copilot-custom-endpoint 4.0.0 → 4.1.1

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
@@ -20,17 +20,17 @@ That's it. No code, no servers to manage (unless the model specifically needs th
20
20
 
21
21
  ## Pick a model
22
22
 
23
- | Model | Provider | Needs proxy? | Vision | Setup guide |
24
- | ---------------------------- | --------- | ---------------------- | ------ | ----------------------------------------------------------------------------------------------------------------------------------------- |
25
- | **Kimi K3.1 Pro** | Moonshot | **Yes** | ✅ | [Manual setup](docs/models/kimi.md) |
26
- | **MiMo V2.6 Pro** | Xiaomi | **Yes** | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) / [Manual setup](docs/models/mimo.md) |
27
- | **MiMo V2.6 Flash** | Xiaomi | **Yes** | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) / [Manual setup](docs/models/mimo.md) |
28
- | **MiMo V2.6 Pro UltraSpeed** | Xiaomi | **Yes** | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) / [Manual setup](docs/models/mimo.md) |
29
- | **Qwen 3.8 Max** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
30
- | **MiniMax M3.1 Flash** | MiniMax | No | ✅ | [Manual setup](docs/models/minimax.md) |
31
- | **GLM 5.3 Flash** | Z.ai | No | ✅ | [Manual setup](docs/models/glm.md) |
32
- | **GLM 5.3** | Z.ai | No | ❌ | [Manual setup](docs/models/glm.md) |
33
- | **DeepSeek V4.1 Flash 1017** | DeepSeek | No (uses an extension) | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) / [setup notes](docs/models/deepseek.md) |
23
+ | Model | Provider | Needs proxy? | Vision | Setup guide |
24
+ | ---------------------------- | --------- | ---------------------- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------ |
25
+ | **Kimi K3.1 Pro** | Moonshot | **Yes** | ✅ | [Manual setup](docs/models/kimi.md) |
26
+ | **MiMo V2.6 Pro** | Xiaomi | **Yes** | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) / [Manual setup](docs/models/mimo.md) |
27
+ | **MiMo V2.6 Flash** | Xiaomi | **Yes** | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) / [Manual setup](docs/models/mimo.md) |
28
+ | **MiMo V2.6 Pro UltraSpeed** | Xiaomi | **Yes** | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) / [Manual setup](docs/models/mimo.md) |
29
+ | **Qwen 3.8 Max** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
30
+ | **MiniMax M3.1 Flash** | MiniMax | No | ✅ | [Manual setup](docs/models/minimax.md) |
31
+ | **GLM 5.3 Flash** | Z.ai | No | ✅ | [Manual setup](docs/models/glm.md) |
32
+ | **GLM 5.3** | Z.ai | No | ❌ | [Manual setup](docs/models/glm.md) |
33
+ | **DeepSeek V4.1 Flash 1017** | DeepSeek | No | ✅ | [Manual setup](docs/models/deepseek.md) / [Extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) |
34
34
 
35
35
  ## Setup
36
36
 
@@ -61,7 +61,7 @@ If the file doesn't exist yet, create it with `[]` inside.
61
61
 
62
62
  Open the setup guide for the model you picked (links in the table above) and copy its JSON snippet into the file. Each snippet is a single provider object inside the array.
63
63
 
64
- > **⚠️ Leave `apiKey` as `""`** — a key pasted into this file is **not** used. Measured on VS Code 1.146: an entry with a literal `apiKey` produced `Authorization: Bearer` with an empty token, so the provider answered `401` / "request failed". Use the UI step below.
64
+ > **⚠️ `apiKey` must be non-empty** — the file's schema enforces `minLength: 1`, so `"apiKey": ""` raises _String is shorter than the minimum length of 1_. Keep the `${input:...}` placeholder from the snippet and fill it with the UI step below; a **literal** key pasted into this file is **not** used either. Measured on VS Code 1.146: an entry with a literal `apiKey` produced `Authorization: Bearer` with an empty token, so the provider answered `401` / "request failed".
65
65
 
66
66
  > **The models don't appear in the picker yet.** After editing the file, open **Chat: Manage Language Models** once (or the picker's **Add Models…**) and close it. Measured on 1.146: until the editor has been opened in that window, the picker lists only extension-provided models while the editor already shows your provider.
67
67
 
@@ -139,11 +139,13 @@ The current AA values are **Artificial Analysis Intelligence Index v5.0** compos
139
139
 
140
140
  **Every pricing cell comes from first-party provider pricing or GitHub Copilot’s official billing table, never OpenRouter.** The Qwen 3.8 Max row scores **33.6** under v5.0, and Qwen Cloud PAYG pricing remains **$2 / $0.25 implicit cache / $6**.
141
141
 
142
- This snapshot records Gemini 3.8 Flash, Gemini 4 Argon, Gemini 4 Carbon, Grok 4.7, GPT-6 Sol, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Luna, Claude Fable 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 as **Copilot-native** models.
142
+ This snapshot records Gemini 3.8 Flash, Gemini 4 Argon, Gemini 4 Carbon, Grok 4.7, GPT-6 Sol, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Luna, GPT-6.2 Sol, GPT-6.2 Astra, Claude Fable 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 as **Copilot-native** models.
143
+
144
+ **GPT-6.2 Astra** and **GPT-6.2 Sol** (released November 2026, in Copilot since November 17 for Pro+ and higher) top the OpenAI lineup: Astra scores **62.1** — second overall behind Claude Fable 5.2 — on pricing of **$8 / $0.40 cache read / $40** per 1M tokens (20% below GPT-6 Astra, with 60% off cached input), or **~$0.1288** per intelligence point at roughly **$8.00** per modeled session. GPT-6.2 Sol scores **57.3** while carrying GPT-6.1 Sol's **$2 / $0.10 / $10** rates, or **~$0.0349** per intelligence point. Both have vision and a 1M context.
143
145
 
144
146
  **GPT-6.1 Terra** (released October 2026, in Copilot since October 26) enters at **51** on flat pricing of **$1 / $0.05 cache read / $5** per 1M tokens with vision and a 1M context, which puts it at **~$0.0196** per intelligence point — about half of GPT-6.1 Sol’s **~$0.0367**. Gemini 4 Argon (released October 13, 2026) scores **50.4** on Google’s introductory pricing of **$2 / $0.10 implicit cache / $10** per 1M tokens, which doubles to **$4 / $0.20 / $20** on December 1, 2026.
145
147
 
146
- **Gemini 4 Carbon** (announced October 28, 2026; in Copilot since November 10) scores **60** — second overall behind Claude Fable 5.2 — on the same **$2 / $0.10 / $10** introductory rates as Argon, which also double to **$4 / $0.20 / $20** on December 1. That puts it at **~$0.0333** per intelligence point at roughly **$2.00** per modeled session, but Google notes Carbon spends more tokens per task than Argon, so a real Carbon session costs more at identical rates. Its **60** is Artificial Analysis' current v5.0.1 value; Google's launch post listed **59** under v5.0.
148
+ **Gemini 4 Carbon** (announced October 28, 2026; in Copilot since November 10) scores **60** — third overall behind Claude Fable 5.2 and GPT-6.2 Astra — on the same **$2 / $0.10 / $10** introductory rates as Argon, which also double to **$4 / $0.20 / $20** on December 1. That puts it at **~$0.0333** per intelligence point at roughly **$2.00** per modeled session, but Google notes Carbon spends more tokens per task than Argon, so a real Carbon session costs more at identical rates. Its **60** is Artificial Analysis' current v5.0.1 value; Google's launch post listed **59** under v5.0.
147
149
 
