copilot-custom-endpoint 3.1.1 → 3.2.0

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
@@ -20,18 +20,20 @@ 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** | 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 3.8 Max (0803)** | OpenRouter | Optional (experimental) | ✅ | [Snapshot/proxy setup](docs/models/qwen.md#optional-openrouter-snapshot-proxy) |
29
- | **Qwen 3.8 Max (0902)** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
30
- | **MiniMax M3** | MiniMax | No | ✅ | [Extension](https://github.com/tugudush/minimax-copilot) ★ / [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** | DeepSeek | No (uses an extension) | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) / [setup notes](docs/models/deepseek.md) |
34
- | **DeepSeek V4 Pro 0813** | 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** | Moonshot | **Yes** | ✅ | [Manual setup](docs/models/kimi.md) |
26
+ | **MiMo V2.6 Pro** | Xiaomi | **Yes** | ✅ | [Manual setup](docs/models/mimo.md) |
27
+ | **MiMo V2.6 Flash** | Xiaomi | **Yes** | ✅ | [Manual setup](docs/models/mimo.md) |
28
+ | **MiMo V2.6 Pro UltraSpeed** | Xiaomi | **Yes** | ✅ | [Manual setup](docs/models/mimo.md) |
29
+ | **MiMo V2.5 / V2.5 Pro** | Xiaomi | Optional (legacy) | V2.5 | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) / [Migration guide](docs/models/mimo.md) |
30
+ | **Qwen 3.8 Max (0803)** | OpenRouter | Optional (experimental) | ✅ | [Snapshot/proxy setup](docs/models/qwen.md#optional-openrouter-snapshot-proxy) |
31
+ | **Qwen 3.8 Max (0902)** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
32
+ | **MiniMax M3** | MiniMax | No | ✅ | [Extension](https://github.com/tugudush/minimax-copilot) ★ / [Manual setup](docs/models/minimax.md) |
33
+ | **GLM 5.3 Flash** | Z.ai | No | ✅ | [Manual setup](docs/models/glm.md) |
34
+ | **GLM 5.3** | Z.ai | No | ❌ | [Manual setup](docs/models/glm.md) |
35
+ | **DeepSeek V4.1 Flash** | DeepSeek | No (uses an extension) | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) / [setup notes](docs/models/deepseek.md) |
36
+ | **DeepSeek V4 Pro 0813** | DeepSeek | No (uses an extension) | ❌ | [Extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) / [setup notes](docs/models/deepseek.md) |
35
37
 
36
38
  ## Setup
37
39
 
@@ -65,8 +67,9 @@ Open the setup guide for the model you picked (links in the table above) and cop
65
67
  1. Open VS Code Settings (`Ctrl+,` / `Cmd+,`).
66
68
  2. Search for **"Chat: Utility Small Model"** (setting ID: `chat.lm.utilitySmallModel`).
67
69
  3. Pick the **fastest, cheapest model** available to you from the dropdown. Good choices:
68
- - **DeepSeek V4.1 Flash** — if you have the [DeepSeek V4 for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) extension installed (fastest, ~$0.27/session at peak rates).
69
- - **MiMo V2.5** — if you already have Xiaomi MiMo configured (cheapest custom-endpoint option, ~$0.10/session).
70
+ - **GLM 5.3 Flash** — if you have [GLM configured](docs/models/glm.md) (cheapest custom-endpoint option, ~$0.13/session).
71
+ - **GPT-5.6 Luna** — if it is available through your native Copilot models (fast, ~$0.22/session).
72
+ - **MiMo V2.6 Flash** — if you already have Xiaomi MiMo configured (low-cost multimodal option, ~$0.10/session).
70
73
  - **Default** — if you still have native Copilot model access, this lets VS Code use its built-in fast model.
71
74
  4. The setting takes effect immediately — no restart needed.
72
75
 
@@ -105,31 +108,50 @@ npx copilot-custom-endpoint clean # Remove debug_log/
105
108
 
