Skip to content

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.

  • 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
Provider
Category
Cost

OpenCode Zen

7 models

ModelIDCategoryCostContextZen API
DeepSeek V4 Flash Free
Free DeepSeek coding model with a large context window.
deepseek-v4-flash-freefastFree1.0Mopenai-compatible
GPT 5 Nano
Lowest-cost GPT for quick edits and simple commands.
gpt-5-nanofastLower-cost400Kopenai-responses
Claude Haiku 4.5
Fast Claude model for quick command generation.
claude-haiku-4-5fastLower-cost200Kanthropic
Gemini 3.5 Flash
Fast Gemini model with a large context window.
gemini-3.5-flashfastLower-cost1.0Mgoogle
Claude Sonnet 4.6
Balanced Claude model for harder coding tasks.
claude-sonnet-4-6smartPremium1Manthropic
GPT 5.5
Flagship GPT model for complex shell tasks.
gpt-5.5smartPremium1.1Mopenai-responses
Claude Opus 4.8
Top Claude reasoning model for complex tasks.
claude-opus-4-8reasoningPremium1Manthropic

OpenRouter

8 models

ModelIDCategoryCostContext
DeepSeek V4 Flash (Free)
Fast DeepSeek coding model on OpenRouter's free tier.
deepseek/deepseek-v4-flash:freefastFree1.0M
DeepSeek V4 Flash
Fast DeepSeek coding model with a large context window.
deepseek/deepseek-v4-flashfastLower-cost1.0M
GLM 5.2
Fast GLM model for low-cost command generation.
z-ai/glm-5.2fastLower-cost203K
Kimi K2.7 Code
Open-weight coding model for larger code tasks.
moonshotai/kimi-k2.7-codesmartLower-cost262K
DeepSeek V4 Pro
High-context DeepSeek model for larger code tasks.
deepseek/deepseek-v4-prosmartLower-cost1.0M
Claude Sonnet 4.6
Balanced Claude model for harder coding tasks.
anthropic/claude-sonnet-4.6smartPremium1M
GPT 5.5
Flagship GPT model for complex shell tasks.
openai/gpt-5.5smartPremium1.1M
Claude Opus 4.8
Top Claude reasoning model for complex tasks.
anthropic/claude-opus-4.8reasoningPremium1M

Vercel AI Gateway

3 models

ModelIDCategoryCostContext
GPT 5.5
Flagship GPT model for complex shell tasks.
openai/gpt-5.5smartPremium1.1M
Claude Sonnet 4.6
Balanced Claude model for harder coding tasks.
anthropic/claude-sonnet-4.6smartPremium1M
Claude Opus 4.8
Top Claude reasoning model for complex tasks.
anthropic/claude-opus-4.8reasoningPremium1M

Cloudflare AI Gateway

4 models

ModelIDCategoryCostContext
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-fastsmartLower-cost24K
GPT 5.5
Flagship GPT model for complex shell tasks. through Cloudflare AI Gateway
openai/gpt-5.5smartPremium1.1M
Claude Sonnet 4.6
Balanced Claude model for harder coding tasks. through Cloudflare AI Gateway
anthropic/claude-sonnet-4-6smartPremium1M
Claude Opus 4.8
Top Claude reasoning model for complex tasks. through Cloudflare AI Gateway
anthropic/claude-opus-4-8reasoningPremium1M

Cloudflare Workers AI

3 models

ModelIDCategoryCostContext
Llama 3.1 8B Instruct
Cloudflare Workers AI lightweight Llama instruct model
@cf/meta/llama-3.1-8b-instructfastLower-cost8K
Llama 3.3 70B Fast
Cloudflare Workers AI fast Llama instruct model
@cf/meta/llama-3.3-70b-instruct-fp8-fastsmartLower-cost24K
GPT OSS 120B
OpenAI open-weight model hosted by Cloudflare Workers AI
@cf/openai/gpt-oss-120breasoningLower-cost32K