Supported Providers
| Provider | API Endpoint | Key Setup |
|---|---|---|
| OpenCode Go | opencode.ai/zen/go/v1 | OpenCode subscription |
| OpenCode Zen | opencode.ai/zen/v1 | OpenCode subscription |
| DeepSeek | api.deepseek.com/v1 | DeepSeek Platform |
How Model Lists Work
Ignite caches available models in a local SQLite database on startup. Models refresh automatically every 15 minutes in the background. If you haven't configured an API key yet, Ignite shows a default model list so you can still browse and plan before setting up your provider.
Available Models by Provider
OpenCode Go
Without an API key, the following models appear by default. With a key configured, the live model list replaces these on the next sync.
| GLM-5.2 | Zhipu AI's flagship model |
| GLM-5.1 | Zhipu AI's prior generation |
| Kimi K2.7 Code | Moonshot AI's code-focused model |
| Kimi K2.6 | Moonshot AI's general purpose model |
| MiMo-V2.5 | Minimax's balanced multimodal |
| MiMo-V2.5-Pro | Minimax's most capable variant |
| MiniMax M3 | MiniMax's latest generation |
| MiniMax M2.7 | MiniMax's previous generation |
| Qwen3.7 Max | Alibaba's frontier model |
| Qwen3.7 Plus | Alibaba's balanced variant |
| Qwen3.6 Plus | Alibaba's prior generation |
| DeepSeek V4 Pro | DeepSeek's frontier tier (49B active) |
| DeepSeek V4 Flash | DeepSeek's fast tier |
OpenCode Zen
Curated selection of GPT-5, Claude, Gemini, Grok, and DeepSeek models. Without an API key, the following models appear by default. With a key configured, the live model list replaces these on the next sync.
| GPT-5.5 | OpenAI's latest flagship |
| GPT-5.5 Pro | OpenAI's most powerful |
| GPT-5.4 | GPT-5.4 generation |
| GPT-5.4 Pro | GPT-5.4 enhanced |
| GPT-5.4 Mini | GPT-5.4 compact |
| GPT-5.4 Nano | GPT-5.4 smallest |
| GPT-5.3 Codex | Code-focused generation |
| GPT-5.2 | Prior generation |
| GPT-5.1 | Stable release |
| GPT-5.1 Codex | Codex generation |
| GPT-5 | Legacy GPT-5 |
| GPT-5 Codex | Legacy codex |
| GPT-5 Nano | Fastest GPT-5 |
| Claude Fable 5 | Anthropic frontier |
| Claude Opus 4.8 | Latest Opus |
| Claude Opus 4.5 | Stable Opus |
| Claude Sonnet 4.5 | Latest Sonnet |
| Claude Sonnet 4 | Stable Sonnet |
| Claude Haiku 4.5 | Fast Claude |
| Gemini 3.5 Flash | Latest Gemini |
| Gemini 3.1 Pro | Stable Gemini |
| Gemini 3 Flash | Fast Gemini |
| Grok Build 0.1 | xAI's model |
| DeepSeek V4 Pro | DeepSeek frontier |
| DeepSeek V4 Flash | DeepSeek fast |
| GLM-5.2 | Zhipu AI |
| GLM-5.1 | Zhipu prior gen |
| GLM-5 | Zhipu legacy |
DeepSeek
| DeepSeek Flash | Fast inference, 1M context, $0.14/$0.28 per 1M input/output |
| DeepSeek Pro | Frontier reasoning, 1M context, $0.435/$0.87 per 1M (75% permanent discount) |
API Key Security
All API keys are stored in your OS keychain (macOS Keychain), never in plaintext configuration files. Ignite reads keys from the keychain at runtime. The ~/.ignite/config.json file stores only provider metadata and preferences — no secrets.