copilot-custom-endpoint 3.3.2 → 3.4.0

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
@@ -121,10 +121,11 @@ It approximates the cost of one point on the AA Intelligence Index under the com
121
121
 
122
122
  For example, GLM 5.3 Flash is `(0.5 × $0.15) + (0.1 × $0.50) = $0.125`, shown as `~$0.13`. Cached-input discounts are not included. Actual costs vary with context length, output length, caching, pricing tiers, promotions, and provider billing. DeepSeek estimates use peak rates; official off-peak rates are half.
123
123
 
124
- The current AA values come from OpenRouter's September 23 model metadata and ranking card; **every pricing cell comes from first-party provider pricing or GitHub Copilot's official billing table, never OpenRouter.** The OpenRouter ranking card places unversioned Qwen3.8 Max at **53.4 (#2)**, while the exact 0902 API metadata row is **45.4**. Qwen Cloud PAYG pricing remains **$2 / $0.25 implicit cache / $6** for Qwen3.8 Max; its separate Token Plan is not the PAYG rate table. This refresh records Gemini 3.8 Flash, Grok 4.7, GPT-6 Sol, GPT-6 Luna, and Claude Opus 5.5 as **Copilot-native** models, using current AA v4.3.2 composites.
124
+ The current AA values come from OpenRouter's September 30 model metadata and ranking card; **every pricing cell comes from first-party provider pricing or GitHub Copilot's official billing table, never OpenRouter.** The OpenRouter ranking card places unversioned Qwen3.8 Max at **53.4 (#2)**, while the exact 0902 API metadata row is **45.4**. Qwen Cloud PAYG pricing remains **$2 / $0.25 implicit cache / $6** for Qwen3.8 Max; its separate Token Plan is not the PAYG rate table. This refresh records Gemini 3.8 Flash, Grok 4.7, GPT-6 Sol, GPT-6.1 Sol, GPT-6 Luna, Claude Opus 5.5, and Claude Sonnet 5.5 as **Copilot-native** models, using current AA v4.3.2 composites. GPT-6.1 Sol (released September 29) enters at **51.8**, and MiMo V2.6 Flash now has a composite (**37.9**) and moves to the top of the table.
125
125
 
126
126
  | Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
127
127
  | ---------------------------- | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
128
+ | **MiMo V2.6 Flash** | Xiaomi | **~$0.0026** | **37.9** | ~$0.10 | ✅ | 1M |
128
129
  | **GPT-6 Luna** | OpenAI | **~$0.0027** | **37.3** | ~$0.10 | ✅ | 1M |
129
130
  | **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.8** | ~$0.13 | ✅ | 1M |
130
131
  | **GPT-5.6 Luna** | OpenAI | **~$0.0059** | **37.3** | ~$0.22 | ✅ | 1M |
@@ -137,7 +138,9 @@ The current AA values come from OpenRouter's September 23 model metadata and ran
137
138
  | **Qwen 3.8 Max (0803)** | DashScope | **~$0.0300** | **53.4** | ~$1.60 | ✅ | 1M |
138
139
  | **Grok 4.7** | xAI | **~$0.0345** | **46.4** | ~$1.60 | ✅ | 500K |
139
140
  | **Qwen 3.8 Max (0902)** | DashScope | **~$0.0352** | **45.4** | ~$1.60 | ✅ | 1M |
141
+ | **Claude Sonnet 5.5** | Anthropic | **~$0.0357** | **56.0** | ~$2.00 | ✅ | 1M |
140
142
  | **Grok 4.6** | xAI | **~$0.0361** | **44.3** | ~$1.60 | ✅ | 500K |
143
+ | **GPT-6.1 Sol** | OpenAI | **~$0.0386** | **51.8** | ~$2.00 | ✅ | 1M |
141
144
  | **GPT-6 Sol** | OpenAI | **~$0.0421** | **47.5** | ~$2.00 | ✅ | 1M |
142
145
  | **GPT-5.6 Terra** | OpenAI | **~$0.0523** | **42.1** | ~$2.20 | ✅ | 1M |
143
146
  | **Claude Sonnet 5** | Anthropic | **~$0.0524** | **38.2** | ~$2.00 | ✅ | 1M |
@@ -149,17 +152,17 @@ The current AA values come from OpenRouter's September 23 model metadata and ran
149
152
  | **Claude Fable 5.1** | Anthropic | **~$0.1873** | **53.4** | ~$10.00 | ✅ | 1M |
150
153
  | **GPT-6 Astra** | OpenAI | **~$0.1898** | **52.7** | ~$10.00 | ✅ | 1M |
151
154
  | **Claude Fable 5** | Anthropic | **~$0.2016** | **49.6** | ~$10.00 | ✅ | 1M |
152
- | **MiMo V2.6 Flash** | Xiaomi | — | — | ~$0.10 | ✅ | 1M |
153
155
 
