copilot-custom-endpoint 2.0.0 → 2.1.1
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 +46 -42
- package/docs/example-config.md +17 -3
- package/docs/models/deepseek.md +45 -0
- package/docs/models/qwen.md +33 -9
- package/docs/pricing.md +33 -30
- package/package.json +1 -1
- package/proxy/qwen-proxy.mjs +1 -1
package/README.md
CHANGED
|
@@ -20,17 +20,18 @@ 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
|
|
24
|
-
|
|
|
25
|
-
| **Kimi K3 / K2.7 Code / K2.6**
|
|
26
|
-
| **MiMo V2.5**
|
|
27
|
-
| **MiMo V2.5 Pro**
|
|
28
|
-
| **Qwen 3.7 Plus**
|
|
29
|
-
| **Qwen 3.7 Max**
|
|
30
|
-
| **
|
|
31
|
-
| **
|
|
32
|
-
| **GLM
|
|
33
|
-
| **
|
|
23
|
+
| Model | Provider | Needs proxy? | Vision | Setup guide |
|
|
24
|
+
| -------------------------------- | --------- | ---------------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
25
|
+
| **Kimi K3 / K2.7 Code / K2.6** | Moonshot | **Yes** | ✅ | [Manual setup](docs/models/kimi.md) |
|
|
26
|
+
| **MiMo V2.5** | Xiaomi | Optional (recommended) | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) ★ / [Manual setup](docs/models/mimo.md) |
|
|
27
|
+
| **MiMo V2.5 Pro** | Xiaomi | Optional (recommended) | ❌ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) ★ / [Manual setup](docs/models/mimo.md) |
|
|
28
|
+
| **Qwen 3.7 Plus** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
|
|
29
|
+
| **Qwen 3.7 Max** | DashScope | Optional (recommended) | ❌ | [Manual setup](docs/models/qwen.md) |
|
|
30
|
+
| **Qwen 3.8 Max** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
|
|
31
|
+
| **MiniMax M3** | MiniMax | No | ✅ | [Extension](https://github.com/tugudush/minimax-copilot) ★ / [Manual setup](docs/models/minimax.md) |
|
|
32
|
+
| **GLM 5.2 / 5.1** | Z.ai | No | ✅ via extension proxy | [Manual setup](docs/models/glm.md) |
|
|
33
|
+
| **GLM 5V Turbo** | Z.ai | No | ✅ | [Manual setup](docs/models/glm.md) |
|
|
34
|
+
| **DeepSeek V4 Pro / Flash 0731** | DeepSeek | No (uses an extension) | ❌ (0731) | [Extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) / [setup notes](docs/models/deepseek.md) |
|
|
34
35
|
|
|
35
36
|
## Setup
|
|
36
37
|
|
|
@@ -106,36 +107,37 @@ npx copilot-custom-endpoint clean # Remove debug_log/
|
|
|
106
107
|
|
|
107
108
|
All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To convert to AI credits, multiply by 100 (e.g., $5.00/1M = 500 credits/1M). Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
|
|
108
109
|
|
|
109
|
-
| Model
|
|
110
|
-
|
|
|
111
|
-
| **DeepSeek V4 Flash**
|
|
112
|
-
| **MiMo V2.5**
|
|
113
|
-
| **GPT-5.6 Luna**
|
|
114
|
-
| **MiniMax M3**
|
|
115
|
-
| **DeepSeek V4 Pro**
|
|
116
|
-
| **MiMo V2.5 Pro**
|
|
117
|
-
| **Qwen 3.7 Plus**
|
|
118
|
-
| **MiniMax M3 Priority**⁴
|
|
119
|
-
| **Kimi K2.6**
|
|
120
|
-
| **Kimi K2.7 Code**
|
|
121
|
-
| **GPT-5.4 mini**
|
|
122
|
-
| **GLM 5.2**
|
|
123
|
-
| **GLM 5.1**
|
|
124
|
-
| **GLM 5V Turbo**
|
|
125
|
-
| **Gemini 3.6 Flash** ⁸
|
|
126
|
-
| **
|
|
127
|
-
| **
|
|
128
|
-
| **
|
|
129
|
-
| **
|
|
130
|
-
| **
|
|
131
|
-
| **
|
|
132
|
-
| **
|
|
133
|
-
| **Claude Sonnet
|
|
134
|
-
| **Claude
|
|
135
|
-
| **Claude Opus
|
|
136
|
-
| **Claude Opus 4.