148
150
  **Gemini 4 Hydrogen** (released November 12, 2026) is Google's cheap everyday-execution counterpart to Carbon and Argon, at a flat **$1.50 / $0.075 implicit cache / $7.50** per 1M tokens across the full 1M window — cheaper than Carbon's intro rates and unaffected by the December 1 price step on Argon and Carbon. It scores **54** at its `xhigh` thinking level (**51** at the default `high`), which puts it at **~$0.0278** per intelligence point at roughly **$1.50** per modeled session. It is API-only for now: Google ships it in AI Studio and the Gemini API, including a free tier, but it is not in Copilot, so reaching it means a custom endpoint. Hydrogen always thinks across `low` / `medium` / `high` / `xhigh`, so real token spend tracks the thinking level.
149
151
 
@@ -167,6 +169,7 @@ DeepSeek’s **V4.1-Flash-1017** build (released October 17, 2026) scores **32**
167
169
  | **Gemini 4 Hydrogen** | Google | **~$0.0278** | **54** | ~$1.50 | ✅ | 1M |
168
170
  | **Muse Spark 1.3** | Meta | **~$0.0288** | **36.4** | ~$1.05 | ✅ | 1M |
169
171
  | **Gemini 4 Carbon** | Google | **~$0.0333** | **60** | ~$2.00 | ✅ | 1M |
172
+ | **GPT-6.2 Sol** | OpenAI | **~$0.0349** | **57.3** | ~$2.00 | ✅ | 1M |
170
173
  | **GLM 5.3** | Z.ai | **~$0.0360** | **31.7** | ~$1.14 | ❌ | 1M |
171
174
  | **GPT-6.1 Sol** | OpenAI | **~$0.0367** | **54.5** | ~$2.00 | ✅ | 1M |
172
175
  | **Claude Sonnet 5.5** | Anthropic | **~$0.0369** | **54.2** | ~$2.00 | ✅ | 1M |
@@ -178,11 +181,12 @@ DeepSeek’s **V4.1-Flash-1017** build (released October 17, 2026) scores **32**
178
181
  | **Claude Opus 5.5** | Anthropic | **~$0.0685** | **58.4** | ~$4.00 | ✅ | 1M |
179
182
  | **MiMo V2.6 Pro UltraSpeed** | Xiaomi | **~$0.1018** | **29.9** | ~$3.05 | ✅ | 1M |
180
183
  | **Claude Fable 5.2** | Anthropic | **~$0.1231** | **65** | ~$8.00 | ✅ | 1M |
184
+ | **GPT-6.2 Astra** | OpenAI | **~$0.1288** | **62.1** | ~$8.00 | ✅ | 1M |
181
185
  | **GPT-6 Astra** | OpenAI | **~$0.1757** | **56.9** | ~$10.00 | ✅ | 1M |
182
186
  | **Claude Fable 5.1** | Anthropic | **~$0.2012** | **49.7** | ~$10.00 | ✅ | 1M |
183
187
 
184
188
  > `MiMo V2.6 Pro UltraSpeed` uses the MiMo V2.6 Pro score (same quality, lower latency).
185
- > Plan access: GPT-6 Sol, GPT-6.1 Sol, Claude Opus 5.5, Claude Fable 5.2, Gemini 4 Argon, and Gemini 4 Carbon need Pro+ or higher; GPT-6 Luna and Claude Sonnet 5.5 are available from Pro; Claude Haiku 5.5 is on every paid plan.
189
+ > Plan access: GPT-6 Sol, GPT-6.1 Sol, GPT-6.2 Sol, GPT-6.2 Astra, Claude Opus 5.5, Claude Fable 5.2, Gemini 4 Argon, and Gemini 4 Carbon need Pro+ or higher; GPT-6 Luna and Claude Sonnet 5.5 are available from Pro; Claude Haiku 5.5 is on every paid plan.
186
190
  > Claude Haiku 5.5 is priced by prompt length; the table shows its sub-100K rates.
187
191
 
188
192
  > 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).
@@ -232,7 +236,7 @@ VS Code's built-in `view_image` tool only accepts **static images** (PNG, JPG, G
232
236
  2. If the provider needs request rewriting, add a proxy under `proxy/`.
233
237
  3. Submit a PR.
234
238
 
235
- The current AA values are **Artificial Analysis Intelligence Index v5.0** composites taken from OpenRouter’s model metadata (re-based from v4.3.2 on October 31, 2026); **every pricing cell comes from first-party provider pricing or GitHub Copilot’s official billing table, never OpenRouter.** 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 snapshot records Gemini 3.8 Flash, Gemini 4 Argon, Gemini 4 Carbon, Grok 4.7, GPT-6 Sol, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Luna, Claude Fable 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 as **Copilot-native** models.
239
+ The current AA values are **Artificial Analysis Intelligence Index v5.0** composites taken from OpenRouter’s model metadata (re-based from v4.3.2 on October 31, 2026); **every pricing cell comes from first-party provider pricing or GitHub Copilot’s official billing table, never OpenRouter.** 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 snapshot records Gemini 3.8 Flash, Gemini 4 Argon, Gemini 4 Carbon, Grok 4.7, GPT-6 Sol, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Luna, GPT-6.2 Sol, GPT-6.2 Astra, Claude Fable 5.2, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 as **Copilot-native** models.
236
240
 
237
241
  - **Chat only.** Inline completions, semantic search, and next-edit suggestions still need a GitHub-hosted model.
238
242
  - Each proxy is tuned for a specific provider family. Don't point the Kimi proxy at an arbitrary OpenAI-compatible endpoint.
@@ -8,7 +8,7 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
8
8
 
9
9
  > **Utility models:** with a GitHub Copilot token, VS Code already uses its built-in utility models, so no extra setup is required. If you use BYOK without Copilot sign-in, set **Chat: Utility Model** and **Chat: Utility Small Model** (or `chat.byokUtilityModelDefault` → _Main Agent Model_). See the [main README](../README.md#4-configure-the-utility-small-model).
10
10
 
11
- > **Note:** The `apiKey` fields are left as empty strings — set them via the **Chat: Manage Language Models** UI (Command Palette → right-click provider group → **Update API Key**). After you set a key via the UI, VS Code replaces the empty string with a `${input:chat.lm.secret.<id>}` secret reference. A key pasted directly into this file is not used: measured on 1.146, the request went out as `Authorization: Bearer` with an empty token and the provider rejected it.
11
+ > **Note:** `apiKey` must be a **non-empty** string — VS Code's schema enforces `minLength: 1`, so `"apiKey": ""` shows _String is shorter than the minimum length of 1_. The snippets below use a `${input:...}` reference, and the reliable way to populate it is the **Chat: Manage Language Models** UI (Command Palette → provider group → **Update API Key**), which stores the key in the OS keychain and rewrites the value to `${input:chat.lm.secret.<id>}`. A key pasted directly into this file as a literal is not used on 1.146: the request goes out as `Authorization: Bearer` with an empty token and the provider rejects it.
12
12
 