154
- > `MiMo V2.6 Pro UltraSpeed` uses the MiMo V2.6 Pro benchmark score because it is the same-quality latency tier; no independent composite is published. `MiniMax M3 Priority` is intentionally omitted from this snapshot because it is the same model with a priority service tier; the full pricing table documents its separate tier cost. `MiMo V2.6 Flash` has no OpenRouter composite score; Xiaomi's published launch benchmarks for it are recorded in [docs/benchmarks.md](docs/benchmarks.md).
155
- > GPT-6 Sol and Luna use standard rates up to 272K input tokens; requests above that threshold have higher input/cache and output rates. GitHub Copilot also bills cache writes separately. Plan access differs: Sol requires Pro+ or higher, Luna is available from Pro, and Claude Opus 5.5 requires Pro+ or higher.
156
+ > `MiMo V2.6 Pro UltraSpeed` uses the MiMo V2.6 Pro benchmark score because it is the same-quality latency tier; no independent composite is published. `MiniMax M3 Priority` is intentionally omitted from this snapshot because it is the same model with a priority service tier; the full pricing table documents its separate tier cost. `MiMo V2.6 Flash`'s composite (37.9) is OpenRouter's Artificial Analysis v4.3.2 value; Xiaomi's published launch benchmarks for it are recorded in [docs/benchmarks.md](docs/benchmarks.md).
157
+ > GPT-6 Sol, GPT-6.1 Sol, and Luna use standard rates up to 272K input tokens; requests above that threshold have higher input/cache and output rates. GitHub Copilot also bills cache writes separately. Plan access differs: GPT-6 Sol and GPT-6.1 Sol require Pro+ or higher, Luna and Claude Sonnet 5.5 are available from Pro, and Claude Opus 5.5 requires Pro+ or higher.
156
158
 
157
159
  > Detailed pricing, benchmark provenance, and model-specific notes live in [docs/pricing.md](docs/pricing.md) and [docs/benchmarks.md](docs/benchmarks.md). This page stays focused on setup and model selection. For a copy-paste config containing **all providers at once**, see [docs/example-config.md](docs/example-config.md).
158
160
 
159
161
  > **👤 Personal picks** —
160
162
  >
161
- > - **GPT-6 Luna** — the lowest cost per intelligence in this table (~$0.0027), at about $0.10/session with vision.
162
- > - **GLM 5.3 Flash** — the lowest cost per intelligence among custom-endpoint models (~$0.0030), at about $0.13/session with vision.
163
+ > - **MiMo V2.6 Flash** — the lowest cost per intelligence in this table (~$0.0026), at about $0.10/session with vision.
164
+ > - **GPT-6 Luna** — the lowest cost per intelligence among Copilot-native models (~$0.0027), at about $0.10/session with vision.
165
+ > - **GLM 5.3 Flash** — the runner-up among custom-endpoint models (~$0.0030), at about $0.13/session with vision.
163
166
 
164
167
  ## Companion tools
165
168
 
@@ -212,7 +215,7 @@ GitHub ships a first-party MCP server (and it's even bundled into Copilot), so a
212
215
  2. If the provider needs request rewriting, add a proxy under `proxy/`.
213
216
  3. Submit a PR.
214
217
 
215
- The current AA values come from OpenRouter's September 23 model metadata and ranking card; **every pricing cell comes from first-party provider pricing or GitHub Copilot's official billing table, never OpenRouter.** The OpenRouter ranking card places unversioned Qwen3.8 Max at **53.4 (#2)**, while the exact 0902 API metadata row is **45.4**. Qwen Cloud PAYG pricing remains **$2 / $0.25 implicit cache / $6** for Qwen3.8 Max; its separate Token Plan is not the PAYG rate table. This refresh records Gemini 3.8 Flash, Grok 4.7, GPT-6 Sol, GPT-6 Luna, and Claude Opus 5.5 as **Copilot-native** models, using current AA v4.3.2 composites.
218
+ The current AA values come from OpenRouter's September 30 model metadata and ranking card; **every pricing cell comes from first-party provider pricing or GitHub Copilot's official billing table, never OpenRouter.** The OpenRouter ranking card places unversioned Qwen3.8 Max at **53.4 (#2)**, while the exact 0902 API metadata row is **45.4**. Qwen Cloud PAYG pricing remains **$2 / $0.25 implicit cache / $6** for Qwen3.8 Max; its separate Token Plan is not the PAYG rate table. This refresh records Gemini 3.8 Flash, Grok 4.7, GPT-6 Sol, GPT-6.1 Sol, GPT-6 Luna, Claude Opus 5.5, and Claude Sonnet 5.5 as **Copilot-native** models, using current AA v4.3.2 composites. GPT-6.1 Sol (released September 29) enters at **51.8**, and MiMo V2.6 Flash now has a composite (**37.9**).
216
219
 
217
220
  - **Chat only.** Inline completions, semantic search, and next-edit suggestions still need a GitHub-hosted model.
218
221
  - Each proxy is tuned for a specific provider family. Don't point the Kimi proxy at an arbitrary OpenAI-compatible endpoint.
@@ -1,22 +1,23 @@
1
1
  # Qwen (DashScope) — VS Code Custom Endpoint Setup Guide
2
2
 
