copilot-custom-endpoint 1.6.4 → 1.6.6

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.
package/README.md CHANGED
@@ -95,10 +95,11 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
95
95
  | Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
96
96
  | ---------------------- | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
97
97
  | **DeepSeek V4 Flash** | DeepSeek | **~$0.0025** | **40.3** | ~$0.10 | ✅ | 1M |
98
+ | **MiMo V2.5** | Xiaomi | **~$0.0025** | **40** ³ | ~$0.10 | ✅ | 1M |
98
99
  | **MiniMax M3** | MiniMax | **~$0.0061** | **44.4** | ~$0.27 | ✅ | 1M |
99
100
  | **DeepSeek V4 Pro** | DeepSeek | **~$0.0068** | **44.3** | ~$0.30 | ✅ | 1M |
101
+ | **MiMo V2.5 Pro** | Xiaomi | **~$0.0072** | **42.2** | ~$0.30 | ❌ | 1M |
100
102
  | **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | ~$0.36 | ✅ | 1M |
101
- | **MiMo V2.5 Pro** | Xiaomi | **~$0.019** | **42.2** | ~$0.80 | ❌ | 1M |
102
103
  | **Gemini 3 Flash** | Google | **~$0.020** | **27.0** ³ | ~$0.55 | ✅ | 173K |
103
104
  | **Kimi K2.6** | Moonshot | **~$0.021** | **42.8** | ~$0.88 | ✅ | 262K |
104
105
  | **Kimi K2.7 Code** | Moonshot | **~$0.021** | **42.0** | ~$0.88 | ✅ | 262K |
@@ -115,7 +116,6 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
115
116
  | **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | ~$5.00 | ✅ | 1M |
116
117
  | **GPT-5.5** | OpenAI | **~$0.10** | **54.8** | ~$5.50 | ✅ | 1M |
117
118
  | **Raptor mini** | GitHub | — | — | ~$0.33 | ❌ | 264K |
118
- | **MiMo V2.5** | Xiaomi | — | — | ~$0.40 | ✅ | 1M |
119
119
  | **MAI-Code-1-Flash** ² | Microsoft | — | — | ~$0.83 | ❌ | — |
120
120
  | **Claude Haiku 4.5** | Anthropic | — | — | ~$1.00 | ❌ | 160K |
121
121
  | **GPT-5.3-Codex** | OpenAI | — | — | ~$2.28 | ❌ | 400K |
@@ -124,6 +124,8 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
124
124
 
125
125
  ² MAI-Code-1-Flash is a continuously improving model — performance and behavior may evolve over time as new checkpoints are released.
126
126
 
127
+ ³ Score is an **estimate** from Artificial Analysis (labelled "independent evaluation forthcoming"). Not a confirmed run of the full evaluation suite.
128
+
127
129
  For footnotes, sources, and detailed notes (cache behavior, tiered pricing, free quotas) see [docs/pricing.md](docs/pricing.md). For a copy-paste config containing **all providers at once**, see [docs/example-config.md](docs/example-config.md).
128
130
 
129
131
  > **👤 Personal picks** —
@@ -1,20 +1,23 @@
1
1
  # GLM (Z.ai / Zhipu AI) — VS Code Custom Endpoint Setup Guide
2
2
 
3
- > **TL;DR:** GLM works directly with VS Code's custom-endpoint provider — **no proxy needed**. The API is OpenAI Chat Completions compatible at `https://api.z.ai/api/paas/v4/chat/completions`, and Z.ai's default `thinking.clear_thinking: true` quietly strips `reasoning_content` from prior turns, which makes multi-turn tool loops stable even when VS Code doesn't preserve reasoning blocks. The **GLM Coding Plan** endpoint is **not** usable here — it is locked to a curated list of coding tools (Claude Code, Cline, OpenCode, etc.).
3
+ > **TL;DR:** GLM works directly with VS Code's custom-endpoint provider — **no proxy needed**. The API is OpenAI Chat Completions compatible at `https://api.z.ai/api/paas/v4/chat/completions`, and Z.ai's default `thinking.clear_thinking: true` quietly strips `reasoning_content` from prior turns, which makes multi-turn tool loops stable even when VS Code doesn't preserve reasoning blocks.
4
+ >
5
+ > **Billing:** The PaaS API is **Pay-as-You-Go** (per-token). Z.ai also offers a **Coding Plan** subscription (Lite/Pro/Max, $18–$160/mo), but it uses a **different endpoint** (`/api/coding/paas/v4`) that is **locked to a curated list of coding tools** (Claude Code, Cursor, Cline, etc.) — it **cannot** be used from VS Code custom endpoints. See [Why the GLM Coding Plan is not an option](#why-the-glm-coding-plan-is-not-an-option-for-vs-code).
4
6
 
