Models
Every model Magic Shell can route to, grouped by provider. The list below is generated from src/lib/models.ts at build time, so it always matches what the CLI ships.
Cost legend
Section titled “Cost legend”- Free — no-cost model (may be time-limited)
- Lower-cost — open-weight, flash, or haiku-class model
- Premium — flagship or high-capability model
Use the filter panel to narrow by provider, category, or cost. The msh --models command lists only the models available for your currently configured provider.
Free no-cost model (may be time-limited)Lower-cost open-weight, flash, or haiku-classPremium flagship or high-capability
Filter by provider & category
OpenCode Zen
| Model | ID | Category | Cost | Context | Zen API |
|---|---|---|---|---|---|
DeepSeek V4 Flash Free Free DeepSeek coding model with a large context window. | deepseek-v4-flash-free | fast | Free | 1.0M | openai-compatible |
GPT 5 Nano Lowest-cost GPT for quick edits and simple commands. | gpt-5-nano | fast | Lower-cost | 400K | openai-responses |
Claude Haiku 4.5 Fast Claude model for quick command generation. | claude-haiku-4-5 | fast | Lower-cost | 200K | anthropic |
Gemini 3.5 Flash Fast Gemini model with a large context window. | gemini-3.5-flash | fast | Lower-cost | 1.0M | google |
Claude Sonnet 4.6 Balanced Claude model for harder coding tasks. | claude-sonnet-4-6 | smart | Premium | 1M | anthropic |
GPT 5.5 Flagship GPT model for complex shell tasks. | gpt-5.5 | smart | Premium | 1.1M | openai-responses |
Claude Opus 4.8 Top Claude reasoning model for complex tasks. | claude-opus-4-8 | reasoning | Premium | 1M | anthropic |
| No models match these filters. | |||||
OpenRouter
| Model | ID | Category | Cost | Context |
|---|---|---|---|---|
DeepSeek V4 Flash (Free) Fast DeepSeek coding model on OpenRouter's free tier. | deepseek/deepseek-v4-flash:free | fast | Free | 1.0M |
DeepSeek V4 Flash Fast DeepSeek coding model with a large context window. | deepseek/deepseek-v4-flash | fast | Lower-cost | 1.0M |
GLM 5.2 Fast GLM model for low-cost command generation. | z-ai/glm-5.2 | fast | Lower-cost | 203K |
Kimi K2.7 Code Open-weight coding model for larger code tasks. | moonshotai/kimi-k2.7-code | smart | Lower-cost | 262K |
DeepSeek V4 Pro High-context DeepSeek model for larger code tasks. | deepseek/deepseek-v4-pro | smart | Lower-cost | 1.0M |
Claude Sonnet 4.6 Balanced Claude model for harder coding tasks. | anthropic/claude-sonnet-4.6 | smart | Premium | 1M |
GPT 5.5 Flagship GPT model for complex shell tasks. | openai/gpt-5.5 | smart | Premium | 1.1M |
Claude Opus 4.8 Top Claude reasoning model for complex tasks. | anthropic/claude-opus-4.8 | reasoning | Premium | 1M |
| No models match these filters. | ||||
Vercel AI Gateway
| Model | ID | Category | Cost | Context |
|---|---|---|---|---|
GPT 5.5 Flagship GPT model for complex shell tasks. | openai/gpt-5.5 | smart | Premium | 1.1M |
Claude Sonnet 4.6 Balanced Claude model for harder coding tasks. | anthropic/claude-sonnet-4.6 | smart | Premium | 1M |
Claude Opus 4.8 Top Claude reasoning model for complex tasks. | anthropic/claude-opus-4.8 | reasoning | Premium | 1M |
| No models match these filters. | ||||
Cloudflare AI Gateway
| Model | ID | Category | Cost | Context |
|---|---|---|---|---|
Workers AI Llama 3.3 70B Fast Cloudflare Workers AI fast Llama model routed through AI Gateway | workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast | smart | Lower-cost | 24K |
GPT 5.5 Flagship GPT model for complex shell tasks. through Cloudflare AI Gateway | openai/gpt-5.5 | smart | Premium | 1.1M |
Claude Sonnet 4.6 Balanced Claude model for harder coding tasks. through Cloudflare AI Gateway | anthropic/claude-sonnet-4-6 | smart | Premium | 1M |
Claude Opus 4.8 Top Claude reasoning model for complex tasks. through Cloudflare AI Gateway | anthropic/claude-opus-4-8 | reasoning | Premium | 1M |
| No models match these filters. | ||||
Cloudflare Workers AI
| Model | ID | Category | Cost | Context |
|---|---|---|---|---|
Llama 3.1 8B Instruct Cloudflare Workers AI lightweight Llama instruct model | @cf/meta/llama-3.1-8b-instruct | fast | Lower-cost | 8K |
Llama 3.3 70B Fast Cloudflare Workers AI fast Llama instruct model | @cf/meta/llama-3.3-70b-instruct-fp8-fast | smart | Lower-cost | 24K |
GPT OSS 120B OpenAI open-weight model hosted by Cloudflare Workers AI | @cf/openai/gpt-oss-120b | reasoning | Lower-cost | 32K |
| No models match these filters. | ||||