13
13
  > **After saving, open the Language Models editor once.** On 1.146 a provider added to this file stays invisible in the model picker until **Chat: Manage Language Models** (or the picker's **Add Models…**) has been opened in that window; the editor itself shows the provider immediately. If your provider's `name` matches an installed extension (for example `GLM` with the Z.ai extension installed), the picker merges them and your models hide behind the extension group — give the provider a distinct name.
14
14
 
@@ -19,12 +19,12 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
19
19
  {
20
20
  "name": "Qwen",
21
21
  "vendor": "customendpoint",
22
- "apiKey": "",
22
+ "apiKey": "${input:qwenApiKey}",
23
23
  "apiType": "chat-completions",
24
24
  "models": [
25
25
  {
26
26
  "id": "qwen3.8-max",
27
- "name": "Qwen 3.8 Max (vision)",
27
+ "name": "Qwen 3.8 Max",
28
28
  "url": "http://127.0.0.1:3458/v1/chat/completions",
29
29
  "toolCalling": true,
30
30
  "vision": true,
@@ -37,12 +37,12 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
37
37
  {
38
38
  "name": "Kimi",
39
39
  "vendor": "customendpoint",
40
- "apiKey": "",
40
+ "apiKey": "${input:kimiApiKey}",
41
41
  "apiType": "chat-completions",
42
42
  "models": [
43
43
  {
44
44
  "id": "kimi-k3.1-pro",
45
- "name": "Kimi K3.1 Pro (vision)",
45
+ "name": "Kimi K3.1 Pro",
46
46
  "url": "http://127.0.0.1:3457/v1/chat/completions",
47
47
  "modelOptions": { "temperature": 1 },
48
48
  "supportsReasoningEffort": ["low", "high", "max"],
@@ -59,7 +59,7 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
59
59
  {
60
60
  "name": "MiMo",
61
61
  "vendor": "customendpoint",
62
- "apiKey": "",
62
+ "apiKey": "${input:mimoApiKey}",
63
63
  "apiType": "chat-completions",
64
64
  "models": [
65
65
  {
@@ -100,12 +100,12 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
100
100
  {
101
101
  "name": "MiniMax",
102
102
  "vendor": "customendpoint",
103
- "apiKey": "",
103
+ "apiKey": "${input:minimaxApiKey}",
104
104
  "apiType": "chat-completions",
105
105
  "models": [
106
106
  {
107
107
  "id": "MiniMax-M3.1-Flash",
108
- "name": "MiniMax M3.1 Flash (vision)",
108
+ "name": "MiniMax M3.1 Flash",
109
109
  "url": "https://api.minimax.io/v1/chat/completions",
110
110
  "toolCalling": true,
111
111
  "vision": true,
@@ -122,12 +122,12 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
122
122
  {
123
123
  "name": "GLM",
124
124
  "vendor": "customendpoint",
125
- "apiKey": "",
125
+ "apiKey": "${input:glmApiKey}",
126
126
  "apiType": "chat-completions",
127
127
  "models": [
128
128
  {
129
129
  "id": "glm-5.3-flash",
130
- "name": "GLM 5.3 Flash (multimodal)",
130
+ "name": "GLM 5.3 Flash",
131
131
  "url": "https://api.z.ai/api/paas/v4/chat/completions",
132
132
  "toolCalling": true,
133
133
  "vision": true,
@@ -154,6 +154,28 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
154
154
  "thinking": true
155
155
  }
156
156
  ]
157
+ },
158
+ {
159
+ "name": "DeepSeek API",
160
+ "vendor": "customendpoint",
161
+ "apiKey": "${input:deepseekApiKey}",
162
+ "apiType": "chat-completions",
163
+ "models": [
164
+ {
165
+ "id": "deepseek-flash",
166
+ "name": "DeepSeek V4.1 Flash",
167
+ "url": "https://api.deepseek.com/v1/chat/completions",
168
+ "toolCalling": true,
169
+ "vision": true,
170
+ "streaming": true,
171
+ "maxInputTokens": 917504,
172
+ "maxOutputTokens": 131072,
173
+ "modelOptions": { "temperature": 1, "top_p": 0.95 },
174
+ "supportsReasoningEffort": ["low", "high", "max"],
175
+ "reasoningEffortFormat": "chat-completions",
176
+ "thinking": true
177
+ }
178
+ ]
157
179
  }
158
180
  ]
159
181
  ```
@@ -169,6 +191,7 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
169
191
  > | `mimo-v2.6-*` | 1,048,576 | 131,072 | 917,504 |
170
192
  > | `MiniMax-M3.1-Flash` | 1,000,000 | 131,072 | 868,928 |
171
193
  > | `glm-5.3`, `glm-5.3-flash` | 1,048,576 | 131,072 | 917,504 |
194
+ > | `deepseek-flash` | 1,048,576 | 131,072 | 917,504 |
172
195
  >
173
196
  > Trade-off: a smaller `maxInputTokens` makes VS Code compact the conversation slightly earlier than the provider's raw input cap (for example 868,928 instead of DashScope's 991,000-token input maximum), which is the safe side of the constraint. Alternatively set `contextWindow` to the provider's window and let VS Code derive `maxInputTokens = contextWindow − maxOutputTokens`. Sources and derivation: [harness research § 4](research/vscode-1.146-copilot-harness.md#4-utility-models-and-context-limits).
174
197
 
@@ -179,5 +202,6 @@ If you only need one provider, jump straight to its setup guide:
179
202
  - [Xiaomi MiMo (V2.6 Pro / Flash / Pro UltraSpeed)](models/mimo.md)
180
203
  - [MiniMax M3.1 Flash](models/minimax.md)
181
204
  - [GLM (5.3 Flash / 5.3 / 5.2 / 5.1)](models/glm.md)
205
+ - [DeepSeek V4.1 Flash](models/deepseek.md)
182
206
 
183
- > **DeepSeek V4.1 Flash 1017** uses the [DeepSeek for Copilot Chat extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot). It appears in `chatLanguageModels.json` as `vendor: "deepseek"` (not as a `customendpoint` provider) and is configured via the extension's settings block.
207
+ > **DeepSeek V4.1 Flash** is also available as the [DeepSeek for Copilot Chat extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot). That route appears in `chatLanguageModels.json` as `vendor: "deepseek"` (not `customendpoint`) and is configured via the extension's settings block; the block above is the plain custom-endpoint route. Name the provider `DeepSeek API` rather than `DeepSeek` when the extension is installed, otherwise the custom endpoint hides behind the extension's picker group.
@@ -1,6 +1,104 @@
1
- # DeepSeek V4.1 Flash for Copilot Chat
2
-
3
- DeepSeek V4.1 Flash is provided by the [DeepSeek for Copilot Chat extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot). It does not use this repository's `chatLanguageModels.json` custom-endpoint configuration.
1
+ # DeepSeek V4.1 Flash — VS Code Custom Endpoint Setup Guide
2
+
3
+ > **TL;DR:** DeepSeek works directly with VS Code's custom-endpoint provider — **no proxy needed**. The API is OpenAI Chat Completions compatible at `https://api.deepseek.com/v1/chat/completions`.
4
+ >
5
