# Model slugs One canonical slug per model, across every vendor. `log.csv`'s `model` column holds a slug from this table and nothing else. ## The slug ``` - ``` Lowercase, hyphens, no spaces, dots normalized to hyphens. Where the vendor's own id already carries the prefix (Anthropic ships `claude-*`) the slug is that id unchanged. **Using a model that is not listed here? Mint its slug and add the row on that model's first use, before writing the log row.** Never mint a second slug for a model that already has one. Never delete a row — old log entries still point at it; mark it retired in the notes instead. `effort` lists the reasoning-effort values the model accepts, or `none` when it has no such setting. Whatever you actually ran with goes in the log's `effort` column. `none` in the table means `none` in the log. Rows marked **?** could not be confirmed against vendor docs. Correct them the next time you use the model. ## anthropic | slug | model | effort | |------|-------|--------| | `claude-opus-5` | Claude Opus 5 | low, medium, high, xhigh, max | | `claude-fable-5` | Claude Fable 5 | low, medium, high, xhigh, max | | `claude-mythos-5` | Claude Mythos 5 (Project Glasswing) | low, medium, high, xhigh, max | | `claude-sonnet-5` | Claude Sonnet 5 | low, medium, high, xhigh, max | | `claude-opus-4-8` | Claude Opus 4.8 | low, medium, high, xhigh, max | | `claude-opus-4-7` | Claude Opus 4.7 | low, medium, high, xhigh, max | | `claude-opus-4-6` | Claude Opus 4.6 | low, medium, high, max | | `claude-sonnet-4-6` | Claude Sonnet 4.6 | low, medium, high, max | | `claude-haiku-4-5` | Claude Haiku 4.5 | none | ## openai | slug | model | effort | |------|-------|--------| | `openai-gpt-5-6-sol` | GPT-5.6 Sol (frontier) | none, minimal, low, medium, high, xhigh, max | | `openai-gpt-5-6-terra` | GPT-5.6 Terra (balanced) | none, minimal, low, medium, high, xhigh, max | | `openai-gpt-5-6-luna` | GPT-5.6 Luna (cost-optimized) | none, minimal, low, medium, high, xhigh, max | | `openai-gpt-realtime-2-1` | GPT Realtime 2.1 | none | | `openai-gpt-realtime-2-1-mini` | GPT Realtime 2.1 mini | none | | `openai-gpt-image-2` | GPT Image 2 | none | Each Sol/Terra/Luna tier also ships `-fast` and `-pro` variants; append the suffix to the slug (`openai-gpt-5-6-sol-pro`). The GPT-5 / 5.5 / o3 / o4-mini lineage is deprecated (retires late 2026) and deliberately not listed. ## cursor | slug | model | effort | |------|-------|--------| | `cursor-composer-2-5` **?** | Composer 2.5 | none | Cursor names Composer only by display name in-product; no public API id string was found. Confirm and correct on first real use. ## xai | slug | model | effort | |------|-------|--------| | `xai-grok-4-5` | Grok 4.5 | none | | `xai-grok-4-3` | Grok 4.3 | none | | `xai-grok-4-20-0309-reasoning` | Grok 4.20 (reasoning) | none | | `xai-grok-4-20-0309-non-reasoning` | Grok 4.20 (non-reasoning) | none | | `xai-grok-4-20-multi-agent-0309` | Grok 4.20 multi-agent | none | | `xai-grok-build-0-1` | Grok Build 0.1 | none | | `xai-grok-imagine-image` | Grok Imagine Image | none | | `xai-grok-imagine-video-1-5` | Grok Imagine Video 1.5 | none | xAI documents no reasoning-effort parameter on current models; the old grok-3-mini low/high split no longer applies. ## moonshot | slug | model | effort | |------|-------|--------| | `moonshot-kimi-k3` | Kimi K3 (flagship, 1M context) | low, high, max (default max) | Kimi K2.7 Code and K2.6 exist by marketing name; their API id strings were not confirmed. Add rows when you use them. ## zhipu | slug | model | effort | |------|-------|--------| | `zhipu-glm-4-6` | GLM-4.6 | none (thinking is an on/off toggle, not a scale) | | `zhipu-glm-5-2` **?** | GLM-5.2 | none, minimal, low, medium, high, xhigh, max **?** | The GLM-5.2 row came from a single unconfirmed source that may have been a template page. Verify before trusting it. ## deepseek | slug | model | effort | |------|-------|--------| | `deepseek-v4-pro` | DeepSeek-V4-Pro | high (full range not documented) | | `deepseek-v4-flash` **?** | DeepSeek-V4-Flash | unconfirmed |