106
109
  ## Pricing snapshot
107
110
 
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. DeepSeek estimates use peak rates; official off-peak rates are half. The current AA values come from OpenRouter's September 15 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. Current corrections include DeepSeek V4.1 Flash at **$0.30 / $0.006 / $1.20** peak, OpenAI GPT-5.6 Sol at **$4 / $0.40 / $20**, and Anthropic Sonnet 5 at **$2 / $0.20 / $10**.
109
-
110
- | Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
111
- | ------------------------ | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
112
- | **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.9** | ~$0.13 | ✅ | 1M |
113
- | **MiMo V2.5** | Xiaomi | **~$0.0045** | **22.3** | ~$0.10 | ✅ | 1M |
114
- | **GPT-5.6 Luna** | OpenAI | **~$0.0059** | **37.5** | ~$0.22 | ✅ | 1M |
115
- | **DeepSeek V4.1 Flash** | DeepSeek | **~$0.0068** | **39.5** | ~$0.27 | ✅ | 1M |
116
- | **MiniMax M3** | MiniMax | **~$0.0091** | **29.6** | ~$0.27 | ✅ | 1M |
117
- | **MiMo V2.5 Pro** | Xiaomi | **~$0.0114** | **26.4** | ~$0.30 | ❌ | 1M |
118
- | **MiniMax M3 Priority** | MiniMax | **~$0.0139** | **29.6** | ~$0.41 | ✅ | 1M |
119
- | **Gemini 3.8 Flash** | Google | **~$0.0182** | **41.2** | ~$0.75 | ✅ | 1M |
120
- | **GLM 5.3** | Z.ai | **~$0.0254** | **44.9** | ~$1.14 | ❌ | 1M |
121
- | **DeepSeek V4 Pro 0813** | DeepSeek | **~$0.0292** | **36.3** | ~$1.06 | ❌ | 1M |
122
- | **Qwen 3.8 Max (0803)** | DashScope | **~$0.0300** | **53.4** | ~$1.60 | ✅ | 1M |
123
- | **Qwen 3.8 Max (0902)** | DashScope | **~$0.0352** | **45.4** | ~$1.60 | ✅ | 1M |
124
- | **Grok 4.6** | xAI | **~$0.0360** | **44.4** | ~$1.60 | ✅ | 500K |
125
- | **GPT-5.6 Terra** | OpenAI | **~$0.0520** | **42.3** | ~$2.20 | ✅ | 1M |
126
- | **Claude Sonnet 5** | Anthropic | **~$0.0521** | **38.4** | ~$2.00 | ✅ | 1M |
127
- | **Kimi K3** | Moonshot | **~$0.0685** | **43.8** | ~$3.00 | ✅ | 1M |
128
- | **GPT-5.6 Sol** | OpenAI | **~$0.0849** | **47.1** | ~$4.00 | ✅ | 1M |
129
- | **Claude Opus 5** | Anthropic | **~$0.0986** | **50.7** | ~$5.00 | ✅ | 1M |
130
- | **Claude Fable 5.1** | Anthropic | **~$0.1873** | **53.4** | ~$10.00 | ✅ | 1M |
131
- | **GPT-6 Astra** | OpenAI | **~$0.1894** | **52.8** | ~$10.00 | ✅ | 1M |
132
- | **Claude Fable 5** | Anthropic | **~$0.2012** | **49.7** | ~$10.00 | ✅ | 1M |
111
+ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01; multiply a dollar amount by 100 to convert it to credits (for example, $5.00/1M = 500 credits/1M).
112
+
113
+ The table is sorted by **Cost per intelligence**, lowest first. This is a value metric calculated as:
114
+
115
+ `estimated session cost / Intelligence Score`
116
+
117
+ It approximates the cost of one point on the AA Intelligence Index under the common workload below. A lower number means more benchmark intelligence per estimated dollar; it is not an overall quality ranking or a provider billing quote.
118
+
119
+ **Est. session** uses ~10K input + ~2K output tokens per turn over 50 turns: 500K input tokens plus 100K output tokens total. For each model, the estimate is:
120
+
121
+ `(0.5 × input price) + (0.1 × output price)`
122
+
123
+ 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.
124
+
125
+ The current AA values come from OpenRouter's September 22 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 adds Xiaomi MiMo V2.6 and xAI Grok 4.7, and uses the current AA v4.3.2 composites.
126
+
127
+ | Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
128
+ | ---------------------------- | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
129
+ | **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.8** | ~$0.13 | ✅ | 1M |
130
+ | **GPT-5.6 Luna** | OpenAI | **~$0.0059** | **37.3** | ~$0.22 | ✅ | 1M |
131
+ | **MiMo V2.6 Pro** | Xiaomi | **~$0.0066** | **46.3** | ~$0.30 | ✅ | 1M |
132
+ | **DeepSeek V4.1 Flash** | DeepSeek | **~$0.0068** | **39.5** | ~$0.27 | ✅ | 1M |
133
+ | **MiniMax M3** | MiniMax | **~$0.0093** | **29.2** | ~$0.27 | ✅ | 1M |
134
+ | **MiMo V2.5 Pro** | Xiaomi | **~$0.0115** | **26.0** | ~$0.30 | ❌ | 1M |
135
+ | **Gemini 3.8 Flash** | Google | **~$0.0183** | **40.9** | ~$0.75 | ✅ | 1M |
136
+ | **GLM 5.3** | Z.ai | **~$0.0254** | **44.8** | ~$1.14 | ❌ | 1M |
137
+ | **DeepSeek V4 Pro 0813** | DeepSeek | **~$0.0294** | **36.0** | ~$1.06 | ❌ | 1M |
138
+ | **Qwen 3.8 Max (0803)** | DashScope | **~$0.0300** | **53.4** | ~$1.60 | ✅ | 1M |
139
+ | **Grok 4.7** | xAI | **~$0.0345** | **46.4** | ~$1.60 | ✅ | 500K |
140
+ | **Qwen 3.8 Max (0902)** | DashScope | **~$0.0352** | **45.4** | ~$1.60 | ✅ | 1M |
141
+ | **Grok 4.6** | xAI | **~$0.0361** | **44.3** | ~$1.60 | ✅ | 500K |
142
+ | **GPT-5.6 Terra** | OpenAI | **~$0.0523** | **42.1** | ~$2.20 | ✅ | 1M |
143
+ | **Claude Sonnet 5** | Anthropic | **~$0.0524** | **38.2** | ~$2.00 | ✅ | 1M |
144
+ | **Kimi K3** | Moonshot | **~$0.0688** | **43.6** | ~$3.00 | ✅ | 1M |
145
+ | **GPT-5.6 Sol** | OpenAI | **~$0.0851** | **47.0** | ~$4.00 | ✅ | 1M |
146
+ | **Claude Opus 5** | Anthropic | **~$0.0984** | **50.8** | ~$5.00 | ✅ | 1M |
147
+ | **Claude Fable 5.1** | Anthropic | **~$0.1873** | **53.4** | ~$10.00 | ✅ | 1M |
148
+ | **GPT-6 Astra** | OpenAI | **~$0.1898** | **52.7** | ~$10.00 | ✅ | 1M |
149
+ | **Claude Fable 5** | Anthropic | **~$0.2016** | **49.6** | ~$10.00 | ✅ | 1M |
150
+ | **MiMo V2.6 Flash** | Xiaomi | — | — | ~$0.10 | ✅ | 1M |
151
+ | **MiMo V2.5** | Xiaomi | — | — | ~$0.10 | ✅ | 1M |
152
+ | **MiMo V2.6 Pro UltraSpeed** | Xiaomi | — | — | ~$3.05 | ✅ | 1M |
153
+
154
+ > `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.
133
155
 
134
156
  > 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).
135
157
 
package/cli.mjs CHANGED
@@ -15,7 +15,7 @@ Start a local proxy for VS Code Copilot custom endpoints.
15
15
  copilot-custom-endpoint all Start all proxies concurrently (default)
16
16
  copilot-custom-endpoint kimi Start the Kimi K2 proxy on port 3457
17
17
  copilot-custom-endpoint qwen Start the Qwen 3.x proxy on port 3458
18
- copilot-custom-endpoint mimo Start the MiMo V2.5 proxy on port 3459
18
+ copilot-custom-endpoint mimo Start the MiMo V2.6 proxy on port 3459
19
19
  copilot-custom-endpoint clean Remove the debug_log/ directory
20
20
 
21
21
  Environment variables: see --help for each proxy.
@@ -2,7 +2,7 @@
2
2
 
3
3
  Here's a complete, real-world `chatLanguageModels.json` that combines **the `customendpoint` providers from the live `chatLanguageModels.json`**, plus the additional GLM models (`glm-5.3-flash`, `glm-5.3`, `glm-5.2`, `glm-5.1`) that are validated in [docs/models/glm.md](models/glm.md) but not present in every live config. Copy what you need, leave the rest out.
4
4
 
5
- > **⚠️ Reminder:** After adding models, you must also configure the **Utility Small Model** setting in VS Code. Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4 Flash or MiMo V2.5). Without this, custom-endpoint models may not function correctly. See the [main README](../README.md#4-configure-the-utility-small-model) for details.
5
+ > **⚠️ Reminder:** After adding models, you must also configure the **Utility Small Model** setting in VS Code. Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4 Flash or MiMo V2.6 Flash). Without this, custom-endpoint models may not function correctly. See the [main README](../README.md#4-configure-the-utility-small-model) for details.
6
6
  >
7
7
  > **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.
8
8
  >
@@ -57,11 +57,11 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
57
57
  "apiType": "chat-completions",
58
58
  "models": [
59
59
  {
60
- "id": "mimo-v2.5-pro",
61
- "name": "MiMo V2.5 Pro (text)",
60
+ "id": "mimo-v2.6-pro",
61
+ "name": "MiMo V2.6 Pro",
62
62
  "url": "http://127.0.0.1:3459/v1/chat/completions",
63
63
  "toolCalling": true,
64
- "vision": false,
64
+ "vision": true,
65
65
  "streaming": true,
66
66
  "maxInputTokens": 1048576,
67
67
  "maxOutputTokens": 131072,
@@ -71,14 +71,28 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
71
71
  }
72
72
  },
73
73
  {
74
- "id": "mimo-v2.5",
75
- "name": "MiMo V2.5 (vision)",
74
+ "id": "mimo-v2.6-flash",
75
+ "name": "MiMo V2.6 Flash",
76
76
  "url": "http://127.0.0.1:3459/v1/chat/completions",
77
77
  "toolCalling": true,
78
78
  "vision": true,
79
79
  "streaming": true,
80
80
  "maxInputTokens": 1048576,
81
- "maxOutputTokens": 32768,
81
+ "maxOutputTokens": 131072,
82
+ "requestBody": {
83
+ "temperature": 1,
84
+ "top_p": 0.95
85
+ }
86
+ },
87
+ {
88
+ "id": "mimo-v2.6-pro-ultraspeed",
89
+ "name": "MiMo V2.6 Pro UltraSpeed",
90
+ "url": "http://127.0.0.1:3459/v1/chat/completions",
91
+ "toolCalling": true,
92
+ "vision": true,
93
+ "streaming": true,
94
+ "maxInputTokens": 1048576,
95
+ "maxOutputTokens": 131072,
82
96
  "requestBody": {
83
97
  "temperature": 1,
84
98
  "top_p": 0.95
@@ -44,7 +44,7 @@
44
44
  2. **Generate an API key** on the API Keys page of the platform.
45
45
  3. **Edit `chatLanguageModels.json`** — add the GLM block below.
46
46
  4. **Set the API key** via Command Palette → **Chat: Manage Language Models** → right-click **GLM** → **Update API Key**.
47
- 5. **Configure the Utility Small Model** — Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4 Flash or MiMo V2.5). [Why?](../../README.md#4-configure-the-utility-small-model)
47
+ 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)
48
48
  6. **Restart VS Code** and select a GLM model from the picker.
49
49
 