5
7
  ## At a Glance
6
8
 
7
- | Field | Value |
8
- | ---------------------- | ------------------------------------------------------- |
9
- | Mode | **Direct** (no proxy) |
10
- | Vision | ✅ Yes (`glm-5v-turbo` only) |
11
- | Tool calling | ✅ Yes (native multimodal tool use on `glm-5v-turbo`) |
12
- | Context (flagship) | 1M (`glm-5.2` Solid Lossless Context) |
13
- | Max output (flagship) | 131072 |
14
- | Required `requestBody` | `thinking: { type: "enabled" }` (recommended) |
15
- | Endpoint (intl) | `https://api.z.ai/api/paas/v4/chat/completions` |
16
- | Endpoint (China) | `https://open.bigmodel.cn/api/paas/v4/chat/completions` |
17
- | Auth | `Authorization: Bearer $ZAI_API_KEY` |
9
+ | Field | Value |
10
+ | ---------------------- | ------------------------------------------------------------------------------------------------------------------ |
11
+ | Mode | **Direct** (no proxy) |
12
+ | Billing | **Pay-as-You-Go** (PaaS API) — Coding Plan subscription exists but is **not usable** from VS Code custom endpoints |
13
+ | Vision | ✅ Yes (`glm-5v-turbo` only) |
14
+ | Tool calling | ✅ Yes (native multimodal tool use on `glm-5v-turbo`) |
15
+ | Context (flagship) | 1M (`glm-5.2` Solid Lossless Context) |
16
+ | Max output (flagship) | 131072 |
17
+ | Required `requestBody` | `thinking: { type: "enabled" }` (recommended) |
18
+ | Endpoint (intl) | `https://api.z.ai/api/paas/v4/chat/completions` |
19
+ | Endpoint (China) | `https://open.bigmodel.cn/api/paas/v4/chat/completions` |
20
+ | Auth | `Authorization: Bearer $ZAI_API_KEY` |
18
21
 
19
22
  ### Models at a glance
20
23
 
@@ -7,6 +7,7 @@
7
7
  | Field | Value |
8
8
  | ----------------- | --------------------------------------------- |
9
9
  | Mode | **Proxy required** (local on `:3457`) |
10
+ | Billing | **Pay-as-You-Go only** — no subscription |
10
11
  | Vision | ✅ Yes |
11
12
  | Tool calling | ✅ Yes |
12
13
  | Upstream endpoint | `https://api.moonshot.ai/v1/chat/completions` |
@@ -108,12 +109,14 @@ Config file location:
108
109
 
109
110
  ### 2. API key
110
111
 
112
+ Kimi is **Pay-as-You-Go only** — there is no monthly subscription or Token Plan alternative. A single Open Platform API key covers all models. Recharge your balance at `platform.kimi.ai/console`.
113
+
111
114
  1. Open the Command Palette (`Ctrl+Shift+P`).
112
115
  2. Run **Chat: Manage Language Models**.
113
116
  3. Find the **Kimi** group → **Update API Key**.
114
- 4. Paste your Moonshot API key.
117
+ 4. Paste your Moonshot / Kimi Platform API key.
115
118
 
116
- > After setting via the UI, VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference.
119
+ > After setting via the UI, VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference. The Kimi Platform (formerly Moonshot) rebranded to `platform.kimi.ai` in 2026 — the `api.moonshot.ai` upstream endpoint still resolves and the proxy targets it unchanged.
117
120
 
118
121
  ### 3. Local proxy
119
122
 
@@ -151,14 +151,19 @@ Config file location:
151
151
 
152
152
  ### 3. Token Plan (optional)
153
153
 
154
- Token Plan subscribers use different base URLs and `tp-` prefixed keys:
154
+ Token Plan subscribers use different base URLs and `tp-` prefixed keys from the pay-as-you-go `sk-` keys. The **model id** (`mimo-v2.5-pro`, `mimo-v2.5`) and **`requestBody`** (thinking, temperature, top_p) are the **same** for both billing modes — only the URL and key prefix differ.
155
155
 