|
|
137
|
-
| **
|
|
138
|
-
| **GPT-5.
|
|
110
|
+
| Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
|
|
111
|
+
| -------------------------- | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
|
|
112
|
+
| **DeepSeek V4 Flash 0731** | DeepSeek | **~$0.0020** | **49.9** | ~$0.10 | ❌ | 1M |
|
|
113
|
+
| **MiMo V2.5** | Xiaomi | **~$0.0025** | **40** ³ | ~$0.10 | ✅ | 1M |
|
|
114
|
+
| **GPT-5.6 Luna** | OpenAI | **~$0.0043** | **51.2** | ~$0.22 | ✅ | 1M |
|
|
115
|
+
| **MiniMax M3** | MiniMax | **~$0.0061** | **44.4** | ~$0.27 | ✅ | 1M |
|
|
116
|
+
| **DeepSeek V4 Pro** | DeepSeek | **~$0.0068** | **44.3** | ~$0.30 | ✅ | 1M |
|
|
117
|
+
| **MiMo V2.5 Pro** | Xiaomi | **~$0.0072** | **42.2** | ~$0.30 | ❌ | 1M |
|
|
118
|
+
| **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | ~$0.36 | ✅ | 1M |
|
|
119
|
+
| **MiniMax M3 Priority**⁴ | MiniMax | **~$0.0092** | **44.4** | ~$0.41 | ✅ | 1M |
|
|
120
|
+
| **Kimi K2.6** | Moonshot | **~$0.021** | **42.8** | ~$0.88 | ✅ | 262K |
|
|
121
|
+
| **Kimi K2.7 Code** | Moonshot | **~$0.021** | **42.0** | ~$0.88 | ✅ | 262K |
|
|
122
|
+
| **GPT-5.4 mini** | OpenAI | **~$0.021** | **40.0** | ~$0.83 | ❌ | 400K |
|
|
123
|
+
| **GLM 5.2** | Z.ai | **~$0.022** | **51.0** | ~$1.14 | ❌ | 1M |
|
|
124
|
+
| **GLM 5.1** | Z.ai | **~$0.028** | **40.2** | ~$1.14 | ❌ | 200K |
|
|
125
|
+
| **GLM 5V Turbo** | Z.ai | **~$0.029** | **34.0** ³ | ~$1.00 | ✅ | 200K |
|
|
126
|
+
| **Gemini 3.6 Flash** ⁸ | Google | **~$0.030** | **50.0** | ~$1.50 | ✅ | 1M |
|
|
127
|
+
| **Qwen 3.8 Max** ¹⁰ | DashScope | **~$0.030** | **53.4** | ~$1.60 | ✅ | 1M |
|
|
128
|
+
| **Gemini 3.5 Flash** | Google | **~$0.033** | **50.2** | ~$1.65 | ✅ | 1M |
|
|
129
|
+
| **GPT-5.6 Terra** | OpenAI | **~$0.040** | **55.0** | ~$2.20 | ✅ | 1M |
|
|
130
|
+
| **Qwen 3.7 Max** | DashScope | **~$0.043** | **46.0** | ~$2.00 | ❌ | 1M |
|
|
131
|
+
| **Gemini 3.1 Pro** | Google | **~$0.047** | **46.5** | ~$2.20 | ✅ | 1M |
|
|
132
|
+
| **Kimi K3** ⁶ | Moonshot | **~$0.053** | **57.0** | ~$3.00 | ✅ | 1M |
|
|
133
|
+
| **GPT-5.4** | OpenAI | **~$0.054** | **51.4** | ~$2.75 | ✅ | 1M |
|
|
134
|
+
| **Claude Sonnet 5** ⁵ | Anthropic | **~$0.057** | **53.0** | ~$3.00 | ✅ | 1M |
|
|
135
|
+
| **Claude Sonnet 4.6** | Anthropic | **~$0.064** | **47.2** | ~$3.00 | ✅ | 1M |
|
|
136
|
+
| **Claude Opus 5** ⁹ | Anthropic | **~$0.082** | **61.0** | ~$5.00 | ✅ | 1M |
|
|
137
|
+
| **Claude Opus 4.8** | Anthropic | **~$0.090** | **55.7** | ~$5.00 | ✅ | 1M |
|
|
138
|
+
| **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | ~$5.00 | ✅ | 1M |
|
|
139
|
+
| **GPT-5.6 Sol** | OpenAI | **~$0.093** | **58.9** | ~$5.50 | ✅ | 1M |
|
|
140
|
+
| **GPT-5.5** | OpenAI | **~$0.10** | **54.8** | ~$5.50 | ✅ | 1M |
|
|
139
141
|
|
|
140
142
|
¹ Gemini 3.1 Pro pricing applies to prompts ≤200K tokens.