50
50
  ## Setup
@@ -33,7 +33,7 @@
33
33
  1. **Start the proxy** — `npm run proxy:kimi` (or `npx copilot-custom-endpoint kimi` standalone).
34
34
  2. **Edit `chatLanguageModels.json`** — add the Kimi block below.
35
35
  3. **Set your Moonshot API key** via Command Palette → **Chat: Manage Language Models**.
36
- 4. **Configure the Utility Small Model** — Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4 Flash or MiMo V2.5). [Why?](../../README.md#4-configure-the-utility-small-model)
36
+ 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)
37
37
  5. **Restart VS Code** and pick "Kimi K3".
38
38
 
39
39
  ## Setup
@@ -1,53 +1,55 @@
1
1
  # Xiaomi MiMo — VS Code Custom Endpoint Setup Guide
2
2
 
3
- > **TL;DR:** The recommended path is the [Xiaomi MiMo for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) VS Code extension — it supports thinking mode WITH tool calling, prompt caching feedback, reasoning visibility in agent mode, and token usage reporting, with zero dependencies. Two alternative methods are documented below for users who prefer direct `chatLanguageModels.json` control.
3
+ > **TL;DR:** MiMo V2.6 is now the current API family. The proxy-backed custom endpoint keeps V2.6 thinking enabled when `reasoning_content` is present and falls back to disabled thinking when VS Code drops that history field. Direct and proxy configurations are documented below; MiMo V2.5 and V2.5 Pro remain available until Xiaomi's October 21, 2026 deprecation.
4
4
 
5
5
  ## At a Glance
6
6
 
7
- | Field | Value |
8
- | ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
9
- | **Recommended method** | **[Xiaomi MiMo for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot)** VS Code extension |
10
- | Alternative methods | Direct API (static `thinking: disabled`) or `proxy/mimo-proxy.mjs` (dynamic suppression) |
11
- | Mode (custom endpoint) | **Direct** (static `thinking: disabled`) **or** **Proxy** (dynamic, local on `:3459`) |
12
- | Billing | **Pay-as-You-Go** _or_ **Token Plan subscription** (shared `requestBody`) |
13
- | Vision | ✅ Yes (`mimo-v2.5` only) |
14
- | Tool calling | ✅ Yes (with thinking disabled, OR thinking enabled via the extension's reasoning cache) |
15
- | Context | 917K (extension) / 1M (custom endpoint) |
16
- | Max output | 131072 (V2.5 Pro) / 32768 (V2.5) |
17
- | Endpoint | `https://api.xiaomimimo.com/v1/chat/completions` |
18
- | Proxy endpoint | `http://127.0.0.1:3459/v1/chat/completions` |
19
- | Auth | `Authorization: Bearer $MIMO_API_KEY` |
7
+ | Field | Value |
8
+ | ---------------------- | ---------------------------------------------------------------------------------------------------------------------- |
9
+ | **Recommended method** | **`proxy/mimo-proxy.mjs`** for V2.6 custom endpoints; the extension is still useful when its model picker exposes V2.6 |
10
+ | Alternative methods | Direct API (static `thinking: disabled`) or the Xiaomi extension |
11
+ | Mode (custom endpoint) | **Direct** (static `thinking: disabled`) **or** **Proxy** (dynamic, local on `:3459`) |
12
+ | Billing | **Pay-as-You-Go** _or_ **Token Plan subscription** (shared `requestBody`) |
13
+ | Vision | ✅ Yes (all V2.6 models; V2.5 Pro remains text-only) |
14
+ | Tool calling | ✅ Yes; V2.6 preserves thinking only when the history includes `reasoning_content` |
15
+ | Context | 1M |
16
+ | Max output | 131072 (V2.6 and V2.5 chat models) |
17
+ | Endpoint | `https://api.xiaomimimo.com/v1/chat/completions` |
18
+ | Proxy endpoint | `http://127.0.0.1:3459/v1/chat/completions` |
19
+ | Auth | `Authorization: Bearer $MIMO_API_KEY` |
20
20
 
21
21
  ### Models
22
22
 
23
- | Model | Vision | Context | Max output | Notes |
24
- | -------------------------- | ------ | ------- | --------------- | --------------------------------------------------------------------- |
25
- | `mimo-v2.5-pro-ultraspeed` | ❌ | 917K | _(unspecified)_ | Fast Pro reasoning for latency-sensitive agent tasks (extension only) |
26
- | `mimo-v2.5-pro` | ❌ | 917K | 131072 | Flagship text-only — best for deep reasoning |
27
- | `mimo-v2.5` | ✅ | 917K | 32768 | Omnimodal — text + image + video + audio |
23
+ | Model | Vision | Context | Max output | Notes |
24
+ | -------------------------- | ------ | ------- | ---------- | ------------------------------------------------------------------ |
25
+ | `mimo-v2.6-pro` | ✅ | 1M | 131072 | Flagship full-modality reasoning for complex and long-horizon work |
26
+ | `mimo-v2.6-flash` | ✅ | 1M | 131072 | Lower-cost full-modality model for frequent calls |
27
+ | `mimo-v2.6-pro-ultraspeed` | ✅ | 1M | 131072 | V2.6 Pro quality with the latency-focused UltraSpeed service |
28
+ | `mimo-v2.5-pro` _(legacy)_ | ❌ | 1M | 131072 | Text-only; deprecated October 21, 2026 |
29
+ | `mimo-v2.5` _(legacy)_ | ✅ | 1M | 131072 | Full-modality; deprecated October 21, 2026 |
28
30
 
29
- > `mimo-v2.5-pro-ultraspeed` is only available through the VS Code extension. Custom-endpoint methods below cover `mimo-v2.5-pro` and `mimo-v2.5`.
31
+ > Xiaomi's API requires the lowercase IDs above. V2.5 and V2.5 Pro are scheduled to stop accepting their old names at 10:00 Beijing time on October 21, 2026.
30
32
 
31
33
  ## Quick Start
32
34
 
33
- ### Recommended: VS Code Extension
35
+ ### Recommended: V2.6 custom endpoint with proxy
34
36
 