156
- | Protocol | Base URL |
156
+ | Mode | Key prefix | Base URL (OpenAI) |
157
+ | ------------- | ---------- | ----------------------------------------- |
158
+ | Pay-as-you-go | `sk-…` | `https://api.xiaomimimo.com/v1` |
159
+ | Token Plan | `tp-…` | `https://token-plan-cn.xiaomimimo.com/v1` |
160
+
161
+ | Protocol | Base URL (Token Plan) |
157
162
  | --------- | ------------------------------------------------ |
158
163
  | OpenAI | `https://token-plan-cn.xiaomimimo.com/v1` |
159
164
  | Anthropic | `https://token-plan-cn.xiaomimimo.com/anthropic` |
160
165
 
161
- > Pay-as-you-go keys are `sk-…`; Token Plan keys are `tp-…`. The endpoint to use depends on which key you set.
166
+ > The same `requestBody` block (thinking, temperature, top_p) is shared between both modes. If you switch from PAYG to Token Plan, update the `url` in `chatLanguageModels.json` and swap the key — the rest of the config stays as-is. Note that the Token Plan endpoint is `token-plan-cn.xiaomimimo.com` (China-hosted), which differs from the PAYG endpoint `api.xiaomimimo.com`.
162
167
 
163
168
  ### 4. Legacy id retirement schedule
164
169
 
@@ -1,19 +1,24 @@
1
1
  # MiniMax — VS Code Custom Endpoint Setup Guide
2
2
 
3
3
  > **TL;DR:** MiniMax-M3 works directly — no proxy needed. Use `thinking: { type: "adaptive" }` + `reasoning_split: true` in `requestBody` so the model can reason and the response arrives in a clean OpenAI format (`reasoning_details` field, separate from `content`). **Important:** `thinking: { type: "disabled" }` is **not** a hard override — the model still reasons internally and emits `<think>` tags / `reasoning_content` regardless.
4
+ >
5
+ > The same `url`, `model id`, and `requestBody` work for **both** Pay-as-You-Go (account-balance billing) and Token Plan (monthly/annual subscription) — only the API key in the secret field changes. See [API key source](#3-api-key-source) below.
4
6
 
5
7
  ## At a Glance
6
8
 
7
- | Field | Value |
8
- | ------------------------ | ------------------------------------------------------- |
9
- | Mode | **Direct** (no proxy) |
10
- | Vision | ✅ Yes (image + video) |
11
- | Tool calling | ✅ Yes |
12
- | Context | 1M (guaranteed 512K) |
13
- | Max output | 131072 |
14
- | Required `requestBody` | `thinking: { type: "adaptive" }, reasoning_split: true` |
15
- | Endpoint (international) | `https://api.minimax.io/v1/chat/completions` |
16
- | Endpoint (China) | `https://api.minimaxi.com/v1/chat/completions` |
9
+ | Field | Value |
10
+ | ------------------------ | ------------------------------------------------------------------------ |
11
+ | Mode | **Direct** (no proxy) |
12
+ | Billing | **Pay-as-You-Go** _or_ **Token Plan subscription** (same config) |
13
+ | Vision | ✅ Yes (image + video) |
14
+ | Tool calling | ✅ Yes |
15
+ | Context | 1M (guaranteed 512K) |
16
+ | Max output | 131072 |
17
+ | Required `requestBody` | `thinking: { type: "adaptive" }, reasoning_split: true` |
18
+ | Endpoint (international) | `https://api.minimax.io/v1/chat/completions` |
19
+ | Endpoint (China) | `https://api.minimaxi.com/v1/chat/completions` |
20
+ | API key (PAYG) | Open Platform API Key from `user-center/basic-information/interface-key` |
21
+ | API key (Token Plan) | **Subscription Key** (`sk-cp-…`) from `user-center/payment/token-plan` |
17
22
 