3
- > **TL;DR:** `qwen3.8-max` (vision) works both direct and via the local proxy. OpenRouter's live rankings card shows unversioned Qwen3.8 Max at **#2 with 53.4**, while the exact `qwen/qwen3.8-max-0902` API metadata row is **45.4**; the public API no longer exposes the unversioned ID. The proxy forwards the upstream `model` value unchanged, so use the exact model ID supported by the endpoint you choose. The proxy gives you dynamic thinking suppression: reasoning stays ON in plain chat but turns OFF automatically when tools are invoked. The direct path is simpler if you don't need reasoning in chat.
3
+ > **TL;DR:** `qwen3.8-max` (vision) works both direct and via the local proxy. OpenRouter's live rankings card shows unversioned Qwen3.8 Max at **#2 with 53.4**, while the exact `qwen/qwen3.8-max-0902` API metadata row is **45.4**; the public API no longer exposes the unversioned ID. The proxy forwards the upstream `model` value unchanged, so use the exact model ID supported by the endpoint you choose. The proxy gives you dynamic thinking suppression: reasoning stays ON in plain chat but turns OFF automatically when tools are invoked. The direct path is simpler if you don't need reasoning in chat. Use the **OpenAI-compatible** endpoint on your **workspace-dedicated** domain ([details](#which-endpoint-to-use)).
4
4
 
5
5
  ## At a Glance
6
6
 
7
- | Field | Value |
8
- | ---------------------- | -------------------------------------------------------------------------------- |
9
- | Mode | **Proxy** (local on `:3458`) **or** **Direct** (static `enable_thinking: false`) |
10
- | Billing | **Pay-as-You-Go only** — 1M-token free quota for new users |
11
- | Vision | ✅ Yes (`qwen3.8-max`) |
12
- | Tool calling | ✅ Yes |
13
- | Context | 1M |
14
- | Max output | 131K |
15
- | Endpoint | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions` |
16
- | Proxy endpoint | `http://127.0.0.1:3458/v1/chat/completions` |
17
- | Auth | `Authorization: Bearer $DASHSCOPE_API_KEY` |
18
- | `requestBody` (direct) | `enable_thinking: false` |
19
- | `requestBody` (proxy) | _none — proxy injects based on tool activity_ |
7
+ | Field | Value |
8
+ | ---------------------- | -------------------------------------------------------------------------------------------------- |
9
+ | Mode | **Proxy** (local on `:3458`) **or** **Direct** (static `enable_thinking: false`) |
10
+ | Billing | **Pay-as-You-Go only** — 1M-token free quota for new users |
11
+ | Vision | ✅ Yes (`qwen3.8-max`) |
12
+ | Tool calling | ✅ Yes |
13
+ | Context | 1M |
14
+ | Max output | 131K |
15
+ | Protocol | **OpenAI-compatible** (`/compatible-mode/v1`) — not native DashScope (`/api/v1`) |
16
+ | Endpoint | `https://<your-workspace-id>.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions` |
17
+ | Proxy endpoint | `http://127.0.0.1:3458/v1/chat/completions` |
18
+ | Auth | `Authorization: Bearer $DASHSCOPE_API_KEY` |
19
+ | `requestBody` (direct) | `enable_thinking: false` |
20
+ | `requestBody` (proxy) | _none — proxy injects based on tool activity_ |
20
21
 
21
22
  ### Models
22
23
 
@@ -92,30 +93,38 @@ Set the API key through **Chat: Manage Language Models**, then verify the proxy
92
93
 
93
94
  ### With Proxy (recommended)
94
95
 
95
- 1. **Start the proxy:** `npm run proxy:qwen` (or `npx copilot-custom-endpoint qwen`).
96
- 2. **Use the proxy-path JSON snippet** below.
97
- 3. **Set your DashScope API key** via Command Palette → **Chat: Manage Language Models**.
98
- 4. **Configure the Utility Small Model** — Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4 Flash or MiMo V2.6 Flash). [Why?](../../README.md#4-configure-the-utility-small-model)
99
- 5. **Restart VS Code.** Reasoning will be visible in plain chat and suppressed on tool turns.
96
+ 1. **Set the upstream:** add `QWEN_UPSTREAM_URL=https://<your-workspace-id>.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions` to the git-ignored repo-root `.env` ([why this endpoint](#which-endpoint-to-use)). Without it the proxy falls back to the legacy shared DashScope domain.
97
+ 2. **Start the proxy:** `npm run proxy:qwen` (or `npx copilot-custom-endpoint qwen`).
98
+ 3. **Use the proxy-path JSON snippet** below.
99
+ 4. **Set your DashScope API key** via Command Palette → **Chat: Manage Language Models**.
100
+ 5. **Configure the Utility Small Model** — Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4 Flash or MiMo V2.6 Flash). [Why?](../../README.md#4-configure-the-utility-small-model)
101
+ 6. **Restart VS Code.** Reasoning will be visible in plain chat and suppressed on tool turns.
100
102
 