35
- 1. **Install** from the [VS Code Marketplace](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot).
36
- 2. **Set your API key** — run **MiMo: Set API Key** from the Command Palette (`Ctrl+Shift+P`).
37
- 3. **Pick a model** in Copilot Chat's model picker — choose **MiMo-V2.5-Pro-UltraSpeed**, **MiMo V2.5 Pro**, or **MiMo V2.5**.
38
- 4. That's it — chat away.
37
+ 1. Add the proxy configuration from the setup section below.
38
+ 2. Start `npm run proxy:mimo` from the repository root.
39
+ 3. Set your API key through **Chat: Manage Language Models**.
40
+ 4. Pick **MiMo V2.6 Pro**, **MiMo V2.6 Flash**, or **MiMo V2.6 Pro UltraSpeed** in Copilot Chat.
39
41
 
40
- **Why the extension over custom endpoints:**
42
+ The [Xiaomi MiMo for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) extension remains the best option when its picker exposes the V2.6 IDs because it can cache reasoning per tool call. The custom endpoint is useful when you need direct control over the model IDs, URL, or proxy behavior.
41
43
 
42
- | Capability | Extension | Custom Endpoint |
43
- | -------------------------------- | ------------------------------------ | -------------------------------------- |
44
- | Thinking + tool calling together | ✅ Yes (reasoning cache) | ❌ Must disable thinking on tool turns |
45
- | Reasoning visible in agent mode | ✅ Yes (`LanguageModelThinkingPart`) | ❌ Hidden (suppressed by proxy) |
46
- | Prompt caching feedback loop | ✅ 97–99% cache hit rates | ❌ No cache awareness |
47
- | Token usage in context widget | ✅ Yes | ❌ No |
48
- | `mimo-v2.5-pro-ultraspeed` model | ✅ Yes | ❌ Not available |
49
- | Multi-region endpoint selector | ✅ Built-in dropdown | ❌ Manual JSON edits |
50
- | Dependencies | ✅ Zero (VS Code + Node built-ins) | ❌ Requires proxy server |
44
+ | Capability | Extension | Custom Endpoint |
45
+ | -------------------------------- | ------------------------------------ | --------------------------------------- |
46
+ | Thinking + tool calling together | ✅ Yes (reasoning cache) | ✅ When `reasoning_content` is retained |
47
+ | Reasoning visible in agent mode | ✅ Yes (`LanguageModelThinkingPart`) | ⚠️ Depends on request history |
48
+ | Prompt caching feedback loop | ✅ 97–99% cache hit rates | ❌ No cache awareness |
49
+ | Token usage in context widget | ✅ Yes | ❌ No |
50
+ | `mimo-v2.6-pro-ultraspeed` model | Depends on extension version | ✅ Yes |
51
+ | Multi-region endpoint selector | ✅ Built-in dropdown | ❌ Manual JSON edits |
52
+ | Dependencies | ✅ Zero (VS Code + Node built-ins) | ❌ Requires proxy server |
51
53
 
52
54
  > **Prerequisites:** VS Code 1.116+, GitHub Copilot subscription (Free tier works), and a MiMo API key from [platform.xiaomimimo.com](https://platform.xiaomimimo.com/console/api-keys). MIT-licensed. Source: [Sdcb/xiaomimimo-for-copilot](https://github.com/Sdcb/xiaomimimo-for-copilot).
53
55
 
@@ -57,12 +59,12 @@ Simplest no-proxy approach — but thinking is always off, so you never see mode
57
59
 
58
60
  1. **Edit `chatLanguageModels.json`** — add the MiMo block(s) below.
59
61
  2. **Set your `MIMO_API_KEY`** via Command Palette → **Chat: Manage Language Models**.
60
- 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)
61
- 4. **Restart VS Code** and pick "MiMo V2.5 Pro" or "MiMo V2.5".
62
+ 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)
63
+ 4. **Restart VS Code** and pick one of the V2.6 entries.
62
64
 
63
65
  ### Alternative: With optional proxy (dynamic thinking)
64
66
 
65
- The `proxy/mimo-proxy.mjs` provides dynamic thinking suppression: reasoning stays ON in plain chat but turns OFF automatically when tools are invoked. A middle ground — reasoning visible in chat, suppressed in agent mode.
67
+ The `proxy/mimo-proxy.mjs` preserves V2.6 thinking when assistant tool-call history contains `reasoning_content`. When VS Code sends a tool loop with missing reasoning history, it injects `thinking: { "type": "disabled" }` to avoid Xiaomi's 400 response. Legacy V2.5 models always use that fallback for tool-enabled requests.
66
68
 
67
69
  - `npm run proxy:mimo` (from the repo root)
68
70
  - `npx copilot-custom-endpoint mimo` (standalone)
@@ -106,11 +108,11 @@ The extension stores your API key in VS Code's `SecretStorage` (OS keychain).
106
108
  "apiType": "chat-completions",
107
109
  "models": [
108
110
  {
109
- "id": "mimo-v2.5-pro",
110
- "name": "MiMo V2.5 Pro (text)",
111
+ "id": "mimo-v2.6-pro",
112
+ "name": "MiMo V2.6 Pro",
111
113
  "url": "https://api.xiaomimimo.com/v1/chat/completions",
112
114
  "toolCalling": true,
113
- "vision": false,
115
+ "vision": true,
114
116
  "streaming": true,
115
117
  "maxInputTokens": 1048576,
116
118
  "maxOutputTokens": 131072,
@@ -121,14 +123,29 @@ The extension stores your API key in VS Code's `SecretStorage` (OS keychain).
121
123
  }
122
124
  },
123
125
  {
124
- "id": "mimo-v2.5",
125
- "name": "MiMo V2.5 (vision)",
126
+ "id": "mimo-v2.6-flash",
127
+ "name": "MiMo V2.6 Flash",
126
128
  "url": "https://api.xiaomimimo.com/v1/chat/completions",
127
129
  "toolCalling": true,
128
130
  "vision": true,
129
131
  "streaming": true,
130
132
  "maxInputTokens": 1048576,
131
- "maxOutputTokens": 32768,
133
+ "maxOutputTokens": 131072,
134
+ "requestBody": {
135
+ "thinking": { "type": "disabled" },
136
+ "temperature": 1,
137
+ "top_p": 0.95
138
+ }
139
+ },
140
+ {
141
+ "id": "mimo-v2.6-pro-ultraspeed",
142
+ "name": "MiMo V2.6 Pro UltraSpeed",
143
+ "url": "https://api.xiaomimimo.com/v1/chat/completions",
144
+ "toolCalling": true,
145
+ "vision": true,
146
+ "streaming": true,
147
+ "maxInputTokens": 1048576,
148
+ "maxOutputTokens": 131072,
132
149
  "requestBody": {
133
150
  "thinking": { "type": "disabled" },
134
151
  "temperature": 1,
@@ -149,25 +166,36 @@ The extension stores your API key in VS Code's `SecretStorage` (OS keychain).
149
166
  "apiType": "chat-completions",
150
167
  "models": [
151
168
  {
152
- "id": "mimo-v2.5-pro",
153
- "name": "MiMo V2.5 Pro (text)",
169
+ "id": "mimo-v2.6-pro",
170
+ "name": "MiMo V2.6 Pro",
154
171
  "url": "http://127.0.0.1:3459/v1/chat/completions",
155
172
  "toolCalling": true,
156
- "vision": false,
173
+ "vision": true,
157
174
  "streaming": true,
158
175
  "maxInputTokens": 1048576,
159
176
  "maxOutputTokens": 131072,
160
177
  "requestBody": { "temperature": 1, "top_p": 0.95 }
161
178
  },
162
179
  {
163
- "id": "mimo-v2.5",
164
- "name": "MiMo V2.5 (vision)",
180
+ "id": "mimo-v2.6-flash",
181
+ "name": "MiMo V2.6 Flash",
165
182
  "url": "http://127.0.0.1:3459/v1/chat/completions",
166
183
  "toolCalling": true,
167
184
  "vision": true,
168
185
  "streaming": true,
169
186
  "maxInputTokens": 1048576,
170
- "maxOutputTokens": 32768,
187
+ "maxOutputTokens": 131072,
188
+ "requestBody": { "temperature": 1, "top_p": 0.95 }
189
+ },
190
+ {
191
+ "id": "mimo-v2.6-pro-ultraspeed",
192
+ "name": "MiMo V2.6 Pro UltraSpeed",
193
+ "url": "http://127.0.0.1:3459/v1/chat/completions",
194
+ "toolCalling": true,
195
+ "vision": true,
196
+ "streaming": true,
197
+ "maxInputTokens": 1048576,
198
+ "maxOutputTokens": 131072,
171
199
  "requestBody": { "temperature": 1, "top_p": 0.95 }
172
200
  }
173
201
  ]
@@ -196,7 +224,7 @@ The extension has a built-in multi-region endpoint selector covering all Token P
196
224
 