18
23
  ## Quick Start
19
24
 
@@ -60,23 +65,48 @@ Config file location:
60
65
  }
61
66
  ```
62
67
 
63
- ### 2. API key
68
+ ### 2. Select your billing mode
69
+
70
+ MiniMax exposes the **same** `https://api.minimax.io/v1/chat/completions` endpoint and the **same** `MiniMax-M3` model id to both billing modes. The only field that changes is the API key — the rest of `chatLanguageModels.json` stays identical.
71
+
72
+ | Billing mode | Key name in console | Where to get it | How usage is metered |
73
+ | ------------- | --------------------------------------- | ----------------------------------------------------------------- | ----------------------------------------------- |
74
+ | Pay-as-You-Go | **Open Platform API Key** | `platform.minimax.io/user-center/basic-information/interface-key` | Per-token, deducted from your account balance |
75
+ | Token Plan | **Subscription Key** (prefix `sk-cp-…`) | `platform.minimax.io/user-center/payment/token-plan` | Monthly quota (5-hour rolling + weekly windows) |
76
+
77
+ The two keys are **not interchangeable** — a Subscription Key against a PAYG-only endpoint or a PAYG key against the Token Plan quota will be rejected. The Token Plan docs are explicit: _"Subscription Keys are separate from standard pay-as-you-go API Keys."_ ([FAQ](https://platform.minimax.io/docs/token-plan/faq#api-key-interchangeable))
78
+
79
+ ### 3. API key source
80
+
81
+ #### Option A — Pay-as-You-Go key
64
82
 
65
83
  1. Open the Command Palette (`Ctrl+Shift+P`).
66
84
  2. Run **Chat: Manage Language Models**.
67
85
  3. Find the **MiniMax** group → **Update API Key**.
68
- 4. Paste your MiniMax API key.
86
+ 4. Paste your **Open Platform API Key** from `platform.minimax.io/user-center/basic-information/interface-key`.
69
87
 
70
88
  > After setting via the UI, VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference.
71
89
 
72
- ### 3. Regional endpoints
90
+ #### Option B — Token Plan Subscription Key
91
+
92
+ The same `chatLanguageModels.json` block above is reused unchanged. Only the secret stored under `${input:chat.lm.secret.<id>}` is replaced with your Subscription Key.
93
+
94
+ 1. Subscribe to a Token Plan (Plus $20 / Max $50 / Ultra $120) at <https://platform.minimax.io/subscribe/token-plan>. Annual billing is also available.
95
+ 2. Open `platform.minimax.io/user-center/payment/token-plan` and copy the **Subscription Key** (prefix `sk-cp-…`).
96
+ 3. In VS Code, run **Chat: Manage Language Models** → **MiniMax** group → **Update API Key** → paste the Subscription Key.
97
+
98
+ That's it. The endpoint, model id, and `requestBody` stay exactly the same. VS Code's Copilot Chat will now route the same `MiniMax-M3` requests through the Token Plan quota instead of the PAYG balance.
99
+
100
+ > When the Token Plan 5-hour or weekly quota is exhausted, the request fails with a Token Plan quota error (see [Troubleshooting](#troubleshooting)). At that point you can either (a) wait for the quota window to reset, (b) buy a Credits top-up at the same console (Credits use the same Subscription Key and cover eligible overflow), or (c) swap the key in **Chat: Manage Language Models** back to your Open Platform API Key to fall back to PAYG. The URL and `requestBody` do not change during the swap.
101
+
102
+ ### 4. Regional endpoints
73
103
 
74
104
  | Region | Endpoint |
75
105
  | ------------- | ---------------------------------------------- |
76
106
  | International | `https://api.minimax.io/v1/chat/completions` |
77
107
  | China | `https://api.minimaxi.com/v1/chat/completions` |
78
108
 
79
- > API keys are region-specific and cannot be used across regions.
109
+ > API keys are region-specific and cannot be used across regions. The same PAYG-vs-Token-Plan distinction applies to the China region (`api.minimaxi.com`); Subscription Keys are issued at `platform.minimaxi.com/user-center/payment/token-plan`.
80
110
 
81
111
  ## Configuration Reference
82
112
 
@@ -130,13 +160,17 @@ MiniMax model IDs are **case-sensitive**. Use exactly:
130
160
 
131
161
  ## Troubleshooting
132
162
 
133
- | Symptom | Likely cause | Fix |
134
- | ------------------------------ | ------------------------------------------------------ | -------------------------------------------------------- |
