copilot-custom-endpoint 1.3.13 → 1.3.14

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 (4) hide show
  1. package/README.md +2 -2
  2. package/docs/models/minimax.md +1 -1
  3. package/docs/pricing.md +3 -3
  4. package/package.json +1 -1
package/README.md CHANGED
@@ -88,16 +88,16 @@ npx copilot-custom-endpoint clean # Remove debug_log/
88
88
 
89
89
  ## Pricing snapshot
90
90
 
91
- All prices are **USD per 1M tokens** (cache miss). 1 AI credit = $0.01.
91
+ 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.
92
92
 
93
93
  | Model | Input | Output | Context |
94
94
  | ---------------------------- | ----- | ------ | ------- |
95
95
  | **MiMo V2 Flash** 🏆 | $0.10 | $0.30 | 256K |
96
96
  | **DeepSeek V4 Flash** 🏆 | $0.14 | $0.28 | 1M |
97
97
  | **Kimi K2.6** (non-thinking) | $0.16 | $0.95 | 256K |
98
+ | **MiniMax M3** | $0.30 | $1.20 | 1M |
98
99
  | **MiMo V2.5** | $0.40 | $2.00 | 1M |
99
100
  | **Qwen 3.7 Plus** | $0.40 | $1.60 | 1M |
100
- | **MiniMax M3** | $0.60 | $2.40 | 1M |
101
101
  | **MiMo V2.5 Pro** | $1.00 | $3.00 | 1M |
102
102
  | **GLM 5V Turbo** | $1.20 | $4.00 | 200K |
103
103
  | **GLM 5.1** | $1.40 | $4.40 | 200K |
package/docs/models/minimax.md CHANGED
@@ -149,7 +149,7 @@ For the cross-provider comparison, see [docs/pricing.md](../pricing.md). MiniMax
149
149
 
150
150
  \* Input tokens above 512K are available in limited quantity for a limited time.
151
151
 
152
- > **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.
152
+ > **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).
153
153
 
154
154
  ### Token Plan (subscription)
155
155
 
package/docs/pricing.md CHANGED
@@ -66,7 +66,7 @@ These are the models available through GitHub Copilot's model roster as of June
66
66
  > - **Qwen** models use **tiered pricing** — determined by total input tokens per request. Prices above are for non-thinking mode.
67
67
  > - **Kimi K2.6** pricing is from the **Moonshot platform** (direct). Via DashScope: $0.89 input / $3.71 output.
68
68
  > - **DashScope** offers a **free quota** of 1M input + 1M output tokens per model, valid for 90 days.
69
- > - **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.
69
+ > - **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.
70
70
  > - **GLM** models support prompt caching — cache hits are priced at $0.24/M for 5V Turbo and $0.26/M for 5.1.
71
71
  > - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion.
72
72
  > - 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)
80
80
  | MiMo V2 Flash | ~$0.08 |
81
81
  | DeepSeek V4 Flash | ~$0.10 |
82
82
  | Kimi K2.6 (non-thinking) | ~$0.18 |
83
+ | MiniMax M3 (50% off) | ~$0.27 |
83
84
  | DeepSeek V4 Pro | ~$0.30 |
84
85
  | Raptor mini | ~$0.33 |
85
86
  | Qwen 3.7 Plus | ~$0.36 |
86
87
  | MiMo V2.5 | ~$0.40 |
87
88
  | Kimi K2.6 (thinking) | ~$0.48 |
88
- | MiniMax M3 | ~$0.54 |
89
89
  | Gemini 3 Flash | ~$0.55 |
90
90
  | MiMo V2.5 Pro | ~$0.80 |
91
91
  | GPT-5.4 mini | ~$0.83 |
@@ -102,7 +102,7 @@ For a typical coding session (~10K input + ~2K output tokens per turn, 50 turns)
102
102
 
103
103
  > **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.)
104
104
 
105
- > Prices last verified: June 1, 2026. Always check the official pages for the latest rates:
105
+ > Prices last verified: June 9, 2026. Always check the official pages for the latest rates:
106
106
  >
107
107
  > - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
108
108
  > - [OpenAI pricing](https://openai.com/api/pricing/)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "copilot-custom-endpoint",
3
- "version": "1.3.13",
3
+ "version": "1.3.14",
4
4
  "description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2 & Qwen 3.x",
5
5
  "license": "MIT",
6
6
  "type": "module",