonus (\$/1M in) | Best for                            |
| --------------------------- | ------------------- | ---------------------- | ----------------------------------- |
| `claude-opus-4-5`           | \$5.00              | \$3.00                 | Complex writing, research, analysis |
| `claude-sonnet-4-5`         | \$3.00              | \$1.80                 | Balanced quality and speed          |
| `claude-sonnet-4-6`         | \$3.00              | \$1.80                 | Latest-generation Sonnet            |
| `claude-sonnet-5`           | \$2.00              | \$1.20                 | Latest generation Claude            |
| `claude-haiku-4-5-20251001` | \$1.00              | \$0.60                 | Fast, cost-efficient tasks          |

## Google

| Model                    | Official (\$/1M in) | After-bonus (\$/1M in) | Best for                        |
| ------------------------ | ------------------- | ---------------------- | ------------------------------- |
| `gemini-2.5-pro`         | \$1.125             | \$0.675                | Complex reasoning, long context |
| `gemini-2.5-flash`       | \$0.09              | \$0.054                | Fast, affordable generalist     |
| `gemini-2.5-flash-lite`  | \$0.09              | \$0.054                | Minimal latency, lowest cost    |
| `gemini-3-flash-preview` | \$0.07              | \$0.042                | Next-gen flash preview          |
| `gemini-embedding-001`   | \$0.15              | \$0.09                 | Text embeddings                 |
| `gemini-2.5-flash-image` | \$0.30              | \$0.18                 | Image understanding             |
| `gemini-3-pro-image`     | \$2.00              | \$1.20                 | High-quality image generation   |

## DeepSeek

| Model               | Official (\$/1M in) | After-bonus (\$/1M in) | Best for                     |
| ------------------- | ------------------- | ---------------------- | ---------------------------- |
| `deepseek-v3`       | \$0.40              | \$0.24                 | Cost-effective general tasks |
| `deepseek-v3.1`     | \$0.21              | \$0.126                | Updated V3 variant           |
| `deepseek-v4-pro`   | \$2.40              | \$1.44                 | Frontier DeepSeek reasoning  |
| `deepseek-v4-flash` | \$0.14              | \$0.084                | Fast, cheap DeepSeek         |

## Qwen

| Model               | Official (\$/1M in) | After-bonus (\$/1M in) | Best for                 |
| ------------------- | ------------------- | ---------------------- | ------------------------ |
| `qwen3.7-max`       | \$2.50              | \$1.50                 | Frontier Qwen generation |
| `qwen3.5-plus`      | \$0.40              | \$0.24                 | Balanced quality         |
| `qwen3.5-flash`     | \$0.10              | \$0.06                 | Fast, cheap tasks        |
| `qwen3.5-397b-a17b` | \$0.43              | \$0.258                | Large MoE model          |

## Z.ai / GLM

| Model         | Official (\$/1M in) | After-bonus (\$/1M in) | Best for               |
| ------------- | ------------------- | ---------------------- | ---------------------- |
| `glm-4.7`     | \$0.286             | \$0.172                | General-purpose GLM    |
| `glm-5-turbo` | \$0.72              | \$0.432                | High-speed GLM variant |
| `glm-5.2`     | \$1.40              | \$0.84                 | Latest GLM generation  |

## Using model IDs

All models use their canonical vendor IDs. Pass the model ID in the `model` field of your request:

```python python theme={null}
response = client.chat.completions.create(
    model="gemini-2.5-flash",  # Google Gemini via Flatkey
    messages=[{"role": "user", "content": "Hello!"}],
)
```

For the complete list including all variants and real-time health data, visit [flatkey.ai/models](https://flatkey.ai/models).