101
103
  ### Direct (no proxy)
102
104
 
103
- 1. **Use the direct-path JSON snippet** below.
105
+ 1. **Use the direct-path JSON snippet** below and replace `<your-workspace-id>` in `url` with your workspace ID.
104
106
  2. **Set your `DASHSCOPE_API_KEY`** via Command Palette → **Chat: Manage Language Models**.
105
107
  3. **Configure the Utility Small Model** — Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4 Flash or MiMo V2.6 Flash). [Why?](../../README.md#4-configure-the-utility-small-model)
106
108
  4. **Restart VS Code** and pick "Qwen 3.8 Max".
107
109
 
108
110
  ## Setup
109
111
 
110
- ### Regional endpoints
112
+ ### Which endpoint to use
111
113
 
112
- DashScope is region-specific — your API key only works on the endpoint it was created for:
114
+ Model Studio's **API Quick Access** dialog (shown once, right after you create a key) lists an **API Host**, an **OpenAI Compatible Endpoint**, and a **DashScope** URL. Two choices matter:
113
115
 
114
- | Region | Endpoint |
115
- | ------------- | ------------------------------------------------------------------------- |
116
- | Singapore | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions` |
117
- | China | `https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions` |
118
- | US (Virginia) | `https://dashscope-us.aliyuncs.com/compatible-mode/v1/chat/completions` |
116
+ - **Protocol — OpenAI-compatible (`/compatible-mode/v1`).** VS Code's `chat-completions` custom endpoint and `proxy/qwen-proxy.mjs` speak the OpenAI Chat Completions schema. The **DashScope** card (`/api/v1`) is the native DashScope protocol (`input.messages` requests, `output.choices` responses, `{code, message, request_id}` errors) and does not work here.
117
+ - **Domain — workspace-dedicated (`<workspace-id>.<region>.maas.aliyuncs.com`).** Alibaba recommends it for production: higher concurrency, network isolation, and a 3600 s request timeout (600 s on the legacy DashScope domains, which Alibaba says stop supporting new features after September 30, 2026). The legacy domains still work, so existing setups keep running.
118
+
119
+ The chat URL is `https://` + domain + `/compatible-mode/v1/chat/completions`. Copy the domain from the API Quick Access dialog (or the **API Host** column on Workspace Management); the **OpenAI Compatible Endpoint** value plus `/chat/completions` gives the same URL.
120
+
121
+ | Region | Workspace-dedicated domain (recommended) | Legacy DashScope domain |
122
+ | ------------- | ------------------------------------------------------ | ----------------------------- |
123
+ | Singapore | `<your-workspace-id>.ap-southeast-1.maas.aliyuncs.com` | `dashscope-intl.aliyuncs.com` |
124
+ | China | `<your-workspace-id>.cn-beijing.maas.aliyuncs.com` | `dashscope.aliyuncs.com` |
125
+ | US (Virginia) | `<your-workspace-id>.us-east-1.maas.aliyuncs.com` | `dashscope-us.aliyuncs.com` |
126
+
127
+ API keys are bound to their region (and, on a workspace-dedicated domain, to their workspace); a mismatch returns `401 invalid_api_key`. Source: [Alibaba Cloud Model Studio — Regions and endpoints](https://www.alibabacloud.com/help/en/model-studio/regions).
119
128
 
120
129
  ### 1. VS Code configuration
121
130
 
@@ -137,7 +146,7 @@ DashScope is region-specific — your API key only works on the endpoint it was
137
146
  {
138
147
  "id": "qwen3.8-max",
139
148
  "name": "Qwen 3.8 Max (vision)",
140
- "url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
149
+ "url": "https://<your-workspace-id>.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions",
141
150
  "toolCalling": true,
142
151
  "vision": true,
143
152
  "streaming": true,
@@ -200,6 +209,8 @@ DashScope is **Pay-as-You-Go only** — but new Model Studio users get **1M inpu
200
209
  4. Paste your DashScope API key.
201
210
 
202
211
  > VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference. Keys are region-specific.
212
+ >
213
+ > New keys start with `sk-ws-` and are shown only once, in the **API Quick Access** dialog — copy the key before closing it. Older `sk-` keys keep working.
203
214
 
204
215
  ## Local Proxy
205
216
 
@@ -217,12 +228,12 @@ The `proxy/qwen-proxy.mjs` adds dynamic thinking suppression on top of the direc
217
228
 
218
229
  Set in `.env` at the repo root (the proxy `import 'dotenv/config'` automatically).
219
230
 
