Home/Models

Models

Clew supports 100+ models across 27 providers. Pick the right model for each task — from frontier reasoning to fast local inference.

Model Selection Guide

WorkloadRecommended ModelsContextNotes
Complex architecture & large editsclaude-opus-4-7, claude-sonnet-4-6, gpt-5.5, deepseek-v4-pro1M tokensBest tool calling, strong reasoning, largest context
Code review & debuggingclaude-sonnet-4-6, gpt-5.5, gemini-3.1-pro1M-2M tokensGood instruction following, reliable output
Quick search & summarizationclaude-haiku-4-5, deepseek-v4-flash, mistral-small-4, groq/llama-3.3-70b128K-200KFast, cost-effective, lower latency
Offline / air-gappedollama/llama4:70b, ollama/llama3.3131K tokensFully local, no network needed
Cost-sensitive bulkkilocode/kilo-auto/free, opencode-go/minimax-m2.7, groq/llama-3.1-8bVariesFree or minimal cost tiers available
Research & reasoningclaude-opus-4-7, deepseek-v4-pro, gemini-3.1-pro1M-2M tokensDeep reasoning, chain-of-thought
Vision / multimodalclaude-sonnet-4-6, gpt-5.5, gemini-3.1-pro, deepseek-v4-flash1M tokensImage understanding, document analysis

Notable Models by Provider

ProviderModels Available
Anthropicclaude-opus-4-7 (1M ctx), claude-sonnet-4-6 (1M ctx, recommended), claude-haiku-4-5 (200K ctx, fast)
OpenAIgpt-5.5 (1M ctx), gpt-5.4 (1M ctx), gpt-5.4-mini (fast)
Googlegemini-3.1-pro (2M ctx), gemini-3.1-flash-lite (1M ctx, fast)
DeepSeekdeepseek-v4-pro (1M ctx, MoE), deepseek-v4-flash (1M ctx, fast MoE)
xAIgrok-4.3 (128K ctx)
Mistralmistral-medium-3.5, mistral-small-4, mistral-large-3
Groqllama-3.3-70b, llama-3.1-8b-instant (fast)
Ollamallama4:70b (local), llama3.3 (local), qwen3.6-plus (local)
GitHub Copilotclaude-opus-4.7, claude-sonnet-4.6, claude-haiku-4.5, gpt-5.5
OpenCodeclaude-opus-4-7, claude-sonnet-4-6, gpt-5.5, gemini-3.1-pro, kimi-k2.6
KiloCodekilo-auto/free, kilo-auto/balanced, kilo-auto/frontier
Coherecommand-a-plus (128K ctx)
Perplexitysonar-pro, sonar, sonar-reasoning-pro
Together AIdeepseek-v4, Qwen3.6, Llama-4
NVIDIA NIMdeepseek-v4-pro, glm-5.1, nemotron-3
Cerebrasqwen-3-235b (extremely fast)
Moonshot (Kimi)kimi-k2.6 (128K ctx)
Zhipu (GLM)glm-4.7 (128K ctx)
Hugging Facellama-3.3-70b-instruct
Poeclaude-3-7-sonnet

Model Switching

/model                          # Interactive picker (recent models at top, grouped by provider)
/model list                     # List all available models
/model claude-sonnet-4-7        # Switch by full ID
/model sonnet                   # Alias-based switching
--model opus                    # CLI flag at startup

The picker shows all models from every provider in named sections — not just the active provider's models. Recent models appear at top with the active provider's default. Select any model from any provider directly.

Model switching is instant — the next conversation turn uses the new model. Previous context is preserved.

Model Aliases

Short aliases are resolved to full model IDs: sonnet, opus, haiku, gpt5, flash, etc.

CLI Flags for Models

FlagDescription
--model <name>Set model at startup (e.g., --model sonnet or --model claude-opus-4-7)
--effort <level>Set reasoning effort: low, medium, high, max
--max-turns <N>Limit agentic turns in non-interactive mode
--thinking <mode>Thinking mode: enabled, adaptive, disabled
--fallback-model <model>Fallback when primary model is overloaded (print mode only)
--task-budget <tokens>API-side task budget in tokens
--max-budget-usd <amount>Maximum spend on API calls (print mode only)

Model Capabilities

Each model declaration in providers.json includes:

  • Model ID and display label
  • Context window (maxContext) and max output tokens (maxOutput)
  • Tool calling type (native, none)
  • Vision support
  • Streaming mode (full, partial)
  • Reasoning support
  • System prompt support
  • Tags (for filtering): fast, verified, recommended, latest, free, vision, tools, native, moe, local