+ > **Wire-validated 2026-11-14** against the live DeepSeek API by replaying the exact request shape VS Code 1.146 sends (the field and role union measured from this repo's own captures — `enable_thinking`, `max_completion_tokens`, `max_tokens`, `messages`, `model`, `n`, `reasoning_effort`, `stream`, `stream_options`, `temperature`, `thinking`, `tool_choice`, `tools`, `top_p`; roles `system` / `user` / `assistant` / `tool`). Every one of those shapes returned HTTP 200, including a streamed 128-tool agent loop with `tool_choice: "auto"` and a replayed `reasoning_content` tool follow-up. The picker/UI pass (SecretStorage key, model-picker refresh) was **not** repeated; see [harness research § 9](../../research/vscode-1.146-copilot-harness.md#9-phase-3-live-provider-validation-2026-11-13) for the setup steps that apply to every provider.
6
+ >
7
+ > **Billing:** Pay-as-you-go with peak/off-peak rates (see [pricing](#current-api-pricing)). There is also a [DeepSeek for Copilot Chat extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) route, which is the only way to get reasoning visibility and the `activate_*` tool-list preflight — see [the extension route](#alternative-the-deepseek-copilot-chat-extension).
8
+
9
+ ## At a Glance
10
+
11
+ | Field | Value |
12
+ | ---------------- | ----------------------------------------------------------------------- |
13
+ | Mode | **Direct** (no proxy) |
14
+ | Vision | ✅ Yes on `deepseek-flash`; ❌ on `deepseek-v4-pro` (text-only) |
15
+ | Tool calling | ✅ Yes — `tool_choice` must be `auto` (or omitted) while thinking is on |
16
+ | Context | 1,048,576 |
17
+ | Max output | 393,216 (API cap); the config below declares 131,072 |
18
+ | Supported config | `modelOptions` sampling + `supportsReasoningEffort` + `thinking: true` |
19
+ | Endpoint | `https://api.deepseek.com/v1/chat/completions` |
20
+ | Auth | `Authorization: Bearer $DEEPSEEK_API_KEY` |
21
+
22
+ ### Models
23
+
24
+ | Model | Vision | Context | Max output | Notes |
25
+ | ----------------- | ------ | --------- | ---------- | -------------------------------------------------------------------------------------------------------------------------- |
26
+ | `deepseek-flash` | ✅ | 1,048,576 | 393,216 | Current Flash build (V4.1-Flash-1017) — always-thinking by default, `reasoning_effort` `low`/`high`/`max` (default `high`) |
27
+ | `deepseek-v4-pro` | ❌ | 1,048,576 | 393,216 | Pro tier — **text-only**; accepts the image field but cannot see it, and answers as if no image was sent |
28
+
29
+ > `GET /v1/models` reports `context_window: 1048576`, `max_output_tokens: 393216`, and `effort.supported_levels: ["low","high","max"]` for both models. `deepseek-v4-pro` is not in the default block below; add it in the same shape if you need it.
30
+
31
+ ## Quick Start
32
+
33
+ 1. **Create an API key** at [platform.deepseek.com](https://platform.deepseek.com/api_keys).
34
+ 2. **Edit `chatLanguageModels.json`** — add the DeepSeek block below.
35
+ 3. **Set the API key** via Command Palette → **Chat: Manage Language Models** → **DeepSeek API** → **Update API Key**.
36
+ 4. **Open that editor once** so the provider appears in the picker, then select **DeepSeek V4.1 Flash**.
37
+ 5. **Re-pick the session target** for each new chat if you are on the Local harness.
38
+
39
+ ## Setup
40
+
41
+ ### 1. VS Code configuration
42
+
43
+ | OS | Path |
44
+ | ------- | ----------------------------------------------------------------- |
45
+ | Windows | `%APPDATA%\Code\User\chatLanguageModels.json` |
46
+ | macOS | `~/Library/Application Support/Code/User/chatLanguageModels.json` |
47
+ | Linux | `~/.config/Code/User/chatLanguageModels.json` |
48
+
49
+ ```json
50
+ {
51
+ "name": "DeepSeek API",
52
+ "vendor": "customendpoint",
53
+ "apiKey": "${input:deepseekApiKey}",
54
+ "apiType": "chat-completions",
55
+ "models": [
56
+ {
57
+ "id": "deepseek-flash",
58
+ "name": "DeepSeek V4.1 Flash",
59
+ "url": "https://api.deepseek.com/v1/chat/completions",
60
+ "toolCalling": true,
61
+ "vision": true,
62
+ "streaming": true,
63
+ "maxInputTokens": 917504,
64
+ "maxOutputTokens": 131072,
65
+ "modelOptions": { "temperature": 1, "top_p": 0.95 },
66
+ "supportsReasoningEffort": ["low", "high", "max"],
67
+ "reasoningEffortFormat": "chat-completions",
68
+ "thinking": true
69
+ }
70
+ ]
71
+ }
72
+ ```
73
+
74
+ > **Name the provider something other than `DeepSeek`.** If the DeepSeek Copilot extension is installed, an identical provider name hides your custom endpoint behind that extension's picker group. `DeepSeek API` avoids the collision.
75
+
76
+ > **Context budget:** `917504 + 131072 = 1048576`, the DeepSeek window (input and output combined). Only raise `maxInputTokens` by lowering `maxOutputTokens`.
77
+
78
+ > **`apiKey` must be non-empty** — the file's schema enforces `minLength: 1`, so `"apiKey": ""` shows _String is shorter than the minimum length of 1_. Use the `${input:...}` placeholder shown above and fill it through the UI (below), which rewrites it to a `${input:chat.lm.secret.<id>}` keychain reference.
79
+
80
+ ### 2. API Key
81
+
82
+ 1. Open the Command Palette (`Ctrl+Shift+P`).
83
+ 2. Run **Chat: Manage Language Models**.
84
+ 3. Find the **DeepSeek API** group → **Update API Key**.
85
+ 4. Paste your DeepSeek API key.
86
+
87
+ ## Notes
88
+
89
+ - **Model IDs are `deepseek-flash` and `deepseek-v4-pro` only.** Anything else is rejected with an explicit list: `The supported API model names are deepseek-flash, deepseek-v4-pro, but you passed …`. The human-readable build label `DeepSeek-V4.1-Flash-1017` is **not** a valid model ID.
90
+ - **`tool_choice` must stay `auto` while thinking is on.** `required` and named-tool `tool_choice` both return **HTTP 400 `Thinking mode does not support this tool_choice`**. VS Code sends `auto` (measured in this repo's captures), so the default works; the constraint only bites if you force a tool choice. Disabling thinking (`thinking: {"type":"disabled"}` or `reasoning_effort: "none"`) makes `required` and named tools return 200.
91
+ - **Thinking is on by default and can be turned off.** `GET /v1/models` advertises `low`/`high`/`max`; in practice `reasoning_effort` also accepts `medium`, `minimal`, and `xhigh` (clamped, not advertised), while `none` genuinely disables thinking and returns zero reasoning tokens. `thinking: {"type": "disabled"}` does the same. This differs from Kimi K2.7 (rejects `disabled`) and MiniMax M3.1 Flash (rejects `disabled`).