197
225
  ## Local Proxy
198
226
 
199
- The `proxy/mimo-proxy.mjs` (optional) provides dynamic thinking suppression: reasoning stays ON in plain chat but turns OFF automatically when tools are invoked. If you don't mind thinking being off on every turn, the direct path is simpler. If you want the agent reasoning cache, use the extension (recommended above).
227
+ The `proxy/mimo-proxy.mjs` (optional) keeps V2.6 reasoning enabled when the conversation history is complete and suppresses it only when a tool loop is missing `reasoning_content`. If you want Xiaomi's full reasoning cache behavior, use an extension version that explicitly supports V2.6.
200
228
 
201
229
  | Setting | Value |
202
230
  | ------------ | ----------------------------------------------------- |
@@ -206,32 +234,36 @@ The `proxy/mimo-proxy.mjs` (optional) provides dynamic thinking suppression: rea
206
234
  | Start | `npm run proxy:mimo` (or `node proxy/mimo-proxy.mjs`) |
207
235
  | Help | `node proxy/mimo-proxy.mjs --help` |
208
236
 
209
- When using the proxy, point model `url`s to `http://127.0.0.1:3459/v1/chat/completions` and **remove** `thinking` from `requestBody`. The proxy handles it dynamically.
237
+ When using the proxy, point model `url`s to `http://127.0.0.1:3459/v1/chat/completions` and **remove** `thinking` from `requestBody`. The proxy handles V2.6 history-aware fallback dynamically.
210
238
 
211
239
  ## Notes
212
240
 
213
- - **Thinking is required for full agent quality.** MiMo returns HTTP 400 if `reasoning_content` is missing from history when thinking is on. Custom endpoints disable thinking on tool turns to avoid this; the extension solves it natively via a per-`tool_call_id` reasoning cache.
241
+ - **Thinking is required for full agent quality.** MiMo V2.6 returns HTTP 400 if `reasoning_content` is missing from history when thinking is on. The proxy preserves thinking when that field is present and disables it as a compatibility fallback when VS Code drops it; an extension with a per-`tool_call_id` reasoning cache can keep thinking enabled throughout.
214
242
  - **`tool_choice` other than `"auto"` is stripped** and treated as `"auto"`. Don't override it (VS Code's default is `auto`).
215
243
  - **Rate limits:** 100 RPM / 10M TPM per model per account.
216
- - **Vision (image input via OpenAI `content` array) is only on `mimo-v2.5`.** `mimo-v2.5-pro` and `mimo-v2.5-pro-ultraspeed` are text-only.
244
+ - **Vision and full modality:** V2.6 Pro, Flash, and Pro UltraSpeed accept text, image, video, and audio; VS Code custom endpoints expose image input through `vision: true`. V2.5 Pro remains text-only.
245
+ - **Deprecation:** Xiaomi will deprecate `mimo-v2.5-pro` and `mimo-v2.5` at 10:00 Beijing time on October 21, 2026.
217
246
 
218
247
  ## Troubleshooting
219
248
 
220
- | Symptom | Likely cause | Fix |
221
- | ------------------------------------------ | -------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |
222
- | HTTP 400 on the second turn of a tool loop | `reasoning_content` missing in history (thinking on) | **Use the extension** (it caches reasoning per tool-call ID). Or: add `thinking: { type: "disabled" }` to `requestBody`, or use the proxy (`npm run proxy:mimo`) |
223
- | Vision request returns an error | Used `mimo-v2.5-pro` (text-only) | Use `mimo-v2.5` for vision |
224
- | Custom `tool_choice` ignored | MiMo only honors `"auto"` | Stick to `auto` |
225
- | 401 Unauthorized | Wrong key, or Token Plan URL used with pay-as-you-go key | Match key prefix (`sk-` vs `tp-`) to the endpoint |
226
- | 429 rate-limited | Concurrent sessions exceeded 100 RPM / 10M TPM | Reduce concurrent agent sessions |
249
+ | Symptom | Likely cause | Fix |
250
+ | ------------------------------------------ | -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------- |
251
+ | HTTP 400 on the second turn of a tool loop | `reasoning_content` missing in history (thinking on) | Use the proxy (`npm run proxy:mimo`), or add `thinking: { type: "disabled" }` to `requestBody`; an extension with a reasoning cache can keep thinking enabled |
252
+ | Vision request returns an error | Used the legacy text-only `mimo-v2.5-pro` | Use `mimo-v2.6-pro`, `mimo-v2.6-flash`, `mimo-v2.6-pro-ultraspeed`, or legacy `mimo-v2.5` for image input |
253
+ | Custom `tool_choice` ignored | MiMo only honors `"auto"` | Stick to `auto` |
254
+ | 401 Unauthorized | Wrong key, or Token Plan URL used with pay-as-you-go key | Match key prefix (`sk-` vs `tp-`) to the endpoint |
255
+ | 429 rate-limited | Concurrent sessions exceeded 100 RPM / 10M TPM | Reduce concurrent agent sessions |
227
256
 
228
257
  ## Pricing
229
258
 
230
259
  For the cross-provider comparison, see [docs/pricing.md](../pricing.md). Overseas (international) pay-as-you-go rates:
231
260
 
