From 4bbeb61dc43464640722fb87083beaf76d318fd4 Mon Sep 17 00:00:00 2001 From: Sagar Narayan Date: Sat, 14 Feb 2026 14:38:52 -0800 Subject: [PATCH] docs: add GPT-5.3-Codex and MiniMax M2.5 to model documentation Add two new models across all documentation tiers: - GPT-5.3-Codex (gpt-5.3-codex): 0.7x multiplier, Extra High reasoning, verbosity support - Droid Core (MiniMax M2.5) (minimax-m2.5): 0.12x multiplier, Low/Medium/High reasoning Updated files: pricing.mdx, cli-reference.mdx, choosing-your-model.mdx, settings.mdx, droid-exec/overview.mdx, token-efficiency.mdx Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> --- docs/cli/configuration/settings.mdx | 6 ++-- docs/cli/droid-exec/overview.mdx | 2 ++ docs/cli/user-guides/choosing-your-model.mdx | 36 +++++++++++--------- docs/guides/power-user/token-efficiency.mdx | 2 ++ docs/pricing.mdx | 2 ++ docs/reference/cli-reference.mdx | 2 ++ 6 files changed, 32 insertions(+), 18 deletions(-) diff --git a/docs/cli/configuration/settings.mdx b/docs/cli/configuration/settings.mdx index 384c880..9ad1732 100644 --- a/docs/cli/configuration/settings.mdx +++ b/docs/cli/configuration/settings.mdx @@ -27,7 +27,7 @@ If the file doesn't exist, it's created with defaults the first time you run **d | Setting | Options | Default | Description | | ------- | ------- | ------- | ----------- | -| `model` | `opus`, `opus-4-6`, `opus-4-6-fast`, `sonnet`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-max`, `gpt-5.2`, `gpt-5.2-codex`, `haiku`, `gemini-3-pro`, `droid-core`, `kimi-k2.5`, `custom-model` | `opus` | The default AI model used by droid | +| `model` | `opus`, `opus-4-6`, `opus-4-6-fast`, `sonnet`, `gpt-5.1`, `gpt-5.1-codex`, `gpt-5.1-codex-max`, `gpt-5.2`, `gpt-5.2-codex`, `gpt-5.3-codex`, `haiku`, `gemini-3-pro`, `droid-core`, `kimi-k2.5`, `minimax-m2.5`, `custom-model` | `opus` | The default AI model used by droid | | `reasoningEffort` | `off`, `none`, `low`, `medium`, `high` (availability depends on the model) | Model-dependent default | Controls how much structured thinking the model performs. | | `autonomyLevel` | `normal`, `spec`, `auto-low`, `auto-medium`, `auto-high` | `normal` | Sets the default autonomy mode when starting droid. | | `cloudSessionSync` | `true`, `false` | `true` | Mirror CLI sessions to Factory web. | @@ -62,11 +62,13 @@ Choose the default AI model that powers your droid: - **`gpt-5.1-codex`** - Advanced coding-focused model - **`gpt-5.1-codex-max`** - GPT-5.1-Codex-Max, supports Extra High reasoning - **`gpt-5.2`** - OpenAI GPT-5.2 -- **`gpt-5.2-codex`** - GPT-5.2-Codex, latest OpenAI coding model with Extra High reasoning +- **`gpt-5.2-codex`** - GPT-5.2-Codex, OpenAI coding model with Extra High reasoning +- **`gpt-5.3-codex`** - GPT-5.3-Codex, latest OpenAI coding model with Extra High reasoning and verbosity support - **`haiku`** - Claude Haiku 4.5, fast and cost-effective - **`gemini-3-pro`** - Gemini 3 Pro - **`droid-core`** - GLM-4.7 open-source model - **`kimi-k2.5`** - Kimi K2.5 open-source model with image support +- **`minimax-m2.5`** - MiniMax M2.5 open-source model with reasoning support (0.12× multiplier) - **`custom-model`** - Your own configured model via BYOK [You can also add custom models and BYOK.](/cli/configuration/byok) diff --git a/docs/cli/droid-exec/overview.mdx b/docs/cli/droid-exec/overview.mdx index 6d88982..9691c6e 100644 --- a/docs/cli/droid-exec/overview.mdx +++ b/docs/cli/droid-exec/overview.mdx @@ -80,10 +80,12 @@ Supported models (examples): - gpt-5.1 - gpt-5.2 - gpt-5.2-codex +- gpt-5.3-codex - gemini-3-pro-preview - gemini-3-flash-preview - glm-4.7 - kimi-k2.5 +- minimax-m2.5 See the [model table](/pricing#pricing-table) for the full list of available models and their costs. diff --git a/docs/cli/user-guides/choosing-your-model.mdx b/docs/cli/user-guides/choosing-your-model.mdx index 1899261..c1c7c09 100644 --- a/docs/cli/user-guides/choosing-your-model.mdx +++ b/docs/cli/user-guides/choosing-your-model.mdx @@ -4,7 +4,7 @@ description: Balance accuracy, speed, and cost by picking the right model and re keywords: ['model', 'models', 'llm', 'claude', 'sonnet', 'opus', 'haiku', 'gpt', 'openai', 'anthropic', 'choose model', 'switch model'] --- -Model quality evolves quickly, and we tune the CLI defaults as the ecosystem shifts. Use this guide as a snapshot of how the major options compare today, and expect to revisit it as we publish updates. This guide was last updated on Thursday, February 12th 2026. +Model quality evolves quickly, and we tune the CLI defaults as the ecosystem shifts. Use this guide as a snapshot of how the major options compare today, and expect to revisit it as we publish updates. This guide was last updated on Friday, February 14th 2026. --- @@ -17,15 +17,17 @@ Model quality evolves quickly, and we tune the CLI defaults as the ecosystem shi | 3 | **Claude Opus 4.5** | Proven quality-and-safety balance; strong default for TUI and exec. | | 4 | **GPT-5.1-Codex-Max** | Fast coding loops with support up to **Extra High** reasoning; great for heavy implementation and debugging. | | 5 | **Claude Sonnet 4.5** | Strong daily driver with balanced cost/quality; great general-purpose choice when you don’t need Opus-level depth. | -| 6 | **GPT-5.2-Codex** | Latest OpenAI coding model with **Extra High** reasoning; strong for implementation-heavy tasks. | -| 7 | **GPT-5.1-Codex** | Quick iteration with solid code quality at lower cost; bump reasoning when you need more depth. | -| 8 | **GPT-5.1** | Good generalist, especially when you want OpenAI ergonomics with flexible reasoning effort. | -| 9 | **GPT-5.2** | Advanced OpenAI model with verbosity support and reasoning up to **Extra High**. | -| 10 | **Claude Haiku 4.5** | Fast, cost-efficient for routine tasks and high-volume automation. | -| 11 | **Gemini 3 Pro** | Strong at mixed reasoning with Low/High settings; helpful for researchy flows with structured outputs. | -| 12 | **Gemini 3 Flash** | Fast, cheap (0.2× multiplier) with full reasoning support; great for high-volume tasks where speed matters. | -| 13 | **Droid Core (GLM-4.7)** | Open-source, 0.25× multiplier, great for bulk automation or air-gapped environments; note: no image support. | -| 14 | **Droid Core (Kimi K2.5)** | Open-source, 0.25× multiplier with image support; good for cost-sensitive work. | +| 6 | **GPT-5.3-Codex** | Newest OpenAI coding model with **Extra High** reasoning and verbosity support; strong for implementation-heavy tasks. | +| 7 | **GPT-5.2-Codex** | Proven OpenAI coding model with **Extra High** reasoning; solid for implementation-heavy tasks. | +| 8 | **GPT-5.1-Codex** | Quick iteration with solid code quality at lower cost; bump reasoning when you need more depth. | +| 9 | **GPT-5.1** | Good generalist, especially when you want OpenAI ergonomics with flexible reasoning effort. | +| 10 | **GPT-5.2** | Advanced OpenAI model with verbosity support and reasoning up to **Extra High**. | +| 11 | **Claude Haiku 4.5** | Fast, cost-efficient for routine tasks and high-volume automation. | +| 12 | **Gemini 3 Pro** | Strong at mixed reasoning with Low/High settings; helpful for researchy flows with structured outputs. | +| 13 | **Gemini 3 Flash** | Fast, cheap (0.2× multiplier) with full reasoning support; great for high-volume tasks where speed matters. | +| 14 | **Droid Core (MiniMax M2.5)** | Open-source, 0.12× multiplier with reasoning support (Low/Medium/High); cheapest model available. No image support. | +| 15 | **Droid Core (GLM-4.7)** | Open-source, 0.25× multiplier, great for bulk automation or air-gapped environments; note: no image support. | +| 16 | **Droid Core (Kimi K2.5)** | Open-source, 0.25× multiplier with image support; good for cost-sensitive work. | We ship model updates regularly. When a new release overtakes the list above, @@ -39,10 +41,10 @@ Model quality evolves quickly, and we tune the CLI defaults as the ecosystem shi | Scenario | Recommended model | | ---------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | | **Deep planning, architecture reviews, ambiguous product specs** | Start with **Opus 4.6** for best depth and safety, or **Opus 4.6 Fast** for faster turnaround. Use **Sonnet 4.5** when you want balanced cost/quality, or **Codex/Codex-Max** for faster iteration with reasoning. | -| **Full-feature development, large refactors** | **Opus 4.6** or **Opus 4.5** for depth and safety. **GPT-5.2-Codex** or **GPT-5.1-Codex-Max** when you need speed plus **Extra High** reasoning; **Sonnet 4.5** for balanced loops. | -| **Repeatable edits, summarization, boilerplate generation** | **Haiku 4.5** or **Droid Core** for speed and cost. **GPT-5.1 / GPT-5.1-Codex** when you need higher quality or structured outputs. | +| **Full-feature development, large refactors** | **Opus 4.6** or **Opus 4.5** for depth and safety. **GPT-5.3-Codex**, **GPT-5.2-Codex**, or **GPT-5.1-Codex-Max** when you need speed plus **Extra High** reasoning; **Sonnet 4.5** for balanced loops. | +| **Repeatable edits, summarization, boilerplate generation** | **Haiku 4.5** or **Droid Core** (including **MiniMax M2.5** at 0.12×) for speed and cost. **GPT-5.1 / GPT-5.1-Codex** when you need higher quality or structured outputs. | | **CI/CD or automation loops** | Favor **Haiku 4.5** or **Droid Core** for predictable, low-cost throughput. Use **Codex** or **Codex-Max** when automation needs stronger reasoning. | -| **High-volume automation, frequent quick turns** | **Haiku 4.5** for speedy feedback. **Droid Core** when cost is critical or you need air-gapped deployment. | +| **High-volume automation, frequent quick turns** | **Haiku 4.5** for speedy feedback. **Droid Core** (especially **MiniMax M2.5** at 0.12× with reasoning) when cost is critical or you need air-gapped deployment. | **Claude Opus 4.6** is the top-tier option for extremely complex architecture decisions or critical work where you need maximum reasoning capability. **Opus 4.6 Fast** is tuned for faster responses at a higher cost. Most tasks don't require Opus-level power—start with Sonnet 4.5 and escalate only if needed. @@ -70,12 +72,14 @@ Tip: you can swap models mid-session with `/model` or by toggling in the setting - **GPT-5.1-Codex-Max**: Low / Medium / High / **Extra High** (default: Medium) - **GPT-5.2**: Off / Low / Medium / High / **Extra High** (default: Low) - **GPT-5.2-Codex**: None / Low / Medium / High / **Extra High** (default: Medium) +- **GPT-5.3-Codex**: None / Low / Medium / High / **Extra High** (default: Medium) - **Gemini 3 Pro**: None / Low / Medium / High (default: High) - **Gemini 3 Flash**: Minimal / Low / Medium / High (default: High) - **Droid Core (GLM-4.7)**: None only (default: None; no image support) - **Droid Core (Kimi K2.5)**: None only (default: None) +- **Droid Core (MiniMax M2.5)**: Low / Medium / High (default: High) -Reasoning effort increases latency and cost—start low for simple work and escalate as needed. **Max** is available on Claude Opus 4.6. **Extra High** is available on GPT-5.1-Codex-Max, GPT-5.2, and GPT-5.2-Codex. +Reasoning effort increases latency and cost—start low for simple work and escalate as needed. **Max** is available on Claude Opus 4.6. **Extra High** is available on GPT-5.1-Codex-Max, GPT-5.2, GPT-5.2-Codex, and GPT-5.3-Codex. Change reasoning effort from `/model` → **Reasoning effort**, or via the @@ -90,14 +94,14 @@ Factory ships with managed Anthropic and OpenAI access. If you prefer to run aga ### Open-source models -**Droid Core (GLM-4.7)** and **Droid Core (Kimi K2.5)** are open-source alternatives available in the CLI. They're useful for: +**Droid Core (GLM-4.7)**, **Droid Core (Kimi K2.5)**, and **Droid Core (MiniMax M2.5)** are open-source alternatives available in the CLI. They're useful for: - **Air-gapped environments** where external API calls aren't allowed - **Cost-sensitive projects** needing unlimited local inference - **Privacy requirements** where code cannot leave your infrastructure - **Experimentation** with open-source model capabilities -**Note:** GLM-4.7 does not support image attachments. Kimi K2.5 does support images. For image-based workflows, use Claude, GPT, or Kimi models. +**Note:** GLM-4.7 and MiniMax M2.5 do not support image attachments. Kimi K2.5 does support images. MiniMax M2.5 is the cheapest model available (0.12× multiplier) and uniquely supports reasoning (Low/Medium/High) among Droid Core models. For image-based workflows, use Claude, GPT, or Kimi models. To use open-source models, you'll need to configure them via BYOK with a local inference server (like Ollama) or a hosted provider. See [BYOK documentation](/cli/configuration/byok) for setup instructions. diff --git a/docs/guides/power-user/token-efficiency.mdx b/docs/guides/power-user/token-efficiency.mdx index eb89075..dd61b02 100644 --- a/docs/guides/power-user/token-efficiency.mdx +++ b/docs/guides/power-user/token-efficiency.mdx @@ -134,11 +134,13 @@ Different models have different cost multipliers and capabilities. Match the mod | Model | Multiplier | Best For | |-------|------------|----------| +| Droid Core (MiniMax M2.5) | 0.12× | Cheapest option with reasoning support | | Gemini 3 Flash | 0.2× | Fast, cheap for high-volume tasks | | Droid Core (GLM-4.7) | 0.25× | Bulk automation, simple tasks | | Droid Core (Kimi K2.5) | 0.25× | Cost-sensitive work, supports images | | Claude Haiku 4.5 | 0.4× | Quick edits, routine work | | GPT-5.1 / GPT-5.1-Codex | 0.5× | Implementation, debugging | +| GPT-5.2-Codex / GPT-5.3-Codex | 0.7× | Advanced coding with Extra High reasoning | | Gemini 3 Pro | 0.8× | Research, analysis | | Claude Sonnet 4.5 | 1.2× | Balanced quality/cost | | Claude Opus 4.5 | 2× | Complex reasoning, architecture | diff --git a/docs/pricing.mdx b/docs/pricing.mdx index ce99983..e5001e3 100644 --- a/docs/pricing.mdx +++ b/docs/pricing.mdx @@ -24,6 +24,7 @@ Different models have different multipliers applied to calculate Standard Token | Model | Model ID | Multiplier | | ------------------------ | ---------------------------- | ---------- | +| Droid Core (MiniMax M2.5)| `minimax-m2.5` | 0.12× | | Gemini 3 Flash | `gemini-3-flash-preview` | 0.2× | | Droid Core (GLM-4.7) | `glm-4.7` | 0.25× | | Droid Core (Kimi K2.5) | `kimi-k2.5` | 0.25× | @@ -33,6 +34,7 @@ Different models have different multipliers applied to calculate Standard Token | GPT-5.1-Codex-Max | `gpt-5.1-codex-max` | 0.5× | | GPT-5.2 | `gpt-5.2` | 0.7× | | GPT-5.2-Codex | `gpt-5.2-codex` | 0.7× | +| GPT-5.3-Codex | `gpt-5.3-codex` | 0.7× | | Gemini 3 Pro | `gemini-3-pro-preview` | 0.8× | | Claude Sonnet 4.5 | `claude-sonnet-4-5-20250929` | 1.2× | | Claude Opus 4.5 | `claude-opus-4-5-20251101` | 2× | diff --git a/docs/reference/cli-reference.mdx b/docs/reference/cli-reference.mdx index 4af08b4..bb6845e 100644 --- a/docs/reference/cli-reference.mdx +++ b/docs/reference/cli-reference.mdx @@ -108,12 +108,14 @@ droid exec --auto high "Run tests, commit, and push changes" | `gpt-5.1` | GPT-5.1 | Yes (None/Low/Medium/High) | none | | `gpt-5.2` | GPT-5.2 | Yes (Off/Low/Medium/High/Extra High) | low | | `gpt-5.2-codex` | GPT-5.2-Codex | Yes (None/Low/Medium/High/Extra High) | medium | +| `gpt-5.3-codex` | GPT-5.3-Codex | Yes (None/Low/Medium/High/Extra High) | medium | | `claude-sonnet-4-5-20250929` | Claude Sonnet 4.5 | Yes (Off/Low/Medium/High) | off | | `claude-haiku-4-5-20251001` | Claude Haiku 4.5 | Yes (Off/Low/Medium/High) | off | | `gemini-3-pro-preview` | Gemini 3 Pro | Yes (None/Low/Medium/High) | high | | `gemini-3-flash-preview` | Gemini 3 Flash | Yes (Minimal/Low/Medium/High) | high | | `glm-4.7` | Droid Core (GLM-4.7) | None only | none | | `kimi-k2.5` | Droid Core (Kimi K2.5) | None only | none | +| `minimax-m2.5` | Droid Core (MiniMax M2.5) | Yes (Low/Medium/High) | high | Custom models configured via [BYOK](/cli/configuration/byok) use the format: `custom:`