freebuff 0.0.153 → 0.0.155

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +3 -3
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -19,7 +19,7 @@ freebuff
19
19
 
20
20
  ## Why Freebuff?
21
21
 
22
- **Choice of leading models** — The regular CLI picker includes DeepSeek, GPT-5.6 Luna, and MiMo, with DeepSeek V4 Pro selected by default.
22
+ **Choice of leading models** — The regular CLI picker includes DeepSeek, GPT-5.6 Luna, and MiMo, with GPT-5.6 Luna selected by default.
23
23
 
24
24
  **Fast** — 5–10× speed up. 3–5× tokens per second compared to Claude, plus context gathering in seconds.
25
25
 
@@ -29,11 +29,11 @@ freebuff
29
29
 
30
30
  **How can it be free?** Freebuff is supported by text ads.
31
31
 
32
- **What models do you use?** In full mode, the regular picker includes DeepSeek V4 Pro, DeepSeek V4 Flash 07/31, GPT-5.6 Luna, and MiMo 2.5. DeepSeek V4 Pro is the CLI default, and the picker falls back to MiMo 2.5 once your daily premium sessions are used up. Limited mode uses MiMo 2.5. These limits are temporary and exist because the providers serving DeepSeek now charge more than free mode can carry: V4 Flash is paused during peak hours, when V4 Pro a legacy build stays available in its place, GPT-5.6 Luna is two sessions a day, and models may serve from a quantized (Q8_0) build.
32
+ **What models do you use?** In full mode, the regular picker includes DeepSeek V4 Flash 07/31, GPT-5.6 Luna, MiMo 2.5, Ox Alpha, and DeepSeek V4 Pro. Ox Alpha is experimental — it has a 1M-token context and costs no session, but it may be unreliable and its provider can withdraw it without notice. GPT-5.6 Luna is the CLI default, and the picker falls back to MiMo 2.5 once your daily premium sessions are used up. Limited mode uses MiMo 2.5. Per-model daily caps are gone: every model draws on your normal daily sessions rather than its own separate limit, and MiMo 2.5 and Ox Alpha cost no session at all. Models may still serve from a quantized (Q8_0) build.
33
33
 
34
34
  **Which countries is Freebuff available in?** All countries. Freebuff runs in "full" mode in the US, Canada, UK, EU, and other select countries, and in "limited" mode everywhere else (or while using a VPN). See [freebuff.com](https://freebuff.com) for the full list.
35
35
 
36
- **What is limited mode?** Limited mode lets you use Freebuff outside the full-access countries, or while using a VPN. It includes MiMo 2.5, with 3 one-hour sessions per day, and you can earn up to 7 by engaging with promoted posts on the Earn page.
36
+ **What is limited mode?** Limited mode lets you use Freebuff outside the full-access countries, or while using a VPN. It includes MiMo 2.5 and Ox Alpha, with 3 one-hour sessions per day, and you can earn up to 7 by engaging with promoted posts on the Earn page.
37
37
 
38
38
  <!-- BEGIN GENERATED FREEBUFF DATA USE -->
39
39
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "freebuff",
3
- "version": "0.0.153",
3
+ "version": "0.0.155",
4
4
  "description": "The world's strongest free coding agent",
5
5
  "license": "MIT",
6
6
  "bin": {