92
+ - **`reasoning_effort` measurably changes depth.** On a multi-step change-counting task, three runs each produced ≈1,463 reasoning tokens at `low`, ≈1,644 at `high`, and ≈3,253 at `max`. `low` also answered **wrong** (4 instead of 24) while `high`/`max` were correct — prefer `high` or `max` for coding and agent work.
93
+ - **Sampling is flexible but `n` is not.** `temperature` accepted `0`, `1`, and `1.5` with no server-side cap; `top_p` must be in `(0, 1.0]` (`0` and `1.1` both 400); `n` must be exactly `1` (`n: 2` and `n: 0` both 400). VS Code sends `n: 1`, so this only matters for hand-built requests. `presence_penalty` / `frequency_penalty` are accepted.
94
+ - **Output caps:** `max_tokens` valid range is `[1, 393216]`; `max_completion_tokens` is also accepted, and sending both together is fine. On 1.146 `maxOutputTokens` reaches the wire as `max_completion_tokens` only for `thinking: true` entries — which this block is.
95
+ - **Reasoning replay is optional, not required.** A tool-loop follow-up returned 200 both with and without `reasoning_content` on the assistant tool-call message (unlike Kimi K2.7, which rejects some shapes). Replaying it preserves reasoning continuity.
96
+ - **Streaming includes everything VS Code needs:** `reasoning_content` deltas, `tool_calls` deltas, `finish_reason`, and a usage chunk when `stream_options.include_usage` is set.
97
+ - **Vision accepts data URLs only in practice.** A base64 `data:image/png;…` URL was read correctly on `deepseek-flash` ("Red" for a solid red image); a public HTTPS image URL failed with `Failed to download image from …`. `deepseek-v4-pro` accepts the image field but is text-only and answers as if no image was sent.
98
+ - **Only four message roles exist:** `system`, `user`, `assistant`, `tool`. A `developer` role returns **HTTP 422** (`unknown variant 'developer'`). VS Code sends exactly the four supported roles, so this is a constraint for non-VS Code clients, not for the picker path.
99
+ - **Unknown top-level fields are ignored, not rejected** — the API is lenient about extra keys, which is why a dropped `requestBody` never breaks the request.
100
+ - **No proxy is needed for thinking control, including in tool loops.** The [Qwen proxy](../../proxy/qwen-proxy.mjs) exists because DashScope's `enable_thinking` cannot be sent from `chatLanguageModels.json` on 1.146 (`requestBody` is dropped) and thinking must be suppressed once tools appear. DeepSeek has neither problem: it accepts thinking during tool loops (measured 2026-11-14 — a 5-turn read/edit agent loop returned HTTP 200 on every turn with thinking on, and DeepSeek spent 0 reasoning tokens on three of those turns anyway), and the effort level already reaches the wire through `supportsReasoningEffort` + `reasoningEffortFormat: "chat-completions"`. Only _automatic_ per-turn switching would require a proxy, and the measurements show it buys nothing here.
101
+ - **Context caching is automatic** — `usage.prompt_cache_hit_tokens` / `prompt_cache_miss_tokens` and `usage.prompt_tokens_details.cached_tokens` report it.
4
102
 
5
103
  ## Current build
6
104
 
@@ -14,11 +112,15 @@ The [DeepSeek API pricing page](https://api-docs.deepseek.com/quick_start/pricin
14
112
 
15
113
  DeepSeek's [October 17 release note](https://api-docs.deepseek.com/news/news261017) describes 1017 as a Pareto improvement over the September 10 build: stronger benchmarks, faster task completion, and shorter outputs. The model supports both non-thinking and thinking (default) modes, keeps the 1M context window and vision input, and publishes open weights on [Hugging Face](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017) (552B total / 16B active parameters, MIT license).
16
114
 
17
- ## Model ID overrides
115
+ ## Alternative: the DeepSeek Copilot Chat extension
116
+
117
+ DeepSeek V4.1 Flash is also available through the extension-only provider. It appears in `chatLanguageModels.json` as `vendor: "deepseek"` (not `customendpoint`) and is configured through the extension's own settings block. The sections below document that route; [benchmarks](#benchmarks) and [pricing](#current-api-pricing) apply to both routes.
118
+
119
+ ### Model ID overrides
18
120
 
19
121
  The extension's `deepseek-copilot.modelIdOverrides` setting changes the upstream API model ID while keeping the normal DeepSeek entry in the Copilot model picker. The current official DeepSeek Chat Completions API accepts `deepseek-flash`, so map the extension's logical Flash entry to that canonical ID.
20
122
 
21
- > **Warning:** Do **not** use the human-readable version label as a model ID. `DeepSeek-V4.1-Flash-1017` is a version string, not a valid `model` field; use `deepseek-flash`. Sending a version-suffixed ID to `https://api.deepseek.com` can return **HTTP 400 "Invalid request body format"**.
123
+ > **Warning:** Do **not** use the human-readable version label as a model ID. `DeepSeek-V4.1-Flash-1017` is a version string, not a valid `model` field; use `deepseek-flash`. Sending a version-suffixed ID to `https://api.deepseek.com` returns **HTTP 400** — measured 2026-11-14: `The supported API model names are deepseek-flash, deepseek-v4-pro, but you passed DeepSeek-V4.1-Flash-1017.`
22
124
 
23
125
  Only add an override when the configured `deepseek-copilot.baseUrl` expects a different model name (e.g., a third-party proxy). The left-hand key is the extension's logical model key; it is not an arbitrary picker label. The right-hand value is sent verbatim as the provider's `model` field.
24
126
 
@@ -40,7 +142,7 @@ DeepSeek switched to peak/off-peak rates at **16:00 UTC on August 16, 2026**. Pr
40
142
 
41
143
  The 1017 build keeps these rates unchanged. See the [official Models & Pricing page](https://api-docs.deepseek.com/quick_start/pricing) for the live rates and concurrency limits.
42
144
 
43
- ## Tool-list stabilization (`experimental.stabilizeToolList`)
145
+ ## Tool-list stabilization — extension route (`experimental.stabilizeToolList`)
44
146
 
45
147
  `deepseek-copilot.experimental.stabilizeToolList` (default `false`) gates an `activate_*` tool **preflight pass** that runs only on tool-calling (agent-mode / MCP) requests. Verified against extension `0.6.2` source: the flag is read in `out/provider/index.js` and only branches inside `out/provider/tools/flow.js` (`if (!stabilizeToolList) { … return }`).