135
- | Model not in picker | Config not reloaded, or wrong casing | Restart VS Code; verify model ID is exactly `MiniMax-M3` |
136
- | Reasoning leaks into `content` | Missing `reasoning_split` | Add `reasoning_split: true` to `requestBody` |
137
- | 401 Unauthorized | API key region mismatch | Use the endpoint that matches your key's region |
138
- | 429 rate-limited | Concurrent sessions exceeded 200 RPM / 10M TPM | Reduce concurrent agent sessions |
139
- | Vision request returns 400 | Vision only supported on M3 (not the legacy M2.x line) | Use `MiniMax-M3` |
163
+ | Symptom | Likely cause | Fix |
164
+ | -------------------------------------------- | ---------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
165
+ | Model not in picker | Config not reloaded, or wrong casing | Restart VS Code; verify model ID is exactly `MiniMax-M3` |
166
+ | Reasoning leaks into `content` | Missing `reasoning_split` | Add `reasoning_split: true` to `requestBody` |
167
+ | 401 Unauthorized | API key region mismatch | Use the endpoint that matches your key's region |
168
+ | 401 `token is unusable` / 1004 | Wrong key type on the endpoint — PAYG key against a Token Plan quota or vice versa | The two keys are not interchangeable. Switch the secret in **Chat: Manage Language Models** to the correct key for the billing mode you intend to use. |
169
+ | 402 / 429 after a burst of agent turns | Token Plan 5-hour or weekly quota exhausted; not a PAYG balance issue | Wait for the quota window to reset, buy a Credits top-up at `platform.minimax.io/user-center/payment/credits`, upgrade plan, or swap the secret to a PAYG key to continue. |
170
+ | 429 rate-limited | Concurrent sessions exceeded 200 RPM / 10M TPM | Reduce concurrent agent sessions |
171
+ | Vision request returns 400 | Vision only supported on M3 (not the legacy M2.x line) | Use `MiniMax-M3` |
172
+ | Token Plan key works in curl but not VS Code | VS Code is still resolving the old `${input:chat.lm.secret.<id>}` reference | Re-open **Chat: Manage Language Models**, re-paste the Subscription Key, then restart VS Code |
173
+ | China account gets 401 on `api.minimax.io` | Key region is China but the URL points to international (or vice versa) | Switch the `url` to `https://api.minimaxi.com/v1/chat/completions` for China, and get the Subscription Key from `platform.minimaxi.com` |
140
174
 
141
175
  ## Pricing
142
176
 
@@ -153,7 +187,19 @@ For the cross-provider comparison, see [docs/pricing.md](../pricing.md). MiniMax
153
187
 
154
188
  ### Token Plan (subscription)
155
189
 
156
- MiniMax also offers monthly subscription plans with quota that resets each month (Plus $20/mo, Max $50/mo, Ultra $120/mo). All plans provide access to all models. See the [MiniMax Token Plan page](https://platform.minimax.io/docs/guides/pricing-token-plan) for details.
190
+ The Token Plan is a **monthly or annual** subscription with a shared multimodal usage bar (text + image + audio + video + music share one quota). It is the same family of plans the MiniMax integration guide for Cursor, Claude Code, Zed, Kilo Code, and other IDEs targets — and the _same_ `https://api.minimax.io/v1/chat/completions` endpoint with the _same_ `MiniMax-M3` model id is used. The only field that changes between PAYG and Token Plan is the API key in `${input:chat.lm.secret.<id>}`.
191
+
192
+ | Tier | Price | Best for | Quota window | Typical agent capacity |
193
+ | ----- | --------- | -------------------------------------------- | ----------------------- | ---------------------- |
194
+ | Plus | $20 / mo | Personal projects, prototyping | 5-hour rolling + weekly | 3–4 agents |
195
+ | Max | $50 / mo | Daily coding with agents and multimodal work | 5-hour rolling + weekly | 4–5 agents |
196
+ | Ultra | $120 / mo | Heavy agent workflows and extended sessions | 5-hour rolling + weekly | 6–7 agents |
197
+
198
+ Annual billing is available; unused subscription quota does **not** roll over to the next cycle. Credits are sold separately (`$5` = 5,000 / `$25` = 25,000 / `$100` = 100,000; 365-day validity) and use the same Subscription Key — when the included Token Plan quota is exhausted, purchased Credits automatically cover eligible overflow within Token Plan resource coverage. Subscription quota is consumed first, Credits second.
