0.5.41

Author: vava-nessa

changelog/v0.5.41.md

@@ -0,0 +1,7 @@
+# Changelog v0.5.41 - 2026-07-07
+
+### Changed
+- Adjusted the context window size of Cerebras models (`zai-glm-4.7` and `gpt-oss-120b`) to `8k` in the model catalog (`sources.js`) to reflect the strict 8192 total token limit of the Cerebras free tier API.
+
+### Fixed
+- Added a custom compatibility flag `"supportsTools": false` in `openai-completions.js` to allow completely disabling tool parameter injection for models with very small context windows.

package.json

@@ -1,6 +1,6 @@
 {
   "name": "free-coding-models",
-  "version": "0.5.40",
+  "version": "0.5.41",
   "description": "Find the fastest coding LLM models in seconds — ping free models from multiple providers, pick the best one for OpenCode, Cursor, or any AI coding assistant.",
   "keywords": [
     "nvidia",

pi-extension/request-params.json

@@ -0,0 +1,21 @@
+import fs from 'node:fs'
+
+const data = JSON.parse(fs.readFileSync('/Users/vava/Documents/GitHub/free-coding-models/pi-extension/request-params.json', 'utf8'))
+const { params } = data
+
+// Force stream: false so we get the full response body easily
+params.stream = false
+
+console.log('Sending request to Cerebras...')
+const resp = await fetch('https://api.cerebras.ai/v1/chat/completions', {
+  method: 'POST',
+  headers: {
+    'Content-Type': 'application/json',
+    'Authorization': 'Bearer csk-cm84r5nv3cvpe4nnxymm5ndt42r6ck8dfkev36d8fvh8839c'
+  },
+  body: JSON.stringify(params)
+})
+
+console.log('Status:', resp.status)
+const text = await resp.text()
+console.log('Response:', text)

pi-extension/test-cerebras-error.js

@@ -94,8 +94,8 @@ export const groq = [
 // 📖 Cerebras source - https://cloud.cerebras.ai
 // 📖 Free API keys available at https://cloud.cerebras.ai
 export const cerebras = [
-  ['gpt-oss-120b',                         'GPT OSS 120B',       'S',  '60.0%', '131k'],
-  ['zai-glm-4.7',                          'GLM 4.7',            'S+', '73.8%', '131k'],
+  ['gpt-oss-120b',                         'GPT OSS 120B',       'S',  '60.0%', '8k'],
+  ['zai-glm-4.7',                          'GLM 4.7',            'S+', '73.8%', '8k'],
 ]
 
 // 📖 SambaNova source - https://cloud.sambanova.ai