46
148
 
@@ -52,13 +154,25 @@ Recommendation: leave it `true` if you use **agent mode or MCP tools** with Deep
52
154
 
53
155
  ## Troubleshooting
54
156
 
157
+ ### Custom endpoint
158
+
159
+ 1. **Model missing from the picker** — open **Chat: Manage Language Models** once in the window, then re-check. If the DeepSeek extension is installed, make sure your provider block is not also named `DeepSeek`; rename it (`DeepSeek API`) to escape the extension's picker group.
160
+ 2. **401 / 403** — set the key through **Chat: Manage Language Models → Update API Key**. A literal `apiKey` in `chatLanguageModels.json` is not sent; VS Code sends an empty `Bearer` token.
161
+ 3. **400 listing the supported model names** — you used a version label such as `DeepSeek-V4.1-Flash-1017`. Use `deepseek-flash` or `deepseek-v4-pro`.
162
+ 4. **400 `Thinking mode does not support this tool_choice`** — something is forcing `required` or a named tool. Keep `tool_choice` at `auto`, or disable thinking.
163
+ 5. **`top_p` / `n` rejected** — `top_p` must be in `(0, 1.0]` and `n` must be exactly `1`.
164
+ 6. **Image ignored** — use `deepseek-flash` (not the text-only `deepseek-v4-pro`) and attach a base64 data URL; public image URLs fail with `Failed to download image from …`.
165
+ 7. **422 `unknown variant 'developer'`** — a non-VS Code client sent a `developer` role. Only `system`, `user`, `assistant`, and `tool` are accepted.
166
+
167
+ ### Extension route
168
+
55
169
  1. Confirm the extension is installed and update it if the setting is not recognized. The setting is owned by `Vizards.deepseek-v4-for-copilot`.
56
170
  2. Use the exact setting name and point the Flash entry at `deepseek-flash`:
57
171
  `deepseek-copilot.modelIdOverrides`.
58
172
  3. Reload VS Code after changing the setting (`Developer: Reload Window`).
59
173
  4. Verify the extension's `deepseek-copilot.baseUrl` points at the compatible provider or proxy. An override changes only the model ID; it does not change the endpoint, authentication, request format, or model capabilities.
60
174
  5. For HTTP 400 errors during agent mode or MCP/tool use, enable the extension's tool-list compatibility option:
61
- `deepseek-copilot.experimental.stabilizeToolList: true` (see [Tool-list stabilization](#tool-list-stabilizationexperimentalstabilizetoollist)). This does **not** help plain-chat 400s — those are usually an invalid `model` ID (see the override warning above).
175
+ `deepseek-copilot.experimental.stabilizeToolList: true` (see **Tool-list stabilization — extension route** above). This does **not** help plain-chat 400s — those are usually an invalid `model` ID (see the override warning above).
62
176
  6. Enable the extension's diagnostic mode (`deepseek-copilot.debugMode: "verbose"`) or inspect its request dump to confirm the outbound request's `model` field. The canonical current Flash value should read `"model":"deepseek-flash"`. If a 400 persists with a valid model ID, the remaining cause is request-shape compatibility or authorization — capture the full request body via the dump and compare against the [Chat Completions schema](https://api-docs.deepseek.com/api/create-chat-completion).
63
177
 
64
- The extension's published settings documentation is authoritative for this setting. Its default model-ID map may change between releases, so do not copy an old default blindly.
178
+ The extension's published settings documentation is authoritative for these settings. Its default model-ID map may change between releases, so do not copy an old default blindly.
@@ -63,12 +63,12 @@
63
63
  {
64
64
  "name": "GLM",
65
65
  "vendor": "customendpoint",
66
- "apiKey": "",
66
+ "apiKey": "${input:glmApiKey}",
67
67
  "apiType": "chat-completions",
68
68
  "models": [
69
69
  {
70
70
  "id": "glm-5.3-flash",
71
- "name": "GLM 5.3 Flash (multimodal)",
71
+ "name": "GLM 5.3 Flash",
72
72
  "url": "https://api.z.ai/api/paas/v4/chat/completions",
73
73
  "toolCalling": true,
74
74
  "vision": true,
@@ -100,7 +100,7 @@
100
100
 
101
101
  > **Context budget:** `917504 + 131072 = 1048576`, the GLM 5.x window (input and output combined). VS Code uses that sum as the model's total context, so only raise `maxInputTokens` by lowering `maxOutputTokens`.
102
102
 
103
- > **Leave `apiKey` as `""`** — set it through the Language Models UI so VS Code stores it in the OS keychain (it will replace the empty string with a `${input:chat.lm.secret.<id>}` reference).
103
+ > **`apiKey` must be non-empty** — the file's schema enforces `minLength: 1`, so `"apiKey": ""` shows _String is shorter than the minimum length of 1_. Use the `${input:...}` placeholder shown above and set it through the Language Models UI, which stores it in the OS keychain and rewrites the value to a `${input:chat.lm.secret.<id>}` reference.
104
104
  > If you signed up on `bigmodel.cn` (China), swap the `url` values in the block above to the regional endpoint `https://open.bigmodel.cn/api/paas/v4/chat/completions`.
105
105
 
106
106
  ### 2. API Key
@@ -55,7 +55,7 @@
55
55
  {
56
56
  "name": "Kimi",
57
57
  "vendor": "customendpoint",
58
- "apiKey": "",
58
+ "apiKey": "${input:kimiApiKey}",
59
59
  "apiType": "chat-completions",
60
60
  "models": [
61
61
  {
@@ -89,7 +89,7 @@ Kimi is **Pay-as-You-Go only** — no subscription. A single Open Platform API k
89
89
  3. Find the **Kimi** group → **Update API Key**.
90
90
  4. Paste your Moonshot / Kimi Platform API key.
91
91
 
92
- > VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference. Kimi Platform (formerly Moonshot) rebranded to `platform.kimi.ai` in 2026 — `api.moonshot.ai` still resolves and the proxy targets it unchanged.
92
+ > **`apiKey` must be non-empty** — the file's schema enforces `minLength: 1`, so `"apiKey": ""` shows _String is shorter than the minimum length of 1_. Use the `${input:...}` placeholder shown above and set it through the Language Models UI, which rewrites it to a `${input:chat.lm.secret.<id>}` keychain reference. Kimi Platform (formerly Moonshot) rebranded to `platform.kimi.ai` in 2026 — `api.moonshot.ai` still resolves and the proxy targets it unchanged.
93
93
 
94
94
  ## Local Proxy
95
95
 
@@ -108,7 +108,7 @@ The extension stores your API key in VS Code's `SecretStorage` (OS keychain).