|
|
141
143
|
|
|
@@ -153,6 +155,8 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
|
|
|
153
155
|
|
|
154
156
|
⁹ **Claude Opus 5** launched July 24, 2026. AA Intelligence Index score of **61.0** (#1 overall) confirmed by [Artificial Analysis](https://artificialanalysis.ai/models/claude-opus-5). Priced at $5.00 / $25.00 per MTok input/output (same as Opus 4.8). 1M context, text + image input, adaptive reasoning. Also available in Fast mode ($10/$50 per MTok input/output). Uses the newer Claude tokenizer (~30% more tokens than pre-4.7 models). See [Anthropic's Opus 5 announcement](https://www.anthropic.com/news/claude-opus-5).
|
|
155
157
|
|
|
158
|
+
¹⁰ **Qwen 3.8 Max** (`qwen3.8-max`) has an OpenRouter-reported Artificial Analysis Intelligence Index of **53.4** (Coding **68.9**, Agentic **44.9**). Arena snapshots place it **#5 in Text**, **#2 in Vision**, and **#4 in Code/WebDev**; it is not listed in Agent Arena. See [OpenRouter](https://openrouter.ai/qwen/qwen3.8-max) and [Arena](https://arena.ai/leaderboard).
|
|
159
|
+
|
|
156
160
|
For footnotes, sources, and detailed notes (cache behavior, tiered pricing, free quotas) see [docs/pricing.md](docs/pricing.md). For a copy-paste config containing **all providers at once**, see [docs/example-config.md](docs/example-config.md).
|
|
157
161
|
|
|
158
162
|
> **👤 Personal picks** —
|
|
@@ -173,7 +177,7 @@ For footnotes, sources, and detailed notes (cache behavior, tiered pricing, free
|
|
|
173
177
|
>
|
|
174
178
|
> Cheaper alternatives for simpler tasks:
|
|
175
179
|
>
|
|
176
|
-
> - **DeepSeek V4 Flash** — ~$0.10/session,
|
|
180
|
+
> - **DeepSeek V4 Flash 0731** — ~$0.10/session, 49.9 score (solid fallback)
|
|
177
181
|
> - **MiMo V2.5** — ~$0.10/session, 40 score (solid fallback, vision-capable)
|
|
178
182
|
|
|
179
183
|
## Companion tools
|
package/docs/example-config.md
CHANGED
|
@@ -16,13 +16,25 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
|
|
|
16
16
|
"apiKey": "",
|
|
17
17
|
"apiType": "chat-completions",
|
|
18
18
|
"models": [
|
|
19
|
+
{
|
|
20
|
+
"id": "qwen3.8-max",
|
|
21
|
+
"name": "Qwen 3.8 Max (vision)",
|
|
22
|
+
"url": "http://127.0.0.1:3458/v1/chat/completions",
|
|
23
|
+
"toolCalling": true,
|
|
24
|
+
"vision": true,
|
|
25
|
+
"streaming": true,
|
|
26
|
+
"maxInputTokens": 991000,
|
|
27
|
+
"maxOutputTokens": 131072
|
|
28
|
+
},
|
|
19
29
|
{
|
|
20
30
|
"id": "qwen3.7-max",
|
|
21
31
|
"name": "Qwen 3.7 Max (text)",
|
|
22
32
|
"url": "http://127.0.0.1:3458/v1/chat/completions",
|
|
23
33
|
"toolCalling": true,
|
|
24
34
|
"vision": false,
|
|
25
|
-
"streaming": true
|
|
35
|
+
"streaming": true,
|
|
36
|
+
"maxInputTokens": 1048576,
|
|
37
|
+
"maxOutputTokens": 131072
|
|
26
38
|
},
|
|
27
39
|
{
|
|
28
40
|
"id": "qwen3.7-plus",
|
|
@@ -30,7 +42,9 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
|
|
|
30
42
|
"url": "http://127.0.0.1:3458/v1/chat/completions",
|
|
31
43
|
"toolCalling": true,
|
|
32
44
|
"vision": true,
|
|
33
|
-
"streaming": true
|
|
45
|
+
"streaming": true,
|
|
46
|
+
"maxInputTokens": 1048576,
|
|
47
|
+
"maxOutputTokens": 131072
|
|
34
48
|
}
|
|
35
49
|
]
|
|
36
50
|
},
|
|
@@ -127,7 +141,7 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
|
|
|
127
141
|
"models": [
|
|
128
142
|
{
|
|
129
143
|
"id": "MiniMax-M3",
|
|
130
|
-
"name": "MiniMax M3 (
|
|
144
|
+
"name": "MiniMax M3 (vision)",
|
|
131
145
|
"url": "https://api.minimax.io/v1/chat/completions",
|
|
132
146
|
"toolCalling": true,
|
|
133
147
|
"vision": true,
|
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
# DeepSeek V4 for Copilot Chat
|
|
2
|
+
|
|
3
|
+
DeepSeek V4 Pro and Flash are provided by the [DeepSeek V4 for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) extension. They do not use this repository's `chatLanguageModels.json` custom-endpoint configuration.
