Use with Cursor
Access 30+ high-value AI models (DeepSeek, Qwen, Kimi, GLM, Doubao) directly in Cursor. One-time setup, 2 minutes.
Setup
1. Get your API key
Sign up at dragonfly-api.com and create an API key from the Dashboard.
2. Open Cursor Settings
Cmd/Ctrl + Shift + J → Models tab, or: Cursor menu → Settings → Models
3. Add Dragonfly as a provider
Click + Add Model and configure:
- Provider: OpenAI Compatible
- Base URL:
https://dragonfly-api.com/v1 - API Key: Your
sk-df-...key
4. Add models
Add the models you want to use — enter the full model ID:
| Model ID | Best For | Cost |
|---|---|---|
| deepseek/deepseek-chat | General coding, chat | $0.27/1M |
| deepseek/deepseek-reasoner | Complex reasoning, math | $0.55/1M |
| qwen/qwen3-235b-a22b | Multilingual, large context | $1.00/1M |
| moonshot/kimi-k2 | Long-context coding | $1.00/1M |
| doubao/doubao-1.5-pro-256k | Cheapest option | $0.30/1M |
Recommended Setup
- Chat (Cmd+L):
deepseek/deepseek-chat— great coding ability, ultra cheap - Inline Edit (Cmd+K):
doubao/doubao-1.5-pro-256k— fast, cheapest - Complex tasks:
deepseek/deepseek-reasoner— chain-of-thought reasoning
Cost Comparison
| Scenario | Built-in (Claude) | Dragonfly (DeepSeek V3) | Savings |
|---|---|---|---|
| 100 chat messages/day | ~$3/day | ~$0.08/day | 97% |
| Heavy refactoring session | ~$5 | ~$0.15 | 97% |
| Monthly (moderate use) | ~$60 | ~$2 | 97% |
Troubleshooting
Model not found — Use the full model ID (e.g., deepseek/deepseek-chat not just deepseek-chat).
Unauthorized — Check your API key starts with sk-df-.
Use with VS Code
Access high-value AI models in VS Code through Continue, Cody, or any OpenAI-compatible extension.
Option 1: Continue (Recommended)
Continue is the most popular open-source AI coding assistant for VS Code.
Setup
- Install Continue from the VS Code Marketplace
- Open Continue config:
Cmd/Ctrl + Shift + P→ "Continue: Open Config" - Add Dragonfly as a provider in
config.yaml:
models:
- name: DeepSeek V3
provider: openai-compatible
model: deepseek/deepseek-chat
apiBase: https://dragonfly-api.com/v1
apiKey: sk-df-your-key
- name: DeepSeek R1
provider: openai-compatible
model: deepseek/deepseek-reasoner
apiBase: https://dragonfly-api.com/v1
apiKey: sk-df-your-key
- name: Kimi K2
provider: openai-compatible
model: moonshot/kimi-k2
apiBase: https://dragonfly-api.com/v1
apiKey: sk-df-your-key
tabAutocompleteModel:
provider: openai-compatible
model: doubao/doubao-1.5-pro-256k
apiBase: https://dragonfly-api.com/v1
apiKey: sk-df-your-keyOption 2: Cline
Cline is an autonomous AI coding agent for VS Code.
- Install Cline from VS Code Marketplace
- Open Cline settings
- Select OpenAI Compatible as provider
- Set Base URL to
https://dragonfly-api.com/v1, add your API key, and pick a model
Option 3: Any OpenAI-Compatible Extension
- Base URL:
https://dragonfly-api.com/v1 - API Key: Your
sk-df-...key - Model: Any model from our model directory
Why these models for coding?
Troubleshooting
Continue can't connect — Make sure apiBase ends with /v1 (not /v1/).
Model not in dropdown — In Continue, models must be explicitly listed in config. Copy the model IDs exactly.
Use with Windsurf
Windsurf (by Codeium) supports custom OpenAI-compatible providers.
Setup
- Open Windsurf Settings → AI Provider
- Select Custom / OpenAI Compatible
- Configure:
- Base URL:
https://dragonfly-api.com/v1 - API Key:
sk-df-your-key - Model:
deepseek/deepseek-chat
- Base URL:
- Save and start coding
Recommended Models
| Model ID | Best For | Cost |
|---|---|---|
| deepseek/deepseek-chat | Chat & coding | $0.27/1M |
| deepseek/deepseek-reasoner | Complex reasoning | $0.55/1M |
| doubao/doubao-1.5-pro-256k | Autocomplete | $0.30/1M |
Use with Cline
Cline is an autonomous AI coding agent for VS Code.
Setup
- Install Cline from the VS Code Marketplace
- Click the Cline icon in the sidebar
- Open Settings (gear icon)
- Under API Provider, select OpenAI Compatible
- Configure:
- Base URL:
https://dragonfly-api.com/v1 - API Key:
sk-df-your-key - Model ID:
deepseek/deepseek-chat
- Base URL:
- Click Save
Tips
- Autonomous tasks: Use
deepseek/deepseek-chat— good balance of capability and cost - Complex multi-file edits: Use
deepseek/deepseek-reasoner— better reasoning - Max tokens: Set to 4096 for most tasks, 8192 for large refactors
Cost Comparison
| Task | Claude Opus | DeepSeek V3 (Dragonfly) | Savings |
|---|---|---|---|
| Simple bug fix (~2K tokens) | $0.06 | $0.001 | 98% |
| Feature implementation (~10K) | $0.30 | $0.005 | 98% |
| Large refactor (~50K) | $1.50 | $0.025 | 98% |