220
- | Variable | Default | Purpose |
221
- | ---------------------------------------- | ------------------------------------------------------------------------- | -------------------------------------------------- |
222
- | `QWEN_PROXY_PORT` | `3458` | Local listen port |
223
- | `QWEN_UPSTREAM_URL` | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions` | Upstream DashScope endpoint |
224
- | `QWEN_PROXY_LOG` | `debug_log/qwen-proxy.ndjson` | Redacted NDJSON log path |
225
- | `QWEN_PROXY_DISABLE_THINKING_WITH_TOOLS` | `1` | Set to `0` to skip tool-aware thinking suppression |
231
+ | Variable | Default | Purpose |
232
+ | ---------------------------------------- | ---------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |
233
+ | `QWEN_PROXY_PORT` | `3458` | Local listen port |
234
+ | `QWEN_UPSTREAM_URL` | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions` (legacy) | Upstream OpenAI-compatible endpoint — set to your workspace-dedicated URL (recommended) |
235
+ | `QWEN_PROXY_LOG` | `debug_log/qwen-proxy.ndjson` | Redacted NDJSON log path |
236
+ | `QWEN_PROXY_DISABLE_THINKING_WITH_TOOLS` | `1` | Set to `0` to skip tool-aware thinking suppression |
226
237
 
227
238
  ### What the proxy does
228
239
 
@@ -250,14 +261,15 @@ The proxy detects active tool use by examining the conversation state (a `"tool"
250
261
 
251
262
  ## Troubleshooting
252
263
 
253
- | Symptom | Likely cause | Fix |
254
- | ----------------------------------------------- | -------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
255
- | "Connection refused" (proxy mode) | Proxy not running | `npm run proxy:qwen` |
256
- | Tool loops fail with `reasoning_content` errors | Direct path missing `enable_thinking: false` | Add `enable_thinking: false` to `requestBody` |
257
- | Tool loops still fail with proxy | Proxy not rewriting | Check `debug_log/qwen-proxy.ndjson` — verify `hasTools: true` requests have `rewrittenEnableThinking: false` |
258
- | Vision fails with external image URL | DashScope couldn't reach the URL | Use a base64 data URI instead |
259
- | 401 Unauthorized | API key region mismatch | Match your key to the regional endpoint |
260
- | Want to switch back to direct | Proxy mode active | Revert `url` to DashScope endpoint and restore `requestBody.enable_thinking: false` |
264
+ | Symptom | Likely cause | Fix |
265
+ | ----------------------------------------------- | ---------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
266
+ | "Connection refused" (proxy mode) | Proxy not running | `npm run proxy:qwen` |
267
+ | Tool loops fail with `reasoning_content` errors | Direct path missing `enable_thinking: false` | Add `enable_thinking: false` to `requestBody` |
268
+ | Tool loops still fail with proxy | Proxy not rewriting | Check `debug_log/qwen-proxy.ndjson` — verify `hasTools: true` requests have `rewrittenEnableThinking: false` |
269
+ | Vision fails with external image URL | DashScope couldn't reach the URL | Use a base64 data URI instead |
270
+ | 401 Unauthorized | API key region or workspace mismatch | Match your key to the endpoint's region (and workspace, on a workspace-dedicated domain) |
271
+ | 404 Not Found | URL uses the native DashScope path (`/api/v1`) or omits the path | Use `/compatible-mode/v1/chat/completions` |
272
+ | Want to switch back to direct | Proxy mode active | Revert `url` to DashScope endpoint and restore `requestBody.enable_thinking: false` |
261
273
 
262
274
  ## Pricing
263
275
 
package/docs/pricing.md CHANGED
@@ -1,6 +1,10 @@
1
1
  # Pricing
2
2
 
3
- > **Latest refresh (September 23, 2026):** OpenRouter's current metadata uses Artificial Analysis v4.3.2 composites. The September 22 Copilot releases add Claude Opus 5.5 (**57.6**), GPT-6 Sol (**47.5**), and GPT-6 Luna (**37.3**) to the roster. The API list rates are **$4 / $0.20 cache hit / $20** for Opus 5.5, **$2 / $0.20 / $10** for Sol, and **$0.10 / $0.01 / $0.50** for Luna. MiMo V2.6 Pro is **46.3**, Grok 4.7 is **46.4**, and current values for existing rows are refreshed below. Gemini 3.8 Flash is also available as a GitHub Copilot native model. Xiaomi released the V2.6 Pro, Flash, and Pro UltraSpeed models on September 22; the September 23 roster cleanup removes two retired legacy models. xAI released Grok 4.7 on September 21 at the same short-context rates as Grok 4.6: **$2 / $0.50 cache hit / $6**. The table preserves Qwen's 0803 ranking-card value (**53.4**) and 0902 metadata value (**45.4**) as separate records. The current table is authoritative for present comparisons.
3
+ > **Latest refresh (September 30, 2026):** GPT-6.1 Sol (released September 29 at OpenAI DevDay; GA in GitHub Copilot the same day for Pro+, Max, Business, and Enterprise) is added at **$2 / $0.10 cache hit / $10** per 1M tokens — identical input/output to GPT-6 Sol, with cache hits at half the rate ($0.10 vs $0.20) — and an Artificial Analysis v4.3.2 composite of **51.8**, so at **~$0.0386** per intelligence point it sorts between Grok 4.6 and GPT-6 Sol. OpenAI cancelled the planned **GPT-6.1 Astra** over safety concerns, so no such row exists. Every other composite and first-party rate was re-checked against live OpenRouter metadata and provider pages with no changes.
4
+ >
5
+ > **Earlier refresh (September 29, 2026):** Claude Sonnet 5.5 (released September 28, GA in GitHub Copilot from Pro) is added at **$2 / $0.20 cache hit / $10** per 1M tokens, unchanged from Sonnet 5, with an Artificial Analysis v4.3.2 composite of **56.0**. MiMo V2.6 Flash now has a composite (**37.9**), so it is scored and sorted instead of listed last; at ~$0.0026 it is the lowest cost per intelligence in the table. All other first-party rates were re-verified with no changes.
6
+ >
7
+ > **Earlier refresh (September 23, 2026):** OpenRouter's current metadata uses Artificial Analysis v4.3.2 composites. The September 22 Copilot releases add Claude Opus 5.5 (**57.6**), GPT-6 Sol (**47.5**), and GPT-6 Luna (**37.3**) to the roster. The API list rates are **$4 / $0.20 cache hit / $20** for Opus 5.5, **$2 / $0.20 / $10** for Sol, and **$0.10 / $0.01 / $0.50** for Luna. MiMo V2.6 Pro is **46.3**, Grok 4.7 is **46.4**, and current values for existing rows are refreshed below. Gemini 3.8 Flash is also available as a GitHub Copilot native model. Xiaomi released the V2.6 Pro, Flash, and Pro UltraSpeed models on September 22; the September 23 roster cleanup removes two retired legacy models. xAI released Grok 4.7 on September 21 at the same short-context rates as Grok 4.6: **$2 / $0.50 cache hit / $6**. The table preserves Qwen's 0803 ranking-card value (**53.4**) and 0902 metadata value (**45.4**) as separate records. The current table is authoritative for present comparisons.
4
8
 