|
|
4
|
+
|
|
5
|
+
## Model ID overrides
|
|
6
|
+
|
|
7
|
+
The extension's `deepseek-copilot.modelIdOverrides` setting changes the upstream API model IDs while keeping the normal DeepSeek entries in the Copilot model picker. The official DeepSeek Chat Completions API only accepts two `model` values — `deepseek-v4-flash` and `deepseek-v4-pro` — so the correct map for the official endpoint is just the defaults:
|
|
8
|
+
|
|
9
|
+
```jsonc
|
|
10
|
+
{
|
|
11
|
+
"deepseek-copilot.modelIdOverrides": {
|
|
12
|
+
"deepseek-v4-flash": "deepseek-v4-flash",
|
|
13
|
+
"deepseek-v4-pro": "deepseek-v4-pro"
|
|
14
|
+
}
|
|
15
|
+
}
|
|
16
|
+
```
|
|
17
|
+
|
|
18
|
+
> **Warning:** Do **not** use the human-readable version label as a model ID. `DeepSeek-V4-Flash-0731` is only the version string shown on the pricing page, not a valid `model` field. Sending `deepseek-v4-flash-0731` to the official `https://api.deepseek.com` endpoint returns **HTTP 400 "Invalid request body format"**. The official endpoint already serves the latest (0731) build under the plain `deepseek-v4-flash` ID, so no override is needed there.
|
|
19
|
+
|
|
20
|
+
Only add an override when the configured `deepseek-copilot.baseUrl` expects a different model name (e.g., a third-party proxy). The left-hand keys are the extension's logical model keys; they are not arbitrary picker labels. The right-hand values are sent verbatim as the provider's `model` field.
|
|
21
|
+
|
|
22
|
+
For Flash, select **DeepSeek V4 Flash** in Copilot Chat after reloading the window. The picker may still display “DeepSeek V4 Flash”; that is expected. The override is not a model registration or a way to add a new picker entry.
|
|
23
|
+
|
|
24
|
+
## Tool-list stabilization (`experimental.stabilizeToolList`)
|
|
25
|
+
|
|
26
|
+
`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 }`).
|
|
27
|
+
|
|
28
|
+
- **When on**, the extension runs a tool-list stabilization / `activate_*` preflight that keeps the offered tool schema set stable across turns. This targets **HTTP 400 errors during agent/tool loops**, where a changing tool list confuses the model.
|
|
29
|
+
- **When off**, the preflight pass is skipped entirely.
|
|
30
|
+
- **Plain chat (no tools) never triggers the flag** — it is inert and has no effect (and no cost) on non-tool requests. It neither causes nor fixes plain-chat 400s such as the invalid model-ID case above.
|
|
31
|
+
|
|
32
|
+
Recommendation: leave it `true` if you use **agent mode or MCP tools** with DeepSeek V4; it is harmless to keep for plain-chat-only use, and safe to remove if you never invoke tools.
|
|
33
|
+
|
|
34
|
+
## Troubleshooting
|
|
35
|
+
|
|
36
|
+
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`.
|
|
37
|
+
2. Use the exact setting name and logical key:
|
|
38
|
+
`deepseek-copilot.modelIdOverrides` → `deepseek-v4-flash`.
|
|
39
|
+
3. Reload VS Code after changing the setting (`Developer: Reload Window`).
|
|
40
|
+
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.
|
|
41
|
+
5. For HTTP 400 errors during agent mode or MCP/tool use, enable the extension's tool-list compatibility option:
|
|
42
|
+
`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).