232
- | Model | Input (Cache Hit) | Input (Cache Miss) | Output |
233
- | --------------- | ----------------- | ------------------ | ---------- |
234
- | `mimo-v2.5-pro` | $0.20 / 1M | $1.00 / 1M | $3.00 / 1M |
235
- | `mimo-v2.5` | $0.08 / 1M | $0.40 / 1M | $2.00 / 1M |
261
+ | Model | Input (Cache Hit) | Input (Cache Miss) | Output |
262
+ | -------------------------- | ----------------- | ------------------ | ---------- |
263
+ | `mimo-v2.6-pro` | $0.0036 / 1M | $0.435 / 1M | $0.87 / 1M |
264
+ | `mimo-v2.6-flash` | $0.0028 / 1M | $0.14 / 1M | $0.28 / 1M |
265
+ | `mimo-v2.6-pro-ultraspeed` | $0.036 / 1M | $4.35 / 1M | $8.70 / 1M |
266
+ | `mimo-v2.5-pro` _(legacy)_ | $0.0036 / 1M | $0.435 / 1M | $0.87 / 1M |
267
+ | `mimo-v2.5` _(legacy)_ | $0.0028 / 1M | $0.14 / 1M | $0.28 / 1M |
236
268
 
237
269
  > Cache writing is currently free of charge (limited-time offer). MiMo also offers a Token Plan subscription with discounted rates and a free cache-writing promotion.
@@ -38,7 +38,7 @@
38
38
 
39
39
  1. **Edit `chatLanguageModels.json`** — add the MiniMax block below.
40
40
  2. **Set your `MINIMAX_API_KEY`** via Command Palette → **Chat: Manage Language Models**.
41
- 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)
41
+ 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)
42
42
  4. **Restart VS Code** and pick "MiniMax M3" in the chat picker.
43
43
 
44
44
  ## Setup
@@ -95,14 +95,14 @@ Set the API key through **Chat: Manage Language Models**, then verify the proxy
95
95
  1. **Start the proxy:** `npm run proxy:qwen` (or `npx copilot-custom-endpoint qwen`).
96
96
  2. **Use the proxy-path JSON snippet** below.
97
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 V2.5). [Why?](../../README.md#4-configure-the-utility-small-model)
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
99
  5. **Restart VS Code.** Reasoning will be visible in plain chat and suppressed on tool turns.
100
100
 
101
101
  ### Direct (no proxy)
102
102
 
103
103
  1. **Use the direct-path JSON snippet** below.
104
104
  2. **Set your `DASHSCOPE_API_KEY`** via Command Palette → **Chat: Manage Language Models**.
105
- 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)
105
+ 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
106
  4. **Restart VS Code** and pick "Qwen 3.8 Max".
107
107
 
108
108
  ## Setup
package/docs/pricing.md CHANGED
@@ -1,8 +1,8 @@
1
1
  # Pricing
2
2
 
3
- > Release history is kept in the reference notes below. Use the current table and September 16 refresh note for present scores and estimates. The September 11 roster cleanup removes two retired models.
3
+ > Release history is kept in the reference notes below. Use the current table and September 22 refresh note for present scores and estimates. The September 11 roster cleanup removes two retired models.
4
4
 
5
- > **Latest refresh (September 16, 2026):** OpenRouter's live benchmark card puts the unversioned Qwen3.8 Max entry at **#2 with 53.4**. The public model API no longer exposes that unversioned ID and canonicalizes it to 0902; the exact `qwen/qwen3.8-max-0902` metadata row now reports **45.4**. The table preserves both values as separate records rather than silently merging them. Qwen Cloud's current PAYG API rates remain **$2 / $0.25 implicit cache / $6** for Qwen3.8 Max. DeepSeek now serves V4.1 Flash as `deepseek-flash` at peak rates of **$0.30 / $0.006 cache hit / $1.20**; the legacy V4 Flash alias is retired. Anthropic kept Sonnet 5 at **$2 / $0.20 / $10**, and OpenAI's Sol rate is **$4 / $0.40 / $20** through at least November 21. GLM 5.3 Flash's 50% launch promotion ended September 9, so list rates are now the applicable baseline.
5
+ > **Latest refresh (September 22, 2026):** OpenRouter's current metadata uses Artificial Analysis v4.3.2 composites. MiMo V2.6 Pro is **46.3**, Grok 4.7 is **46.4**, and the current values for existing rows are refreshed below. Xiaomi released the V2.6 Pro, Flash, and Pro UltraSpeed models on September 22 and kept the V2.5 prices; V2.5 Pro and V2.5 are scheduled for deprecation on October 21. 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. Older numbered notes retain launch-era or earlier methodology scores where relevant; the current table is authoritative for present comparisons.
6
6
 
7
7
  > **⏰ June 1, 2026 — GitHub Copilot switched to usage-based billing (AI Credits) today.**
8
8
  >
@@ -24,31 +24,35 @@ All prices below are in **USD per 1M tokens** (non-cached). To convert to AI cre
24
24
 