5
9
  > **⏰ June 1, 2026 — GitHub Copilot switched to usage-based billing (AI Credits) today.**
6
10
  >
@@ -24,6 +28,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
24
28
 
25
29
  | Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
26
30
  | ---------------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
31
+ | **MiMo V2.6 Flash** | Xiaomi | **~$0.0026** | **37.9** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
27
32
  | **GPT-6 Luna** | OpenAI | **~$0.0027** | **37.3** | $0.10 | $0.01 | $0.50 | ~$0.10 | 1M |
28
33
  | **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.8** | $0.15 | $0.03 | $0.50 | ~$0.13 | 1M |
29
34
  | **GPT-5.6 Luna** | OpenAI | **~$0.0059** | **37.3** | $0.20 | $0.02 | $1.20 | ~$0.22 | 1M |
@@ -37,7 +42,9 @@ All models are listed together below, sorted by Cost per intelligence ascending
37
42
  | **Qwen 3.8 Max (0803)** | DashScope | **~$0.0300** | **53.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
38
43
  | **Grok 4.7** | xAI | **~$0.0345** | **46.4** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
39
44
  | **Qwen 3.8 Max (0902)** | DashScope | **~$0.0352** | **45.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
45
+ | **Claude Sonnet 5.5** | Anthropic | **~$0.0357** | **56.0** | $2.00 | $0.20 | $10.00 | ~$2.00 | 1M |
40
46
  | **Grok 4.6** | xAI | **~$0.0361** | **44.3** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
47
+ | **GPT-6.1 Sol** | OpenAI | **~$0.0386** | **51.8** | $2.00 | $0.10 | $10.00 | ~$2.00 | 1M |
41
48
  | **GPT-6 Sol** | OpenAI | **~$0.0421** | **47.5** | $2.00 | $0.20 | $10.00 | ~$2.00 | 1M |
42
49
  | **GPT-5.6 Terra** | OpenAI | **~$0.0523** | **42.1** | $2.00 | $0.20 | $12.00 | ~$2.20 | 1M |
43
50
  | **Claude Sonnet 5** | Anthropic | **~$0.0524** | **38.2** | $2.00 | $0.20 | $10.00 | ~$2.00 | 1M |
@@ -49,7 +56,6 @@ All models are listed together below, sorted by Cost per intelligence ascending
49
56
  | **Claude Fable 5.1** | Anthropic | **~$0.1873** | **53.4** | $10.00 | $0.25 | $50.00 | ~$10.00 | 1M |
50
57
  | **GPT-6 Astra** | OpenAI | **~$0.1898** | **52.7** | $10.00 | $1.00 | $50.00 | ~$10.00 | 1M |
51
58
  | **Claude Fable 5** | Anthropic | **~$0.2016** | **49.6** | $10.00 | $1.00 | $50.00 | ~$10.00 | 1M |
52
- | **MiMo V2.6 Flash** | Xiaomi | — | — | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
53
59
 
54
60
  Cost per intelligence = estimated session cost ÷ Intelligence Index score. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
55
61
 