|
|
43
|
+
6. Enable the extension's diagnostic mode (`deepseek-copilot.debugMode: "verbose"`) or inspect its request dump to confirm the outbound request's `model` field. If the override is removed, it should read `"model":"deepseek-v4-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).
|
|
44
|
+
|
|
45
|
+
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.
|
package/docs/models/qwen.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Qwen (DashScope) — VS Code Custom Endpoint Setup Guide
|
|
2
2
|
|
|
3
|
-
> **TL;DR:** `qwen3.7-plus` (vision) and `qwen3.7-max` (text) work both direct and via the local proxy. 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), `qwen3.7-plus` (vision), and `qwen3.7-max` (text) work both direct and via the local proxy. 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.
|
|
4
4
|
|
|
5
5
|
## At a Glance
|
|
6
6
|
|
|
@@ -8,10 +8,10 @@
|
|
|
8
8
|
| ---------------------- | -------------------------------------------------------------------------------- |
|
|
9
9
|
| Mode | **Proxy** (local on `:3458`) **or** **Direct** (static `enable_thinking: false`) |
|
|
10
10
|
| Billing | **Pay-as-You-Go only** — 1M-token free quota for new users |
|
|
11
|
-
| Vision | ✅ Yes (`qwen3.7-plus`)
|
|
11
|
+
| Vision | ✅ Yes (`qwen3.8-max`, `qwen3.7-plus`) |
|
|
12
12
|
| Tool calling | ✅ Yes |
|
|
13
13
|
| Context | 1M |
|
|
14
|
-
| Max output |
|
|
14
|
+
| Max output | 131K (`qwen3.8-max`); see Models table for other models |
|
|
15
15
|
| Endpoint | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions` |
|
|
16
16
|
| Proxy endpoint | `http://127.0.0.1:3458/v1/chat/completions` |
|
|
17
17
|
| Auth | `Authorization: Bearer $DASHSCOPE_API_KEY` |
|
|
@@ -20,10 +20,11 @@
|
|
|
20
20
|
|
|
21
21
|
### Models
|
|
22
22
|
|
|
23
|
-
| Model | Vision | Context | Max output | Notes
|
|
24
|
-
| -------------- | ------ | ------- | --------------- |
|
|
25
|
-
| `qwen3.
|
|
26
|
-
| `qwen3.7-
|
|
23
|
+
| Model | Vision | Context | Max output | Notes |
|
|
24
|
+
| -------------- | ------ | ------- | --------------- | ------------------------------------------------------- |
|
|
25
|
+
| `qwen3.8-max` | ✅ Yes | 1M | 131K | Frontier multimodal model; reasoning enabled by default |
|
|
26
|
+
| `qwen3.7-plus` | ✅ Yes | 1M | _(unspecified)_ | Primary model with image understanding |
|
|
27
|
+
| `qwen3.7-max` | ❌ No | 1M | _(unspecified)_ | Larger text-only model |
|
|
27
28
|
|
|
28
29
|
> The live `chatLanguageModels.json` points Qwen at the local proxy by default; the direct DashScope URL is shown below for users who prefer a static `enable_thinking: false` setup.
|
|
29
30
|
|
|
@@ -42,7 +43,7 @@
|
|
|
42
43
|
1. **Use the direct-path JSON snippet** below.
|
|
43
44
|
2. **Set your `DASHSCOPE_API_KEY`** via Command Palette → **Chat: Manage Language Models**.
|
|
44
45
|
3. **Configure the Utility Small Model** — Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4 Flash or MiMo V2.5). [Why?](../../README.md#4-configure-the-utility-small-model)
|
|
45
|
-
4. **Restart VS Code** and pick "Qwen 3.7 Plus" or "Qwen 3.7 Max".
|
|
46
|
+
4. **Restart VS Code** and pick "Qwen 3.8 Max", "Qwen 3.7 Plus", or "Qwen 3.7 Max".
