diff --git a/freebuff/README.md b/freebuff/README.md index 27abb478b2..0749fc7c0b 100644 --- a/freebuff/README.md +++ b/freebuff/README.md @@ -54,7 +54,7 @@ freebuff **How can it be free?** Freebuff is supported by ads shown in the CLI. -**What models do you use?** MiniMax M2.5 as the main coding agent, Gemini 3.1 Flash Lite for finding files and research, and GPT-5.4 for deep thinking if you connect your ChatGPT subscription. +**What models do you use?** GLM 5.1 as the main coding agent, Gemini 3.1 Flash Lite for finding files and research, and GPT-5.4 for deep thinking if you connect your ChatGPT subscription. **Are you training on my data?** No. We only use model providers that do not train on our requests. Your code stays yours. diff --git a/freebuff/SPEC.md b/freebuff/SPEC.md index 1f896350d5..195081533c 100644 --- a/freebuff/SPEC.md +++ b/freebuff/SPEC.md @@ -84,7 +84,7 @@ Freebuff only supports **FREE mode**. All mode-related features are stripped. | `/agent:gpt-5` | Premium agent, not available in free tier | | `/review` | Uses thinker-gpt under the hood | | `/publish` | Agent publishing not available in free tier | -| `/image` (+ `/img`, `/attach`) | Image attachments unavailable with free model (MiniMax M2.5) | +| `/image` (+ `/img`, `/attach`) | Image attachments unavailable with free model (GLM 5.1) | ### Commands to KEEP diff --git a/freebuff/web/src/app/home-client.tsx b/freebuff/web/src/app/home-client.tsx index 1368e95de0..3cff424a37 100644 --- a/freebuff/web/src/app/home-client.tsx +++ b/freebuff/web/src/app/home-client.tsx @@ -31,7 +31,7 @@ const faqs = [ { question: 'What models do you use?', answer: - 'MiniMax M2.5 as the main coding agent. Gemini 3.1 Flash Lite for finding files and research.\n\nConnect your ChatGPT subscription to unlock GPT-5.4 for deep thinking.', + 'GLM 5.1 as the main coding agent. Gemini 3.1 Flash Lite for finding files and research.\n\nConnect your ChatGPT subscription to unlock GPT-5.4 for deep thinking.', }, { question: 'Which countries is Freebuff available in?', @@ -343,7 +343,7 @@ function FAQList() { const PHILOSOPHY_WORDS = [ { word: 'SIMPLE', description: 'No modes. No config. Just works.' }, - { word: 'FAST', description: '5–10× speed up via fast models and quick context gathering.' }, + { word: 'FAST', description: '2–5x speed up via fast models and quick context gathering.' }, { word: 'LOADED', description: '9 specialized subagents: code review, browser use, deep thinking with your ChatGPT subscription, and more.' }, ] diff --git a/scripts/test-fireworks-long.ts b/scripts/test-fireworks-long.ts index ad01abac66..72abcd2abd 100644 --- a/scripts/test-fireworks-long.ts +++ b/scripts/test-fireworks-long.ts @@ -40,6 +40,14 @@ const MODEL_CONFIGS: Record = { cachedInputCostPerToken: 0.26 / 1_000_000, outputCostPerToken: 4.40 / 1_000_000, }, + 'kimi-k2.5': { + id: 'moonshotai/kimi-k2.5', + standardModel: 'accounts/fireworks/models/kimi-k2p5', + deploymentModel: 'accounts/james-65d217/deployments/mx8l5rq2', + inputCostPerToken: 0.60 / 1_000_000, + cachedInputCostPerToken: 0.10 / 1_000_000, + outputCostPerToken: 3.00 / 1_000_000, + }, minimax: { id: 'minimax/minimax-m2.5', standardModel: 'accounts/fireworks/models/minimax-m2p5', diff --git a/web/src/app/docs/[category]/[slug]/page.tsx b/web/src/app/docs/[category]/[slug]/page.tsx index 8eff270c5a..b503269a62 100644 --- a/web/src/app/docs/[category]/[slug]/page.tsx +++ b/web/src/app/docs/[category]/[slug]/page.tsx @@ -33,7 +33,7 @@ const FAQ_ITEMS = [ { question: 'What model does Codebuff use?', answer: - 'Multiple. The orchestrator uses Claude Opus 4.6 in Default and Max modes, or Grok 4.1 Fast in Free mode. Subagents are matched to their tasks: Claude Opus 4.6 for code editing, GPT-5.1 for deep reasoning, Grok 4.1 Fast for terminal commands and research, and Relace AI for fast file rewrites.', + 'Multiple. The orchestrator uses Claude Opus 4.6 in Default and Max modes, or GLM 5.1 in Free mode. Subagents are matched to their tasks: Claude Opus 4.6 for code editing, GPT-5.1 for deep reasoning, Grok 4.1 Fast for terminal commands and research, and Relace AI for fast file rewrites.', }, { question: 'Can I use my Claude Pro or Max subscription with Codebuff?', diff --git a/web/src/content/advanced/how-does-it-work.mdx b/web/src/content/advanced/how-does-it-work.mdx index accdc2c3d4..a337511fd1 100644 --- a/web/src/content/advanced/how-does-it-work.mdx +++ b/web/src/content/advanced/how-does-it-work.mdx @@ -25,7 +25,7 @@ The main agent ("Buffy") runs on Claude Opus 4.6. It reads your prompt, gathers - [**Researcher**](/publishers/codebuff/agents/researcher) (Grok 4 Fast) - web and docs lookup - [**Thinker**](/publishers/codebuff/agents/thinker) (GPT-5.1, Gemini 2.5 Pro) - works through hard problems - [**Editor**](/publishers/codebuff/agents/editor) (GPT-5.1, Claude Opus 4.6) - writes and modifies code -- [**Reviewer**](/publishers/codebuff/agents/reviewer) (Claude Opus 4.6, MiniMax M2.5 in Free mode) - catches bugs and style issues +- [**Reviewer**](/publishers/codebuff/agents/reviewer) (Claude Opus 4.6, GLM 5.1 in Free mode) - catches bugs and style issues - [**Basher**](/publishers/codebuff/agents/basher) (Gemini 3.1 Flash Lite) - runs terminal commands ## Best-of-N Selection (Max Mode) diff --git a/web/src/content/advanced/what-models.mdx b/web/src/content/advanced/what-models.mdx index 4a157737f4..19846213fa 100644 --- a/web/src/content/advanced/what-models.mdx +++ b/web/src/content/advanced/what-models.mdx @@ -19,7 +19,7 @@ The main agent ("Buffy") coordinates everything: | Default | Opus 4.6 | | Plan | Opus 4.6 | | Max | Opus 4.6 | - | Free | MiniMax M2.5 | + | Free | GLM 5.1 | ## Subagents @@ -29,7 +29,7 @@ The orchestrator spawns these for specific jobs: | Task | Models | |------|--------| - | Code editing | Claude Opus 4.6, Minimax M2.5 | + | Code editing | Claude Opus 4.6, GLM 5.1 | | Thinking/reasoning | Claude Opus 4.6, GPT-5.4 | | Code review | Claude Opus 4.6, GPT-5.4 | | File discovery | Gemini 3.1 Flash Lite, Gemini 2.5 Flash Lite | @@ -37,4 +37,4 @@ The orchestrator spawns these for specific jobs: | Web/docs research | Gemini 3.1 Flash Lite | -Max mode runs multiple implementations in parallel and picks the best one. Default mode runs a single implementation pass. Free mode uses MiniMax M2.5 and includes code review support. +Max mode runs multiple implementations in parallel and picks the best one. Default mode runs a single implementation pass. Free mode uses GLM 5.1 and includes code review support. diff --git a/web/src/content/help/faq.mdx b/web/src/content/help/faq.mdx index e22af6977e..104ae35bc1 100644 --- a/web/src/content/help/faq.mdx +++ b/web/src/content/help/faq.mdx @@ -13,7 +13,7 @@ Software development: Writing features, tests, and scripts across common languag ## What model does Codebuff use? -Multiple. The orchestrator uses Claude Opus 4.6 in Default and Max modes, or MiniMax M2.5 in Free mode. Subagents are matched to their tasks: Claude Opus 4.6 for code editing, GPT-5.1 for deep reasoning, Grok 4.1 Fast for terminal commands and research, and Relace AI for fast file rewrites. Free mode includes code review support. See [What models do you use?](/docs/advanced/what-models) for the full breakdown. +Multiple. The orchestrator uses Claude Opus 4.6 in Default and Max modes, or GLM 5.1 in Free mode. Subagents are matched to their tasks: Claude Opus 4.6 for code editing, GPT-5.1 for deep reasoning, Grok 4.1 Fast for terminal commands and research, and Relace AI for fast file rewrites. Free mode includes code review support. See [What models do you use?](/docs/advanced/what-models) for the full breakdown. ## Can I use my Claude Pro or Max subscription with Codebuff? diff --git a/web/src/content/tips/modes.mdx b/web/src/content/tips/modes.mdx index e889155914..0026b18062 100644 --- a/web/src/content/tips/modes.mdx +++ b/web/src/content/tips/modes.mdx @@ -15,7 +15,7 @@ Codebuff has four modes. Switch during a session with `Shift+Tab` or `/mode:` co | Default | Claude Opus 4.6 | editor | Yes | | Max | Claude Opus 4.6 | editor-multi-prompt | Yes | | Plan | Claude Opus 4.6 | None | No | - | Free | MiniMax M2.5 | editor-lite | No | + | Free | GLM 5.1 | None | No | ## Default @@ -60,7 +60,7 @@ Switch to this mode with `/mode:plan`. ## Free -MiniMax M2.5, cheaper and faster: +GLM 5.1, cheaper and faster: - Less file context gathering - Skips code review diff --git a/web/src/llm-api/fireworks.ts b/web/src/llm-api/fireworks.ts index e93747224f..4799e91ac6 100644 --- a/web/src/llm-api/fireworks.ts +++ b/web/src/llm-api/fireworks.ts @@ -40,6 +40,7 @@ const FIREWORKS_USE_CUSTOM_DEPLOYMENT = true /** Custom deployment IDs for models with dedicated Fireworks deployments */ const FIREWORKS_DEPLOYMENT_MAP: Record = { // 'minimax/minimax-m2.5': 'accounts/james-65d217/deployments/lnfid5h9', + 'moonshotai/kimi-k2.5': 'accounts/james-65d217/deployments/mx8l5rq2', 'z-ai/glm-5.1': 'accounts/james-65d217/deployments/mjb4i7ea', }