@@ -57,20 +63,20 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
57
63
  >
58
64
  > - **DeepSeek** input pricing shown is the **peak cache miss** price. Peak cache hits are $0.006/M for V4.1 Flash and $0.044/M for Pro; off-peak rates are half. See the [DeepSeek pricing page](https://api-docs.deepseek.com/quick_start/pricing) for the full schedule.
59
65
  > - **MiMo** input pricing shown is the **cache miss** price. Cache hits are essentially free for V2.6 Pro ($0.0036/M, ~120× cheaper), V2.6 Flash ($0.0028/M, ~50× cheaper), and V2.6 Pro UltraSpeed ($0.036/M, ~120× cheaper). A Xiaomi price cut took effect on 2026-05-27.
60
- > - **Anthropic (Claude)** cache reads and cache writes are billed separately. Claude Opus 5.5 cache reads are $0.20/M; cache writes are $5/M for 5 minutes or $8/M for 1 hour. Fast mode costs $8/M input and $40/M output. Opus 5.5, Opus 5, Sonnet 5, and Fable 5 / 5.1 use a newer tokenizer that produces approximately 30% more tokens for the same text.
61
- > - **OpenAI** models support cached input at 0.1× base input rate. GPT-6 Sol and Luna also bill cache writes separately at 1.25× input. The GPT-6 rows show standard rates through 272K input; for requests >272K, input and cache-read rates double and output is 1.5×.
66
+ > - **Anthropic (Claude)** cache reads and cache writes are billed separately. Claude Opus 5.5 cache reads are $0.20/M; cache writes are $5/M for 5 minutes or $8/M for 1 hour. Fast mode costs $8/M input and $40/M output. Opus 5.5, Opus 5, Sonnet 5 / 5.5, and Fable 5 / 5.1 use a newer tokenizer that produces approximately 30% more tokens for the same text. Claude Sonnet 5.5 keeps Sonnet 5's $2 / $0.20 / $10 rates (cache writes $2.50/M for 5 minutes and $4/M for 1 hour; batch $1 / $5), and Anthropic made those rates permanent: the Sonnet 5 increase to $3 / $15 scheduled for September 1 was cancelled. Artificial Analysis measured Sonnet 5.5 at 138.7 tokens/s but very verbose (410M output tokens to run the Intelligence Index vs an 88M median), so real sessions can cost more than this table's modeled token counts; Anthropic reports up to 30% fewer tokens per task than Sonnet 5.
67
+ > - **OpenAI** models support cached input at 0.1× base input rate — except **GPT-6.1 Sol**, whose cache hits are 0.05× ($0.10/M, half of GPT-6 Sol's $0.20/M). GPT-6 Sol, GPT-6.1 Sol, and Luna also bill cache writes separately at 1.25× input. The GPT-6 and GPT-6.1 rows show standard rates through 272K input; for requests >272K, input and cache-read rates double and output is 1.5×.
62
68
  > - **Qwen** models use **tiered pricing** — determined by total input tokens per request. Prices above are for non-thinking mode.
63
- > - **Kimi** official tables list **Cache Hit before Cache Miss** (opposite order to our table). The rows below transpose them so "Input" = cache miss and "Cached input" = cache hit.
69
+ > - **Kimi** official tables list **Cache Hit before Cache Miss** (opposite order to our table; Kimi K3 also bills cache writes separately at $3.00/M for a 5-minute TTL and $6.00/M for 1 hour). The rows below transpose them so "Input" = cache miss and "Cached input" = cache hit.
64
70
  > - **DashScope** offers a **free quota** of 1M input + 1M output tokens per model, valid for 90 days.
65
71
  > - **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.
66
72
  > - **MiniMax M3 Priority** is not a separate model — it is the same `MiniMax-M3` weights invoked with `"service_tier": "priority"` in the request body. Priority costs **1.5× Standard** across input, output, and cache reads, in exchange for **priority admission** (faster responses, fewer failures during MiniMax peak hours — typically 15:00–17:30 weekdays). Capabilities, context window (1M, guaranteed 512K), vision, tool calling, rate limits (200 RPM / 10M TPM), and thinking modes are identical to Standard. See [docs/research/minimax-m3-priority.md](research/minimax-m3-priority.md) for the full breakdown.
67
73
  > - **GLM** models support prompt caching — cache hits are priced at $0.26/M for 5.3 and $0.03/M for 5.3 Flash (list; $0.015/M during the launch promo).
68
- > - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion. MiMo V2.6 Flash has no OpenRouter composite score; Xiaomi's published launch benchmarks for it are recorded in [docs/benchmarks.md](benchmarks.md).
74
+ > - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion. MiMo V2.6 Flash's **37.9** composite comes from OpenRouter's Artificial Analysis v4.3.2 metadata (AA also measures it at 55.4 tokens/s and very verbose); Xiaomi's published launch benchmarks for it are recorded in [docs/benchmarks.md](benchmarks.md).
69
75
  > - For typical Copilot chat usage (short-to-medium prompts), you'll almost always fall in the lowest pricing tier.
70
76
 
71
77
  > **How long does 7,000 credits last?** A Pro+ subscriber running 50-turn sessions can estimate monthly capacity by multiplying each modeled session cost by 100 to convert it to AI credits, then mixing models as needed.
72
78
 