|
|
46
47
|
|
|
47
48
|
## Setup
|
|
48
49
|
|
|
@@ -73,6 +74,17 @@ DashScope is region-specific — your API key only works on the endpoint it was
|
|
|
73
74
|
"apiKey": "",
|
|
74
75
|
"apiType": "chat-completions",
|
|
75
76
|
"models": [
|
|
77
|
+
{
|
|
78
|
+
"id": "qwen3.8-max",
|
|
79
|
+
"name": "Qwen 3.8 Max (vision)",
|
|
80
|
+
"url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions",
|
|
81
|
+
"toolCalling": true,
|
|
82
|
+
"vision": true,
|
|
83
|
+
"streaming": true,
|
|
84
|
+
"maxInputTokens": 991000,
|
|
85
|
+
"maxOutputTokens": 131072,
|
|
86
|
+
"requestBody": { "enable_thinking": false }
|
|
87
|
+
},
|
|
76
88
|
{
|
|
77
89
|
"id": "qwen3.7-max",
|
|
78
90
|
"name": "Qwen 3.7 Max (text)",
|
|
@@ -120,6 +132,16 @@ DashScope is region-specific — your API key only works on the endpoint it was
|
|
|
120
132
|
"apiKey": "",
|
|
121
133
|
"apiType": "chat-completions",
|
|
122
134
|
"models": [
|
|
135
|
+
{
|
|
136
|
+
"id": "qwen3.8-max",
|
|
137
|
+
"name": "Qwen 3.8 Max (vision)",
|
|
138
|
+
"url": "http://127.0.0.1:3458/v1/chat/completions",
|
|
139
|
+
"toolCalling": true,
|
|
140
|
+
"vision": true,
|
|
141
|
+
"streaming": true,
|
|
142
|
+
"maxInputTokens": 991000,
|
|
143
|
+
"maxOutputTokens": 131072
|
|
144
|
+
},
|
|
123
145
|
{
|
|
124
146
|
"id": "qwen3.7-max",
|
|
125
147
|
"name": "Qwen 3.7 Max (text)",
|
|
@@ -195,7 +217,8 @@ The proxy detects active tool use by examining the conversation state (a `"tool"
|
|
|
195
217
|
|
|
196
218
|
## Notes
|
|
197
219
|
|
|
198
|
-
- **Vision (`qwen3.7-plus`)** uses OpenAI-compatible `content` array format. Base64 data URIs work reliably; external image URLs may fail if DashScope can't reach them. If a drag-and-drop image fails to load, providing the absolute file path (e.g. `c:\path\to\image.png`) in the prompt is a reliable workaround.
|
|
220
|
+
- **Vision (`qwen3.8-max`, `qwen3.7-plus`)** uses OpenAI-compatible `content` array format. Base64 data URIs work reliably; external image URLs may fail if DashScope can't reach them. If a drag-and-drop image fails to load, providing the absolute file path (e.g. `c:\path\to\image.png`) in the prompt is a reliable workaround.
|
|
221
|
+
- **Qwen 3.8 reasoning:** `qwen3.8-max` enables reasoning by default and supports `reasoning_effort` values `low`, `medium`, and `xhigh` (default). The direct snippet disables reasoning for stable VS Code tool loops; the proxy leaves it on for plain chat and suppresses it when tool activity is detected.
|
|
199
222
|
- **Thinking trade-off:** Direct = thinking always off (loops stable, no reasoning visible). Proxy = thinking on in plain chat, off in tool turns.
|
|
200
223
|
- **`tool_choice` only supports `auto`** — don't override it (VS Code's default is `auto`).
|
|
201
224
|
|
|
@@ -216,6 +239,7 @@ For the cross-provider comparison, see [docs/pricing.md](../pricing.md). DashSco
|
|
|
216
239
|
|
|
217
240
|
| Model | Input (≤ 256K tokens) | Input (> 256K tokens) | Output (≤ 256K tokens) | Output (> 256K tokens) |
|
|
218
241
|
| -------------- | --------------------- | --------------------- | ---------------------- | ---------------------- |
|
|
242
|
+
| `qwen3.8-max` | $2.00 | — | $6.00 | — |
|
|
219
243
|
| `qwen3.7-plus` | $0.40 / 1M | $1.20 / 1M | $1.60 / 1M | $4.80 / 1M |
|
|
220
244
|
| `qwen3.7-max` | $2.50 / 1M (≤ 1M) | — | $7.50 / 1M (≤ 1M) | — |
|
|
221
245
|
|
package/docs/pricing.md
