# CanopyWave

CanopyWave serves 13 text models on LLM API from DeepSeek, Moonshot AI, Z.ai and 2 other labs.

Model ID prefix: `canopywave/` · 13 models · 5 labs
Updated: 2026-10-27
Canonical: https://llmapi.ai/providers/canopywave/

## Models and prices

Prices when CanopyWave serves the request. A value in brackets is the price before the discount.

### Text (13)

Prices per 1M tokens.

| Model | Model ID | Input | Output | Cache read | Context |
| --- | --- | --- | --- | --- | --- |
| [DeepSeek V4 Pro](https://llmapi.ai/models/deepseek-deepseek-v4-pro/) (−10%) | `canopywave/deepseek-v4-pro` | $1.188 (list $1.32) | $3.564 (list $3.96) | $0.108 (list $0.12) | 1M |
| [DeepSeek V4.1 Flash](https://llmapi.ai/models/deepseek-deepseek-v4-1-flash/) | `canopywave/deepseek/deepseek-v4.1-flash` | $0.3 | $1.2 | $0.006 | 1M |
| [Kimi K3](https://llmapi.ai/models/moonshotai-kimi-k3/) | `canopywave/kimi-k3` | $3 | $15 | $0.3 | 1M |
| [Kimi K2.7-Code](https://llmapi.ai/models/moonshotai-kimi-k2-7-code/) | `canopywave/kimi-k2.7-code` | $0.95 | $4 | $0.19 | 262K |
| [Qwen3.8 Flash Next](https://llmapi.ai/models/alibaba-qwen3-8-flash-next/) | `canopywave/qwen3.8-flash-next` | $0.201 | $0.5 | $0.05 | 262K |
| [GLM-5.3](https://llmapi.ai/models/zhipu-glm-5-3/) | `canopywave/glm-5.3` | $1.4 | $4.4 | $0.26 | 1M |
| [GLM-5.3-Flash](https://llmapi.ai/models/zhipu-glm-5-3-flash/) | `canopywave/glm-5.3-flash` | $0.15 | $0.5 | $0.03 | 1M |
| [DeepSeek V4.1 Flash 1017](https://llmapi.ai/models/deepseek-v4-1-flash-1017/) | `canopywave/deepseek-v4.1-flash-1017` | $0.3 | $1.2 | $0.04 | 1M |
| [DeepSeek V4 Flash 0731](https://llmapi.ai/models/deepseek-v4-flash-0731/) (−10%) | `canopywave/deepseek-v4-flash-0731` | $0.396 (list $0.44) | $1.188 (list $1.32) | $0.036 (list $0.04) | 1M |
| [GLM 5.2](https://llmapi.ai/models/zhipu-zai-glm-5-2/) (−15%) | `canopywave/zai-glm-5.2` | $1.19 (list $1.4) | $3.74 (list $4.4) | $0.221 (list $0.26) | 1M |
| [Kimi K2.7 Code HighSpeed](https://llmapi.ai/models/moonshotai-kimi-k2-7-code-highspeed/) | `canopywave/kimi-k2.7-code-highspeed` | $1.9 | $8 | $0.38 | 262K |
| [MiniMax M3](https://llmapi.ai/models/minimax-m3/) (−5%) | `canopywave/minimax-m3` | $0.3373 (list $0.355) | $1.6862 (list $1.775) | $0.0845 (list $0.089) | 512K |
| [Kimi K2.6](https://llmapi.ai/models/moonshotai-kimi-k2-6/) (−10%) | `canopywave/kimi-k2.6` | $0.855 (list $0.95) | $3.6 (list $4) | $0.144 (list $0.16) | 262K |

**Volume pricing.** At higher monthly volume, models on CanopyWave may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Send requests to CanopyWave

Put `canopywave/` before a model ID and the request goes to CanopyWave. If CanopyWave’s uptime over the last 5 minutes is below 90%, it goes to another provider of the model, unless it sends `X-No-Fallback: true`. [Routing docs](https://docs.llmapi.ai/features/routing)

Example: DeepSeek V4 Pro, Chat Completions (`POST /v1/chat/completions`). Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="canopywave/deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Prices synced 2026-10-27.

Next step: [Get API key](https://app.llmapi.ai/signup)