199
+
200
+ > The Token Plan is intended for **individual, interactive developer use**, not production. MiniMax recommends PAYG for production workloads. Peak-hour dynamic rate-limiting may apply (typically 15:00–17:30 weekdays, per the [Token Plan platform-traffic rules](https://platform.minimax.io/docs/token-plan/faq#token-plan-limit-rules)). For background, see the [Token Plan overview](https://platform.minimax.io/docs/token-plan/intro) and the [subscription pricing page](https://platform.minimax.io/docs/guides/pricing-token-plan).
201
+ >
202
+ > **Source for the same-config claim:** the Token Plan docs show `https://api.minimax.io/v1` + model id `MiniMax-M3` for the OpenAI-compatible path and `https://api.minimax.io/anthropic` for the Anthropic-compatible path, with the same request body fields the PAYG path uses — see [Other Tools › Configuration Reference](https://platform.minimax.io/docs/token-plan/other-tools#configuration-reference). The FAQ explicitly says: _"Can the Subscription Key and the standard Open Platform API Key be used interchangeably? No, they cannot."_ — the **keys are not swappable, but the endpoint, model id, and `requestBody` are.**
157
203
 
158
204
  ---
159
205
 
@@ -243,5 +289,9 @@ Asked the model to inspect a YouTube video (`https://www.youtube.com/watch?v=rAz
243
289
  - MiniMax Pricing: `https://platform.minimax.io/docs/pricing/overview`
244
290
  - MiniMax Pay as You Go: `https://platform.minimax.io/docs/guides/pricing-paygo`
245
291
  - MiniMax Token Plan: `https://platform.minimax.io/docs/guides/pricing-token-plan`
292
+ - MiniMax Token Plan Overview: `https://platform.minimax.io/docs/token-plan/intro`
293
+ - MiniMax Token Plan Quickstart: `https://platform.minimax.io/docs/token-plan/quickstart`
294
+ - MiniMax Token Plan FAQ (key interchangeability, quota windows, platform limits): `https://platform.minimax.io/docs/token-plan/faq`
295
+ - MiniMax Token Plan — Other Tools configuration reference (same endpoint + model id for PAYG and Token Plan): `https://platform.minimax.io/docs/token-plan/other-tools#configuration-reference`
246
296
  - MiniMax Rate Limits: `https://platform.minimax.io/docs/guides/rate-limits`
247
297
  - MiniMax M3 for AI Coding Tools: `https://platform.minimax.io/docs/guides/text-ai-coding-tools`
@@ -7,6 +7,7 @@
7
7
  | Field | Value |
8
8
  | ------------------------------- | -------------------------------------------------------------------------------- |
9
9
  | Mode | **Proxy** (local on `:3458`) **or** **Direct** (static `enable_thinking: false`) |
10
+ | Billing | **Pay-as-You-Go only** — no subscription; 1M-token free quota for new users |
10
11
  | Vision | ✅ Yes (`qwen3.7-plus`) |
11
12
  | Tool calling | ✅ Yes |
12
13
  | Context | 1M |
@@ -182,12 +183,14 @@ The proxy detects active tool use by examining the conversation state, not just
182
183
 
183
184
  ### API key
184
185
 
186
+ DashScope is **Pay-as-You-Go only** — there is no monthly subscription plan. However, Alibaba Cloud grants a **free quota** of **1M input + 1M output tokens per model** (valid 90 days) for new Model Studio users. Prepaid token resource packages are also available through the Alibaba Cloud console for discounted rates, but these are prepaid credits, not a subscription.
187
+
185
188
  1. Open the Command Palette (`Ctrl+Shift+P`).
186
189
  2. Run **Chat: Manage Language Models**.
187
190
  3. Find the **Qwen** group → **Update API Key**.
188
191
  4. Paste your DashScope API key.
189
192
 
190
- > After setting via the UI, VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference.
193
+ > After setting via the UI, VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference. API keys are generated at `dashscope-intl.aliyuncs.com` (international) or `dashscope.aliyuncs.com` (China) and are region-specific.
191
194
 
192
195
  ## Configuration Reference
193
196
 
package/docs/pricing.md CHANGED
@@ -23,10 +23,11 @@ All models are listed together below, sorted by Cost per intelligence ascending
23
23
  | Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
24
24
  | ---------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
25
25