CHANGED
|
@@ -22,36 +22,37 @@ All prices below are in **USD per 1M tokens** (non-cached). To convert to AI cre
|
|
|
22
22
|
|
|
23
23
|
All models are listed together below, sorted by Cost per intelligence ascending (lower is better). Models without a Cost per intelligence are ordered by estimated session cost ascending. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
|
|
24
24
|
|
|
25
|
-
| Model
|
|
26
|
-
|
|
|
27
|
-
| **DeepSeek V4 Flash**
|
|
28
|
-
| **MiMo V2.5**
|
|
29
|
-
| **GPT-5.6 Luna**
|
|
30
|
-
| **MiniMax M3**
|
|
31
|
-
| **DeepSeek V4 Pro**
|
|
32
|
-
| **MiMo V2.5 Pro**
|
|
33
|
-
| **Qwen 3.7 Plus**
|
|
34
|
-
| **MiniMax M3 Priority**⁵
|
|
35
|
-
| **Kimi K2.6**
|
|
36
|
-
| **Kimi K2.7 Code**
|
|
37
|
-
| **GPT-5.4 mini**
|
|
38
|
-
| **GLM 5.2** ⁴
|
|
39
|
-
| **GLM 5.1**
|
|
40
|
-
| **GLM 5V Turbo**
|
|
41
|
-
| **Gemini 3.6 Flash** ⁹
|
|
42
|
-
| **
|
|
43
|
-
| **
|
|
44
|
-
| **
|
|
45
|
-
| **
|
|
46
|
-
| **
|
|
47
|
-
| **
|
|
48
|
-
| **
|
|
49
|
-
| **Claude Sonnet
|
|
50
|
-
| **Claude
|
|
51
|
-
| **Claude Opus
|
|
52
|
-
| **Claude Opus 4.
|
|
53
|
-
| **
|
|
54
|
-
| **GPT-5.
|
|
25
|
+
| Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
|
|
26
|
+
| -------------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
|
|
27
|
+
| **DeepSeek V4 Flash 0731** | DeepSeek | **~$0.0020** | **49.9** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
|
|
28
|
+
| **MiMo V2.5** | Xiaomi | **~$0.0025** | **40** ³ | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
|
|
29
|
+
| **GPT-5.6 Luna** | OpenAI | **~$0.0043** | **51.2** | $0.20 | $0.02 | $1.20 | ~$0.22 | 1M |
|
|
30
|
+
| **MiniMax M3** | MiniMax | **~$0.0061** | **44.4** | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | ~$0.27 | 1M |
|
|
31
|
+
| **DeepSeek V4 Pro** | DeepSeek | **~$0.0068** | **44.3** | $0.435 | $0.003625 | $0.87 | ~$0.30 | 1M |
|
|
32
|
+
| **MiMo V2.5 Pro** | Xiaomi | **~$0.0072** | **42.2** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
|
|
33
|
+
| **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | $0.40 (≤256K) / $1.20 (>256K) | — | $1.60 (≤256K) / $4.80 (>256K) | ~$0.36 | 1M |
|
|
34
|
+
| **MiniMax M3 Priority**⁵ | MiniMax | **~$0.0092** | **44.4** | $0.90 (≤512K) / $1.80 (>512K) | $0.18 (≤512K) / $0.36 (>512K) | $3.60 (≤512K) / $7.20 (>512K) | ~$0.41 | 1M |
|
|
35
|
+
| **Kimi K2.6** | Moonshot | **~$0.021** | **42.8** | $0.95 | $0.16 | $4.00 | ~$0.88 | 256K |
|
|
36
|
+
| **Kimi K2.7 Code** | Moonshot | **~$0.021** | **42.0** | $0.95 | $0.19 | $4.00 | ~$0.88 | 262K |
|
|
37
|
+
| **GPT-5.4 mini** | OpenAI | **~$0.021** | **40.0** | $0.75 | $0.075 | $4.50 | ~$0.83 | 400K |
|
|
38
|
+
| **GLM 5.2** ⁴ | Z.ai | **~$0.022** | **51.0** | $1.40 | $0.26 | $4.40 | ~$1.14 | 1M |
|
|
39
|
+
| **GLM 5.1** | Z.ai | **~$0.028** | **40.2** | $1.40 | $0.26 | $4.40 | ~$1.14 | 200K |
|
|
40
|
+
| **GLM 5V Turbo** | Z.ai | **~$0.029** | **34.0** ³ | $1.20 | $0.24 | $4.00 | ~$1.00 | 200K |
|
|
41
|
+
| **Gemini 3.6 Flash** ⁹ | Google | **~$0.030** | **50.0** | $1.50 | $0.15 | $7.50 | ~$1.50 | 1M |
|
|
42
|
+
| **Qwen 3.8 Max** ¹¹ | DashScope | **~$0.030** | **53.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
|
|
43
|
+
| **Gemini 3.5 Flash** | Google | **~$0.033** | **50.2** | $1.50 | $0.15 | $9.00 | ~$1.65 | 1M |
|
|
44
|
+
| **GPT-5.6 Terra** | OpenAI | **~$0.040** | **55.0** | $2.00 | $0.20 | $12.00 | ~$2.20 | 1M |
