copilot-custom-endpoint 1.3.12 → 1.3.14

package/README.md

@@ -88,16 +88,16 @@ npx copilot-custom-endpoint clean    # Remove debug_log/
 
 ## Pricing snapshot
 
-All prices are **USD per 1M tokens** (cache miss). 1 AI credit = $0.01.
+All prices are **USD per 1M tokens** (cache miss). 1 AI credit = $0.01. **MiniMax M3** figures reflect a permanent 50% off list price — see the model doc for the full rate card.
 
 | Model                        | Input | Output | Context |
 | ---------------------------- | ----- | ------ | ------- |
 | **MiMo V2 Flash** 🏆         | $0.10 | $0.30  | 256K    |
 | **DeepSeek V4 Flash** 🏆     | $0.14 | $0.28  | 1M      |
 | **Kimi K2.6** (non-thinking) | $0.16 | $0.95  | 256K    |
+| **MiniMax M3**               | $0.30 | $1.20  | 1M      |
 | **MiMo V2.5**                | $0.40 | $2.00  | 1M      |
 | **Qwen 3.7 Plus**            | $0.40 | $1.60  | 1M      |
-| **MiniMax M3**               | $0.60 | $2.40  | 1M      |
 | **MiMo V2.5 Pro**            | $1.00 | $3.00  | 1M      |
 | **GLM 5V Turbo**             | $1.20 | $4.00  | 200K    |
 | **GLM 5.1**                  | $1.40 | $4.40  | 200K    |
@@ -118,7 +118,7 @@ VS Code's built-in `view_image` tool only accepts **static images** (PNG, JPG, G
 **Video Context MCP** is a small MCP server that bridges that gap. It works with **GitHub Copilot, Cursor, and Claude Code** out of the box, and:
 
 - **Extracts frames** from local files or remote URLs (no `ffmpeg` gymnastics required).
-- **Routes them through a multi-provider fallback chain** — `Gemini → GLM 4.6V Flash → Qwen3.7-plus → Kimi K2.6 → MiMo-V2.5` — so a single `GLM 5V Turbo` rate-limit hiccup doesn't kill your session.
+- **Routes them through a multi-provider fallback chain** — `Gemini → GLM 4.6V Flash → Qwen3.7-plus → Kimi K2.6 → MiMo-V2.5`.
 - **Answers natural-language questions** about the video grounded in actual frames: "what does the speaker click in the last 30 seconds?", "summarize the demo", "find the frame where the error appears".
 - **Extras:** timestamp search, audio transcription with speaker diarization, and video metadata (resolution, duration, codec).
 

package/docs/models/minimax.md

@@ -149,7 +149,7 @@ For the cross-provider comparison, see [docs/pricing.md](../pricing.md). MiniMax
 
 \* Input tokens above 512K are available in limited quantity for a limited time.
 
-> **Promo:** A 7-day 50% off promotion is available for new accounts, making the ≤ 512K tier effectively $0.30 / 1M input and $1.20 / 1M output for the first week.
+> **Permanent 50% off:** A standing 50% discount applies to all MiniMax-M3 pay-as-you-go usage on both the Standard and Priority tiers (verified June 9, 2026). The effective rates are $0.30 / 1M input, $1.20 / 1M output, and $0.06 / 1M cached input (≤ 512K tier).
 
 ### Token Plan (subscription)
 

package/docs/pricing.md

@@ -66,7 +66,7 @@ These are the models available through GitHub Copilot's model roster as of June
 > - **Qwen** models use **tiered pricing** — determined by total input tokens per request. Prices above are for non-thinking mode.
 > - **Kimi K2.6** pricing is from the **Moonshot platform** (direct). Via DashScope: $0.89 input / $3.71 output.
 > - **DashScope** offers a **free quota** of 1M input + 1M output tokens per model, valid for 90 days.
-> - **MiniMax M3** uses **tiered pricing** — input price doubles above 512K input tokens. Cache hits are priced at 20% of the input rate ($0.12/M ≤512K, $0.24/M >512K). A 7-day 50% off promotion is available for new accounts.
+> - **MiniMax M3** uses **tiered pricing** — input price doubles above 512K input tokens. Cache hits are priced at 20% of the input rate ($0.12/M ≤512K, $0.24/M >512K). A **permanent 50% off** discount applies to all MiniMax-M3 pay-as-you-go usage (Standard and Priority tiers), making the effective rates half the list prices above.
 > - **GLM** models support prompt caching — cache hits are priced at $0.24/M for 5V Turbo and $0.26/M for 5.1.
 > - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion.
 > - For typical Copilot chat usage (short-to-medium prompts), you'll almost always fall in the lowest pricing tier.
@@ -80,12 +80,12 @@ For a typical coding session (~10K input + ~2K output tokens per turn, 50 turns)
 | MiMo V2 Flash            | ~$0.08                 |
 | DeepSeek V4 Flash        | ~$0.10                 |
 | Kimi K2.6 (non-thinking) | ~$0.18                 |
+| MiniMax M3 (50% off)     | ~$0.27                 |
 | DeepSeek V4 Pro          | ~$0.30                 |
 | Raptor mini              | ~$0.33                 |
 | Qwen 3.7 Plus            | ~$0.36                 |
 | MiMo V2.5                | ~$0.40                 |
 | Kimi K2.6 (thinking)     | ~$0.48                 |
-| MiniMax M3               | ~$0.54                 |
 | Gemini 3 Flash           | ~$0.55                 |
 | MiMo V2.5 Pro            | ~$0.80                 |
 | GPT-5.4 mini             | ~$0.83                 |
@@ -102,7 +102,7 @@ For a typical coding session (~10K input + ~2K output tokens per turn, 50 turns)
 
 > **How long does 7,000 credits last?** A Pro+ subscriber running 50-turn sessions could afford roughly **13 GPT-5.5 sessions**, **23 Opus sessions**, or **212 Raptor mini sessions** per month — or mix and match. (Multiply session cost by 100 to convert to AI credits.)
 
-> Prices last verified: June 1, 2026. Always check the official pages for the latest rates:
+> Prices last verified: June 9, 2026. Always check the official pages for the latest rates:
 >
 > - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
 > - [OpenAI pricing](https://openai.com/api/pricing/)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "copilot-custom-endpoint",
-  "version": "1.3.12",
+  "version": "1.3.14",
   "description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2 & Qwen 3.x",
   "license": "MIT",
   "type": "module",
@@ -55,4 +55,4 @@
   "dependencies": {
     "dotenv": "^17.4.2"
   }
-}
+}