25
25
  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.
26
26
 
27
- | Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
28
- | ------------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
29
- | **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.9** | $0.15 | $0.03 | $0.50 | ~$0.13 | 1M |
30
- | **MiMo V2.5** | Xiaomi | **~$0.0045** | **22.3** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
31
- | **GPT-5.6 Luna** | OpenAI | **~$0.0059** | **37.5** | $0.20 | $0.02 | $1.20 | ~$0.22 | 1M |
32
- | **DeepSeek V4.1 Flash** | DeepSeek | **~$0.0068** | **39.5** | $0.30 | $0.006 | $1.20 | ~$0.27 | 1M |
33
- | **MiniMax M3** | MiniMax | **~$0.0091** | **29.6** | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | ~$0.27 | 1M |
34
- | **MiMo V2.5 Pro** | Xiaomi | **~$0.0114** | **26.4** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
35
- | **MiniMax M3 Priority** | MiniMax | **~$0.0139** | **29.6** | $0.90 (≤512K) / $1.80 (>512K) | $0.18 (≤512K) / $0.36 (>512K) | $3.60 (≤512K) / $7.20 (>512K) | ~$0.41 | 1M |
36
- | **Gemini 3.8 Flash** | Google | **~$0.0182** | **41.2** | $0.75 | $0.075 | $3.75 | ~$0.75 | 1M |
37
- | **GLM 5.3** | Z.ai | **~$0.0254** | **44.9** | $1.40 | $0.26 | $4.40 | ~$1.14 | 1M |
38
- | **DeepSeek V4 Pro 0813** | DeepSeek | **~$0.0292** | **36.3** | $1.32 | $0.044 | $3.96 | ~$1.06 | 1M |
39
- | **Qwen 3.8 Max (0803)²⁵** | DashScope | **~$0.0300** | **53.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
40
- | **Qwen 3.8 Max (0902)²⁶** | DashScope | **~$0.0352** | **45.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
41
- | **Grok 4.6** | xAI | **~$0.0360** | **44.4** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
42
- | **GPT-5.6 Terra** | OpenAI | **~$0.0520** | **42.3** | $2.00 | $0.20 | $12.00 | ~$2.20 | 1M |
43
- | **Claude Sonnet 5** | Anthropic | **~$0.0521** | **38.4** | $2.00 | $0.20 | $10.00 | ~$2.00 | 1M |
44
- | **Kimi K3** | Moonshot | **~$0.0685** | **43.8** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
45
- | **GPT-5.6 Sol** | OpenAI | **~$0.0849** | **47.1** | $4.00 | $0.40 | $20.00 | ~$4.00 | 1M |
46
- | **Claude Opus 5** | Anthropic | **~$0.0986** | **50.7** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
47
- | **Claude Fable 5.1** | Anthropic | **~$0.1873** | **53.4** | $10.00 | $0.25 | $50.00 | ~$10.00 | 1M |
48
- | **GPT-6 Astra** | OpenAI | **~$0.1894** | **52.8** | $10.00 | $1.00 | $50.00 | ~$10.00 | 1M |
49
- | **Claude Fable 5** | Anthropic | **~$0.2012** | **49.7** | $10.00 | $1.00 | $50.00 | ~$10.00 | 1M |
50
-
51
- > **Reference notes:** The details below preserve release and pricing context. Use the current table and September 10 refresh note for present values.
27
+ | Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
28
+ | ------------------------------ | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
29
+ | **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.8** | $0.15 | $0.03 | $0.50 | ~$0.13 | 1M |
30
+ | **GPT-5.6 Luna** | OpenAI | **~$0.0059** | **37.3** | $0.20 | $0.02 | $1.20 | ~$0.22 | 1M |
31
+ | **MiMo V2.6 Pro**²⁷ | Xiaomi | **~$0.0066** | **46.3** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
32
+ | **DeepSeek V4.1 Flash** | DeepSeek | **~$0.0068** | **39.5** | $0.30 | $0.006 | $1.20 | ~$0.27 | 1M |
33
+ | **MiniMax M3** | MiniMax | **~$0.0093** | **29.2** | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | ~$0.27 | 1M |
34
+ | **MiMo V2.5 Pro** | Xiaomi | **~$0.0115** | **26.0** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
35
+ | **MiniMax M3 Priority** | MiniMax | **~$0.0139** | **29.2** | $0.90 (≤512K) / $1.80 (>512K) | $0.18 (≤512K) / $0.36 (>512K) | $3.60 (≤512K) / $7.20 (>512K) | ~$0.41 | 1M |
36
+ | **Gemini 3.8 Flash** | Google | **~$0.0183** | **40.9** | $0.75 | $0.075 | $3.75 | ~$0.75 | 1M |
37
+ | **GLM 5.3** | Z.ai | **~$0.0254** | **44.8** | $1.40 | $0.26 | $4.40 | ~$1.14 | 1M |
38
+ | **DeepSeek V4 Pro 0813** | DeepSeek | **~$0.0294** | **36.0** | $1.32 | $0.044 | $3.96 | ~$1.06 | 1M |
39
+ | **Qwen 3.8 Max (0803)²⁵** | DashScope | **~$0.0300** | **53.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
40
+ | **Grok 4.7²⁸** | xAI | **~$0.0345** | **46.4** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
41
+ | **Qwen 3.8 Max (0902)²⁶** | DashScope | **~$0.0352** | **45.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
42
+ | **Grok 4.6** | xAI | **~$0.0361** | **44.3** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
43
+ | **GPT-5.6 Terra** | OpenAI | **~$0.0523** | **42.1** | $2.00 | $0.20 | $12.00 | ~$2.20 | 1M |
44
+ | **Claude Sonnet 5** | Anthropic | **~$0.0524** | **38.2** | $2.00 | $0.20 | $10.00 | ~$2.00 | 1M |
45
+ | **Kimi K3** | Moonshot | **~$0.0688** | **43.6** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
46
+ | **GPT-5.6 Sol** | OpenAI | **~$0.0851** | **47.0** | $4.00 | $0.40 | $20.00 | ~$4.00 | 1M |
47
+ | **Claude Opus 5** | Anthropic | **~$0.0984** | **50.8** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
48
+ | **Claude Fable 5.1** | Anthropic | **~$0.1873** | **53.4** | $10.00 | $0.25 | $50.00 | ~$10.00 | 1M |
49
+ | **GPT-6 Astra** | OpenAI | **~$0.1898** | **52.7** | $10.00 | $1.00 | $50.00 | ~$10.00 | 1M |
50
+ | **Claude Fable 5** | Anthropic | **~$0.2016** | **49.6** | $10.00 | $1.00 | $50.00 | ~$10.00 | 1M |
51
+ | **MiMo V2.6 Flash**²⁷ | Xiaomi | — | — | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
52
+ | **MiMo V2.5** | Xiaomi | — | — | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
53
+ | **MiMo V2.6 Pro UltraSpeed**²⁷ | Xiaomi | — | — | $4.35 | $0.036 | $8.70 | ~$3.05 | 1M |
54
+
55
+ > **Reference notes:** The details below preserve release and pricing context. Use the current table and September 22 refresh note for present values.
52
56
 
53
57
  ⁵ **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 (list prices shown above; effective rates after the standing 50% off are $0.45/$1.80/$0.09 ≤512K and $0.90/$3.60/$0.18 >512K), 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. To enable it on the custom-endpoint entry, add `"service_tier": "priority"` to the `requestBody` of the single `MiniMax-M3` block (and remove it to go back to Standard). See [docs/models/minimax.md](models/minimax.md#4-m3-priority-tier-optional) and [docs/research/minimax-m3-priority.md](research/minimax-m3-priority.md) for the full breakdown.
54
58
 
@@ -82,6 +86,10 @@ All models are listed together below, sorted by Cost per intelligence ascending
82
86
 
83
87
  ²⁶ **Qwen 3.8 Max (0902)** is a separate OpenRouter snapshot, [`qwen/qwen3.8-max-0902`](https://openrouter.ai/qwen/qwen3.8-max-0902), released September 4, 2026. The current public model API reports an AA Intelligence Index of **45.4** for this exact ID. It has the same published **$2.00 / $0.25 implicit cache / $6.00** rates, 1M context, 131K maximum output, and text/image/video input. The OpenRouter slug is not automatically a valid DashScope model ID; see [the Qwen setup guide](models/qwen.md) before changing the upstream URL.
84
88
 
89
+ ²⁷ **MiMo V2.6** was released by Xiaomi on **September 22, 2026** as three API models: `mimo-v2.6-pro`, `mimo-v2.6-flash`, and `mimo-v2.6-pro-ultraspeed`. All support text, image, video, and audio input, 1M context, and 131K maximum output. Overseas PAYG pricing is Pro **$0.435 / $0.0036 / $0.87**, Flash **$0.14 / $0.0028 / $0.28**, and UltraSpeed **$4.35 / $0.036 / $8.70** per 1M input/cache-hit/output. OpenRouter's current metadata reports AA Intelligence **46.3** for Pro and no composite yet for Flash or UltraSpeed. MiMo V2.5 and V2.5 Pro keep their existing prices but are scheduled for deprecation at 10:00 Beijing time on October 21, 2026. See Xiaomi's [V2.6 release](https://mimo.mi.com/docs/news/latest/v2-6), [model list](https://mimo.mi.com/docs/en-US/quick-start/summary/model), and [pricing](https://mimo.mi.com/docs/en-US/pricing).
90
+
91
+ ²⁸ **Grok 4.7** was released by xAI on **September 21, 2026**. It supports text, image, and file input, a 500K context window, and reasoning effort levels from low through xhigh. Short-context API pricing is **$2.00 / $0.50 / $6.00** per 1M input/cache-hit/output; prompts at or above 200K use **$4.00 / $1.00 / $12.00**. OpenRouter's current metadata reports AA Intelligence **46.4**. xAI reports CursorBench 4.0 **46.3%**, DeepSWE v1.1 **71.0%** at high effort, EEBench **64.0%**, AA Briefcase **1,657**, and Terminal-Bench 4.0 **38.0%**. See the [xAI announcement](https://x.ai/news/grok-4-7), [xAI model pricing](https://docs.x.ai/docs/models), and [AA model page](https://artificialanalysis.ai/models/grok-4-7).
92
+
85
93
  Cost per intelligence = estimated session cost ÷ Intelligence Index score. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
86
94
 