|
|
45
|
+
| **Qwen 3.7 Max** | DashScope | **~$0.043** | **46.0** | $2.50 (≤1M) | — | $7.50 (≤1M) | ~$2.00 | 1M |
|
|
46
|
+
| **Gemini 3.1 Pro** | Google | **~$0.047** | **46.5** | $2.00¹ | $0.20 | $12.00¹ | ~$2.20 | 1M |
|
|
47
|
+
| **Kimi K3** ⁷ | Moonshot | **~$0.053** | **57.0** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
|
|
48
|
+
| **GPT-5.4** | OpenAI | **~$0.054** | **51.4** | $2.50 | $0.25 | $15.00 | ~$2.75 | 1M |
|
|
49
|
+
| **Claude Sonnet 5** ⁶ | Anthropic | **~$0.057** | **53.0** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
|
|
50
|
+
| **Claude Sonnet 4.6** | Anthropic | **~$0.064** | **47.2** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
|
|
51
|
+
| **Claude Opus 5** ¹⁰ | Anthropic | **~$0.082** | **61.0** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
|
|
52
|
+
| **Claude Opus 4.8** | Anthropic | **~$0.090** | **55.7** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
|
|
53
|
+
| **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
|
|
54
|
+
| **GPT-5.6 Sol** | OpenAI | **~$0.093** | **58.9** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
|
|
55
|
+
| **GPT-5.5** | OpenAI | **~$0.10** | **54.8** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
|
|
55
56
|
|
|
56
57
|
¹ Gemini 3.1 Pro pricing applies to prompts ≤200K tokens.
|
|
57
58
|
|
|
@@ -71,6 +72,8 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
71
72
|
|
|
72
73
|
¹⁰ **Claude Opus 5** was released on **July 24, 2026**. AA Intelligence Index score (**61.0**) confirmed by [Artificial Analysis](https://artificialanalysis.ai/models/claude-opus-5). Pricing is $5.00 / $0.50 / $25.00 per MTok input/cached/output (same as Opus 4.8). 1M context window, text + image input, adaptive reasoning. Also available in Fast mode ($10/$50 per MTok input/output) and Batch ($2.50/$12.50 per MTok input/output). Uses the newer Claude tokenizer (~30% more tokens than pre-4.7 models). See [Anthropic's Opus 5 announcement](https://www.anthropic.com/news/claude-opus-5).
|
|
73
74
|
|
|
75
|
+
¹¹ **Qwen 3.8 Max** (`qwen3.8-max`) launched on **August 3, 2026**. Qwen Cloud lists $2.00 input / $6.00 output per 1M tokens, $0.25 implicit-cache input, $2.50 explicit-cache creation, and $0.17 explicit-cache reads. The modeled session cost is ~$1.60 using 10K input + 2K output tokens per turn across 50 turns. It has a 1M context window, 131K maximum output, and text/image/video input. OpenRouter currently reports an Artificial Analysis Intelligence Index of **53.4** for this model. See the [Qwen Cloud model page](https://www.qwencloud.com/models/qwen3.8-max) and [OpenRouter model page](https://openrouter.ai/qwen/qwen3.8-max).
|
|
76
|
+
|
|
74
77
|
Cost per intelligence = estimated session cost ÷ Intelligence Index score. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
|
|
75
78
|
|
|
76
79
|
> **Notes:**
|
package/package.json
CHANGED
package/proxy/qwen-proxy.mjs
CHANGED
|
@@ -5,7 +5,7 @@ import { createProxy } from '../lib/create-proxy.mjs'
|
|
|
5
5
|
|
|
6
6
|
/**
|
|
7
7
|
* Supported model scope for this proxy:
|
|
8
|
-
* - Validated with `qwen3.7-plus
|
|
8
|
+
* - Validated with `qwen3.8-max`, `qwen3.7-plus`, and `qwen3.7-max`.
|
|
9
9
|
* - Expected to work for any Qwen3 hybrid-thinking model (qwen3-* series)
|
|
10
10
|
* that supports the `enable_thinking` top-level field on DashScope's
|
|
11
11
|
* OpenAI-compatible surface.
|