  | **DeepSeek V4 Flash** | DeepSeek | **~$0.0025** | **40.3** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
26
+ | **MiMo V2.5** | Xiaomi | **~$0.0025** | **40** ³ | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
26
27
  | **MiniMax M3** | MiniMax | **~$0.0061** | **44.4** | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | ~$0.27 | 1M |
27
28
  | **DeepSeek V4 Pro** | DeepSeek | **~$0.0068** | **44.3** | $0.435 | $0.003625 | $0.87 | ~$0.30 | 1M |
29
+ | **MiMo V2.5 Pro** | Xiaomi | **~$0.0072** | **42.2** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
28
30
  | **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | $0.40 (≤256K) / $1.20 (>256K) | — | $1.60 (≤256K) / $4.80 (>256K) | ~$0.36 | 1M |
29
- | **MiMo V2.5 Pro** | Xiaomi | **~$0.019** | **42.2** | $1.00 | $0.20 | $3.00 | ~$0.80 | 1M |
30
31
  | **Gemini 3 Flash** | Google | **~$0.020** | **27.0** ³ | $0.50 | $0.05 | $3.00 | ~$0.55 | 173K |
31
32
  | **Kimi K2.6** | Moonshot | **~$0.021** | **42.8** | $0.95 | $0.16 | $4.00 | ~$0.88 | 256K |
32
33
  | **Kimi K2.7 Code** | Moonshot | **~$0.021** | **42.0** | $0.95 | $0.19 | $4.00 | ~$0.88 | 262K |
@@ -44,7 +45,6 @@ All models are listed together below, sorted by Cost per intelligence ascending
44
45
  | **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
45
46
  | **GPT-5.5** | OpenAI | **~$0.10** | **54.8** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
46
47
  | **Raptor mini** | GitHub | — | — | $0.25 | $0.025 | $2.00 | ~$0.33 | 264K |
47
- | **MiMo V2.5** | Xiaomi | — | — | $0.40 | $0.08 | $2.00 | ~$0.40 | 1M |
48
48
  | **MAI-Code-1-Flash** ² | Microsoft | — | — | $0.75 | $0.075 | $4.50 | ~$0.83 | — |
49
49
  | **Claude Haiku 4.5** | Anthropic | — | — | $1.00 | $0.10 | $5.00 | ~$1.00 | 160K |
50
50
 
@@ -61,7 +61,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
61
61
  > **Notes:**
62
62
  >
63
63
  > - **DeepSeek V4** input pricing shown is the **cache miss** price. Cache hits are significantly cheaper ($0.0028/M for Flash, $0.003625/M for Pro).
64
- > - **MiMo** input pricing shown is the **cache miss** price. Cache hits are 5× cheaper for V2.5 Pro ($0.20/M) and V2.5 ($0.08/M).
64
+ > - **MiMo** input pricing shown is the **cache miss** price. Cache hits are essentially free for V2.5 Pro ($0.0036/M, ~120× cheaper) and V2.5 ($0.0028/M, ~50× cheaper). A Xiaomi price cut took effect on 2026-05-27.
65
65
  > - **Gemini 3 Flash** is priced at $0.50/MTok input (text/image/video) and $1.00/MTok input for audio.
66
66
  > - **Anthropic (Claude)** models also have a cache write cost ($6.25/MTok for Opus, $3.75/MTok for Sonnet, $1.25/MTok for Haiku). Opus 4.7+ use a new tokenizer that may use up to 35% more tokens for the same text.
67
67
  > - **OpenAI** models support cached input at 0.1× base input rate.
@@ -77,7 +77,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
77
77
 
78
78
  > **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.)
79
79
 
80
- > Prices last verified: June 14, 2026. Always check the official pages for the latest rates:
80
+ > Prices last verified: June 27, 2026. Always check the official pages for the latest rates:
81
81
  >
82
82
  > - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
83
83
  > - [Microsoft MAI-Code-1-Flash model card](https://docs.github.com/en/copilot/reference/ai-models/model-comparison#task-general-purpose-coding-and-writing)
@@ -86,6 +86,6 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
86
86
  > - [Google Gemini pricing](https://ai.google.dev/pricing)
87
87
  > - [DashScope pricing](https://www.alibabacloud.com/help/en/model-studio/billing-for-model-studio)
88
88
  > - [DeepSeek pricing](https://api-docs.deepseek.com/quick_start/pricing)
89
- > - [MiMo pricing](https://platform.xiaomimimo.com/docs/en-US/pricing)
89
+ > - [MiMo pricing](https://mimo.mi.com/docs/en-US/pricing)
90
90
  > - [MiniMax pricing](https://platform.minimax.io/docs/pricing/overview)
91
91
  > - [Z.ai (GLM) pricing](https://docs.z.ai/guides/overview/pricing)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "copilot-custom-endpoint",
3
- "version": "1.6.4",
3
+ "version": "1.6.6",
4
4
  "description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2, Qwen 3.x & MiMo V2.5",
5
5
  "license": "MIT",
6
6
  "type": "module",