73
- > Prices last verified: September 23, 2026. Always check the official pages for the latest rates:
79
+ > Prices last verified: September 30, 2026. Always check the official pages for the latest rates:
74
80
  >
75
81
  > - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
76
82
  > - [OpenAI pricing](https://openai.com/api/pricing/)
@@ -79,13 +85,18 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
79
85
  > - [OpenAI GPT-6 Sol and Luna announcement](https://openai.com/index/introducing-gpt-6-sol-and-luna/)
80
86
  > - [OpenAI GPT-6 Sol API details](https://developers.openai.com/api/docs/models/gpt-6-sol)
81
87
  > - [OpenAI GPT-6 Luna API details](https://developers.openai.com/api/docs/models/gpt-6-luna)
88
+ > - [OpenAI GPT-6.1 Sol announcement](https://openai.com/index/introducing-gpt-6-1-sol/)
89
+ > - [OpenAI GPT-6.1 Sol API details](https://developers.openai.com/api/docs/models/gpt-6.1-sol)
82
90
  > - [Anthropic (Claude) pricing](https://platform.claude.com/docs/en/about-claude/pricing)
83
91
  > - [Anthropic Claude Opus 5.5 announcement](https://www.anthropic.com/claude-opus-5-5)
84
92
  > - [Anthropic Opus 5.5 API docs](https://platform.claude.com/docs/en/models/opus-5-5/overview)
93
+ > - [Anthropic Claude Sonnet 5.5 announcement](https://www.anthropic.com/claude-sonnet-5-5)
94
+ > - [GitHub Copilot Claude Sonnet 5.5 release](https://github.blog/changelog/2026-09-28-claude-sonnet-5-5-in-github-copilot)
85
95
  > - [GitHub Copilot GPT-6 Sol and Luna release](https://github.blog/changelog/2026-09-22-openais-gpt-6-sol-and-gpt-6-luna-now-available)
96
+ > - [GitHub Copilot GPT-6.1 Sol release](https://github.blog/changelog/2026-09-29-gpt-6-1-sol-in-github-copilot)
86
97
  > - [GitHub Copilot Claude Opus 5.5 release](https://github.blog/changelog/2026-09-22-claude-opus-5-5-is-now-available-in-github-copilot)
87
98
  > - [GitHub Copilot supported models](https://docs.github.com/en/copilot/reference/ai-models/supported-models)
88
- > - [Artificial Analysis GPT-6 Sol](https://artificialanalysis.ai/models/gpt-6-sol), [GPT-6 Luna](https://artificialanalysis.ai/models/gpt-6-luna), and [Claude Opus 5.5](https://artificialanalysis.ai/models/claude-opus-5-5)
99
+ > - [Artificial Analysis GPT-6 Sol](https://artificialanalysis.ai/models/gpt-6-sol), [GPT-6 Luna](https://artificialanalysis.ai/models/gpt-6-luna), [GPT-6.1 Sol](https://artificialanalysis.ai/models/gpt-6-1-sol), [Claude Opus 5.5](https://artificialanalysis.ai/models/claude-opus-5-5), [Claude Sonnet 5.5](https://artificialanalysis.ai/models/claude-sonnet-5-5), and [MiMo-V2.6-Flash](https://artificialanalysis.ai/models/mimo-v2-6-flash)
89
100
  > - [Google Gemini pricing](https://ai.google.dev/pricing)
90
101
  > - [DashScope pricing](https://www.alibabacloud.com/help/en/model-studio/billing-for-model-studio)
91
102
  > - [DeepSeek pricing](https://api-docs.deepseek.com/quick_start/pricing)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "copilot-custom-endpoint",
3
- "version": "3.3.2",
3
+ "version": "3.4.0",
4
4
  "description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2, Qwen 3.x & MiMo V2.6",
5
5
  "license": "MIT",
6
6
  "type": "module",
@@ -57,4 +57,4 @@
57
57
  "dependencies": {
58
58
  "dotenv": "^17.4.2"
59
59
  }
60
- }
60
+ }
@@ -41,9 +41,11 @@ ID qwen3.8-max and OpenRouter ID qwen/qwen3.8-max-0902.
41
41
 
42
42
  Environment variables:
43
43
  QWEN_PROXY_PORT Local listen port. Default: 3458 (falls back to PORT)
44
- QWEN_UPSTREAM_URL Upstream chat-completions URL (DashScope by default;
45
- OpenRouter can be selected for snapshot IDs).
46
- Default: https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions
44
+ QWEN_UPSTREAM_URL Upstream chat-completions URL (OpenAI-compatible path).
45
+ Recommended: your workspace-dedicated endpoint, e.g.
46
+ https://<workspace-id>.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions
47
+ OpenRouter can be selected for snapshot IDs.
48
+ Default (legacy shared domain): https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions
47
49
  QWEN_PROXY_DISABLE_THINKING_WITH_TOOLS
48
50
  Inject enable_thinking: false when tools are present.
49
51
  Default: 1