108
108
  {
109
109
  "name": "MiMo",
110
110
  "vendor": "customendpoint",
111
- "apiKey": "",
111
+ "apiKey": "${input:mimoApiKey}",
112
112
  "apiType": "chat-completions",
113
113
  "models": [
114
114
  {
@@ -154,7 +154,7 @@ The extension stores your API key in VS Code's `SecretStorage` (OS keychain).
154
154
  {
155
155
  "name": "MiMo",
156
156
  "vendor": "customendpoint",
157
- "apiKey": "",
157
+ "apiKey": "${input:mimoApiKey}",
158
158
  "apiType": "chat-completions",
159
159
  "models": [
160
160
  {
@@ -201,7 +201,7 @@ The extension stores your API key in VS Code's `SecretStorage` (OS keychain).
201
201
  3. Find the **MiMo** group → **Update API Key**.
202
202
  4. Paste your MiMo API key.
203
203
 
204
- > VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference. The extension uses its own **MiMo: Set API Key** command instead — skip this step if using the extension.
204
+ > **`apiKey` must be non-empty** — the file's schema enforces `minLength: 1`, so `"apiKey": ""` shows _String is shorter than the minimum length of 1_. Use the `${input:...}` placeholder shown above and set it through the Language Models UI, which rewrites it to a `${input:chat.lm.secret.<id>}` keychain reference. The extension uses its own **MiMo: Set API Key** command instead — skip this step if using the extension.
205
205
 
206
206
  ### 2. Token Plan (optional, all methods)
207
207
 
@@ -41,7 +41,7 @@
41
41
  1. **Edit `chatLanguageModels.json`** — add the MiniMax block below.
42
42
  2. **Set your `MINIMAX_API_KEY`** via Command Palette → **Chat: Manage Language Models**.
43
43
  3. **Configure the Utility Small Model** — Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4.1 Flash or MiMo V2.6 Flash). [Why?](../../README.md#4-configure-the-utility-small-model)
44
- 4. **Restart VS Code** and pick "MiniMax M3.1 Flash (vision)" in the chat picker.
44
+ 4. **Restart VS Code** and pick "MiniMax M3.1 Flash" in the chat picker.
45
45
 
46
46
  ## Setup
47
47
 
@@ -66,12 +66,12 @@
66
66
  {
67
67
  "name": "MiniMax",
68
68
  "vendor": "customendpoint",
69
- "apiKey": "",
69
+ "apiKey": "${input:minimaxApiKey}",
70
70
  "apiType": "chat-completions",
71
71
  "models": [
72
72
  {
73
73
  "id": "MiniMax-M3.1-Flash",
74
- "name": "MiniMax M3.1 Flash (vision)",
74
+ "name": "MiniMax M3.1 Flash",
75
75
  "url": "https://api.minimax.io/v1/chat/completions",
76
76
  "toolCalling": true,
77
77
  "vision": true,
@@ -113,7 +113,7 @@ The two keys are **not interchangeable** — a Subscription Key against a PAYG-o
113
113
  3. Find the **MiniMax** group → **Update API Key**.
114
114
  4. Paste your **Open Platform API Key** from `platform.minimax.io/user-center/basic-information/interface-key`.
115
115
 
116
- > VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference.
116
+ > **`apiKey` must be non-empty** — the file's schema enforces `minLength: 1`, so `"apiKey": ""` shows _String is shorter than the minimum length of 1_. Use the `${input:...}` placeholder shown above and set it through the Language Models UI, which rewrites it to a `${input:chat.lm.secret.<id>}` keychain reference.
117
117
 
118
118
  #### Option B — Token Plan Subscription Key
119
119
 
@@ -1,6 +1,6 @@
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. 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)).
3
+ > **TL;DR:** `qwen3.8-max` works both direct and via the local proxy. 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
 
@@ -80,12 +80,12 @@ API keys are bound to their region (and, on a workspace-dedicated domain, to the
80
80
  {
81
81
  "name": "Qwen",
82
82
  "vendor": "customendpoint",
83
- "apiKey": "",
83
+ "apiKey": "${input:qwenApiKey}",
84
84
  "apiType": "chat-completions",
85
85
  "models": [
86
86
  {
87
87
  "id": "qwen3.8-max",
88
- "name": "Qwen 3.8 Max (vision)",
88
+ "name": "Qwen 3.8 Max",
89
89
  "url": "https://<your-workspace-id>.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1/chat/completions",
90
90
  "toolCalling": true,
91
91
  "vision": true,
@@ -122,12 +122,12 @@ API keys are bound to their region (and, on a workspace-dedicated domain, to the
122
122
  {
123
123
  "name": "Qwen",
124
124
  "vendor": "customendpoint",
125
- "apiKey": "",
125
+ "apiKey": "${input:qwenApiKey}",
126
126
  "apiType": "chat-completions",
127
127
  "models": [
128
128
  {
129
129
  "id": "qwen3.8-max",
130
- "name": "Qwen 3.8 Max (vision)",
130
+ "name": "Qwen 3.8 Max",
131
131
  "url": "http://127.0.0.1:3458/v1/chat/completions",
132
132
  "toolCalling": true,
133
133
  "vision": true,
@@ -150,7 +150,7 @@ DashScope is **Pay-as-You-Go only** — but new Model Studio users get **1M inpu
150
150
  3. Find the **Qwen** group → **Update API Key**.
151
151
  4. Paste your DashScope API key.
152
152
 
153
- > VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference. Keys are region-specific.
153
+ > **`apiKey` must be non-empty** — the file's schema enforces `minLength: 1`, so `"apiKey": ""` shows _String is shorter than the minimum length of 1_. Use the `${input:...}` placeholder shown above and set it through the Language Models UI, which rewrites it to a `${input:chat.lm.secret.<id>}` keychain reference. Keys are region-specific.
154
154
  >
155
155
  > 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.
156
156
 
package/docs/pricing.md CHANGED
@@ -36,6 +36,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
36
36
  | **Gemini 4 Hydrogen** | Google | **~$0.0278** | **54** | $1.50 | $0.075 | $7.50 | ~$1.50 | 1M |
37
37
  | **Muse Spark 1.3** | Meta | **~$0.0288** | **36.4** | $1.25 | $0.15 | $4.25 | ~$1.05 | 1M |
38
38
  | **Gemini 4 Carbon** | Google | **~$0.0333** | **60** | $2.00 | $0.10 | $10.00 | ~$2.00 | 1M |
39
+ | **GPT-6.2 Sol** | OpenAI | **~$0.0349** | **57.3** | $2.00 | $0.10 | $10.00 | ~$2.00 | 1M |
39
40
  | **GLM 5.3** | Z.ai | **~$0.0360** | **31.7** | $1.40 | $0.26 | $4.40 | ~$1.14 | 1M |
40
41
  | **GPT-6.1 Sol** | OpenAI | **~$0.0367** | **54.5** | $2.00 | $0.10 | $10.00 | ~$2.00 | 1M |
41
42
  | **Claude Sonnet 5.5** | Anthropic | **~$0.0369** | **54.2** | $2.00 | $0.10 | $10.00 | ~$2.00 | 1M |
@@ -47,6 +48,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
47
48
  | **Claude Opus 5.5** | Anthropic | **~$0.0685** | **58.4** | $4.00 | $0.20 | $20.00 | ~$4.00 | 1M |
48
49
  | **MiMo V2.6 Pro UltraSpeed** | Xiaomi | **~$0.1018** | **29.9** | $4.35 | $0.036 | $8.70 | ~$3.05 | 1M |
49
50
  | **Claude Fable 5.2** | Anthropic | **~$0.1231** | **65** | $8.00 | $0.20 | $40.00 | ~$8.00 | 1M |
51
+ | **GPT-6.2 Astra** | OpenAI | **~$0.1288** | **62.1** | $8.00 | $0.40 | $40.00 | ~$8.00 | 1M |
50
52
  | **GPT-6 Astra** | OpenAI | **~$0.1757** | **56.9** | $10.00 | $1.00 | $50.00 | ~$10.00 | 1M |
51
53
  | **Claude Fable 5.1** | Anthropic | **~$0.2012** | **49.7** | $10.00 | $0.25 | $50.00 | ~$10.00 | 1M |
52
54
 
@@ -57,7 +59,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
57
59
  > - **DeepSeek:** the table shows peak cache-miss pricing; off-peak rates are half. See the [DeepSeek pricing page](https://api-docs.deepseek.com/quick_start/pricing).
58
60
  > - **MiMo:** the table shows cache-miss pricing; cache hits are far cheaper (see the Cached input column). A Token Plan subscription with discounted rates is also available.
59
61
  > - **Anthropic:** cache reads and writes are billed separately. Haiku 5.5 is the only Claude model with prompt-length tiering; the table shows its ≤100K rates. Fast mode is $8 / $40 per 1M.
60
- > - **OpenAI:** GPT-6 Sol, GPT-6.1 Sol, and Luna bill cache writes at 1.25× input. Requests over 272K input cost 2× input and cache rates, with 1.5× output.
62
+ > - **OpenAI:** GPT-6 Sol, GPT-6.1 Sol, and Luna bill cache writes at 1.25× input. Requests over 272K input cost 2× input and cache rates, with 1.5× output. GPT-6.2 Astra is $8 / $0.40 cache read / $40 per 1M (20% below GPT-6 Astra, 60% off cached input); GPT-6.2 Sol carries GPT-6.1 Sol's $2 / $0.10 / $10 rates.
61
63
  > - **Gemini 4 Argon and Gemini 4 Carbon:** both bill $2 / $10 per 1M with $0.10 implicit cache through November 30, 2026, then rise to $4 / $20 with $0.20 cache; explicit caching is unsupported. Output includes thinking tokens. Batch and Flex are half price; Priority is $3.60 / $18. Carbon is the more deliberate of the two and spends more tokens per task, so its session cost runs higher than Argon's at identical rates.
62
64
  > - **Gemini 4 Hydrogen:** flat $1.50 / $7.50 per 1M with $0.075 implicit cache across the entire 1M window; explicit caching is unsupported. Batch and Flex are half price ($0.75 / $3.75), Priority is $2.70 / $13.50, and a free tier is available in AI Studio. Hydrogen always thinks (`low` / `medium` / `high` / `xhigh`), so token spend — and this modeled session cost — rises with the thinking level; its **54** Intelligence Score is Artificial Analysis' `xhigh` measurement, while Google reports **51** at the default `high` level. It is API-only and not Copilot-native as of November 13, 2026.
63
65
  > - **Kimi K3.1 Pro and MiniMax M3.1 Flash:** both always think, so control cost with `reasoning_effort`. See [docs/models/kimi.md](models/kimi.md) and [docs/models/minimax.md](models/minimax.md).
@@ -68,10 +70,12 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
68
70
 
69
71
  > **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.
70
72
 
71
- > Prices last verified: November 13, 2026. Always check the official pages for the latest rates:
73
+ > Prices last verified: November 18, 2026. Always check the official pages for the latest rates:
72
74
  >
73
75
  > - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
74
76
  > - [OpenAI pricing](https://openai.com/api/pricing/)
77
+ > - [OpenAI GPT-6.2 Astra and Sol announcement](https://openai.com/index/introducing-gpt-6-2-astra-sol/)
78
+ > - [GitHub Copilot GPT-6.2 Astra and Sol release](https://github.blog/changelog/2026-11-17-openais-gpt-6-2-astra-and-gpt-6-2-sol-now-available/)
75
79
  > - [OpenAI GPT-6 Sol and Luna announcement](https://openai.com/index/introducing-gpt-6-sol-and-luna/)
76
80
  > - [OpenAI GPT-6 Sol API details](https://developers.openai.com/api/docs/models/gpt-6-sol)
77
81
  > - [OpenAI GPT-6 Luna API details](https://developers.openai.com/api/docs/models/gpt-6-luna)
@@ -95,7 +99,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
95
99
  > - [GitHub Copilot GPT-6.1 Sol release](https://github.blog/changelog/2026-09-29-gpt-6-1-sol-in-github-copilot)
96
100
  > - [GitHub Copilot Claude Opus 5.5 release](https://github.blog/changelog/2026-09-22-claude-opus-5-5-is-now-available-in-github-copilot)
97
101
  > - [GitHub Copilot supported models](https://docs.github.com/en/copilot/reference/ai-models/supported-models)
98
- > - [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), [GPT-6.1 Terra](https://artificialanalysis.ai/models/gpt-6-1-terra), [Claude Opus 5.5](https://artificialanalysis.ai/models/claude-opus-5-5), [Claude Sonnet 5.5](https://artificialanalysis.ai/models/claude-sonnet-5-5), [Claude Haiku 5.5](https://artificialanalysis.ai/models/claude-haiku-5-5), [MiMo-V2.6-Flash](https://artificialanalysis.ai/models/mimo-v2-6-flash), [Gemini 4 Argon](https://artificialanalysis.ai/models/gemini-4-argon), [Muse Spark 1.3](https://artificialanalysis.ai/models/muse-spark-1-3), [Kimi K3.1 Pro](https://artificialanalysis.ai/models/kimi-k3-1-pro), and [MiniMax-M3.1-Flash](https://artificialanalysis.ai/models/minimax-m3-1-flash)
102
+ > - [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), [GPT-6.1 Terra](https://artificialanalysis.ai/models/gpt-6-1-terra), [GPT-6.2 Astra](https://artificialanalysis.ai/models/gpt-6-2-astra), [GPT-6.2 Sol](https://artificialanalysis.ai/models/gpt-6-2-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), [Claude Haiku 5.5](https://artificialanalysis.ai/models/claude-haiku-5-5), [MiMo-V2.6-Flash](https://artificialanalysis.ai/models/mimo-v2-6-flash), [Gemini 4 Argon](https://artificialanalysis.ai/models/gemini-4-argon), [Muse Spark 1.3](https://artificialanalysis.ai/models/muse-spark-1-3), [Kimi K3.1 Pro](https://artificialanalysis.ai/models/kimi-k3-1-pro), and [MiniMax-M3.1-Flash](https://artificialanalysis.ai/models/minimax-m3-1-flash)
99
103
  > - [Google Gemini pricing](https://ai.google.dev/pricing)
100
104
  > - [Google Gemini 4 Carbon announcement](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/)
101
105
  > - [Google Gemini 4 Carbon availability](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-carbon-now-available/)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "copilot-custom-endpoint",
3
- "version": "4.0.0",
3
+ "version": "4.1.1",
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
+ }