87
95
  > **Notes:**
@@ -101,7 +109,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
101
109
 
102
110
  > **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.
103
111
 
104
- > Prices last verified: September 16, 2026. Always check the official pages for the latest rates:
112
+ > Prices last verified: September 22, 2026. Always check the official pages for the latest rates:
105
113
  >
106
114
  > - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
107
115
  > - [OpenAI pricing](https://openai.com/api/pricing/)
@@ -0,0 +1,80 @@
1
+ function summarizePayload(payload, hasTools, rewriteInfo) {
2
+ const messages = Array.isArray(payload.messages) ? payload.messages : []
3
+ const tools = Array.isArray(payload.tools) ? payload.tools : []
4
+
5
+ return {
6
+ model: payload.model,
7
+ stream: payload.stream,
8
+ hasTools,
9
+ toolCount: tools.length,
10
+ toolChoice: payload.tool_choice,
11
+ ...rewriteInfo,
12
+ maxTokens:
13
+ payload.max_tokens ??
14
+ payload.max_completion_tokens ??
15
+ payload.max_output_tokens,
16
+ messageCount: messages.length,
17
+ messageRoles: messages.map((message) => message?.role).slice(0, 16),
18
+ topLevelKeys: Object.keys(payload).sort()
19
+ }
20
+ }
21
+
22
+ export function hasMissingReasoningContent(messages) {
23
+ return messages.some((message) => {
24
+ if (
25
+ message?.role !== 'assistant' ||
26
+ !Array.isArray(message.tool_calls) ||
27
+ message.tool_calls.length === 0
28
+ ) {
29
+ return false
30
+ }
31
+
32
+ return (
33
+ typeof message.reasoning_content !== 'string' ||
34
+ message.reasoning_content.trim().length === 0
35
+ )
36
+ })
37
+ }
38
+
39
+ export function rewriteMiMo(payload, { disableThinkingWithTools = true } = {}) {
40
+ const messages = Array.isArray(payload.messages) ? payload.messages : []
41
+ const hasToolRole = messages.some((message) => message?.role === 'tool')
42
+ const hasToolsArray = Array.isArray(payload.tools) && payload.tools.length > 0
43
+ const toolChoice = payload.tool_choice
44
+ const hasActiveToolCall =
45
+ hasToolRole ||
46
+ hasToolsArray ||
47
+ (toolChoice !== undefined && toolChoice !== 'none' && toolChoice !== null)
48
+ const hasTools = hasActiveToolCall
49
+ const model = String(payload.model ?? '').toLowerCase()
50
+ const isV26 = model.startsWith('mimo-v2.6')
51
+ const incomingThinkingType = payload?.thinking?.type
52
+ const missingReasoningContent = isV26 && hasMissingReasoningContent(messages)
53
+ const shouldDisableThinking =
54
+ disableThinkingWithTools && hasTools && (!isV26 || missingReasoningContent)
55
+
56
+ if (shouldDisableThinking) {
57
+ payload.thinking = { type: 'disabled' }
58
+ } else if (!hasTools) {
59
+ delete payload.thinking
60
+ }
61
+
62
+ const rewrittenThinkingType = payload?.thinking?.type
63
+ const thinkingAction = shouldDisableThinking
64
+ ? '"disabled"'
65
+ : hasTools
66
+ ? '<preserved>'
67
+ : '<deleted>'
68
+
69
+ return {
70
+ summary: summarizePayload(payload, hasTools, {
71
+ isV26,
72
+ missingReasoningContent,
73
+ incomingThinkingType,
74
+ rewrittenThinkingType
75
+ }),
76
+ consoleMsg: `[${hasTools ? 'tools' : 'chat'}] thinking.type=${String(
77
+ incomingThinkingType
78
+ )} -> ${thinkingAction}, model=${payload.model ?? '?'}`
79
+ }
80
+ }
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "copilot-custom-endpoint",
3
- "version": "3.1.1",
4
- "description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2, Qwen 3.x & MiMo V2.5",
3
+ "version": "3.2.0",
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",
7
7
  "bin": {
@@ -2,10 +2,11 @@
2
2
  import 'dotenv/config'
3
3
  import { fileURLToPath } from 'node:url'
4
4
  import { createProxy } from '../lib/create-proxy.mjs'
5
+ import { rewriteMiMo } from '../lib/mimo-rewrite.mjs'
5
6
 
6
7
  /**
7
8
  * Supported model scope for this proxy:
8
- * - Validated with `mimo-v2.5-pro`, `mimo-v2.5`, and `mimo-v2-flash`.
9
+ * - Validated with the MiMo V2.6 and V2.5 chat model IDs.
9
10
  * - Expected to work for any MiMo model that supports the `thinking` object
10
11
  * with a `type` field on the OpenAI-compatible surface.
11
12
  * - Not intended for non-MiMo providers, because the rewrite assumes
@@ -28,17 +29,19 @@ const logPath = process.env.MIMO_PROXY_LOG ?? defaultLogPath
28
29
  if (process.argv.includes('--help')) {
29
30
  console.log(`MiMo proxy
30
31
 
31
- Starts a local HTTP proxy that conditionally injects thinking: { type: "disabled" }
32
- when the request includes a tools array, letting MiMo models show reasoning in
33
- plain chat while keeping tool loops stable.
32
+ Starts a local HTTP proxy that preserves MiMo V2.6 thinking when the request
33
+ history includes reasoning_content, and falls back to thinking: { type: "disabled" }
34
+ when a tool loop has missing reasoning history. Legacy MiMo models use the
35
+ disabled-thinking fallback for tool-enabled requests.
34
36
 
35
37
  Environment variables:
36
38
  MIMO_PROXY_PORT Local listen port. Default: 3459 (falls back to PORT)
37
39
  MIMO_UPSTREAM_URL Upstream MiMo chat-completions URL.
38
40
  Default: https://api.xiaomimimo.com/v1/chat/completions
39
41
  MIMO_PROXY_DISABLE_THINKING_WITH_TOOLS
40
- Inject thinking: { type: "disabled" } when tools are present.
41
- Default: 1
42
+ Enable the tool-loop fallback that injects thinking:
43
+ { type: "disabled" } for legacy models or incomplete
44
+ V2.6 reasoning history. Default: 1
42
45
  MIMO_PROXY_LOG Path to the redacted NDJSON log file.
43
46
 
44
47
  Suggested VS Code model URL:
@@ -47,66 +50,6 @@ Suggested VS Code model URL:
47
50
  process.exit(0)
48
51
  }
49
52
 
50
- // ---- Provider-specific rewrite logic ----
51
-
52
- function summarizePayload(payload, hasTools, rewriteInfo) {
53
- const messages = Array.isArray(payload.messages) ? payload.messages : []
54
- const tools = Array.isArray(payload.tools) ? payload.tools : []
55
-
56
- return {
57
- model: payload.model,
58
- stream: payload.stream,
59
- hasTools,
60
- toolCount: tools.length,
61
- toolChoice: payload.tool_choice,
62
- ...rewriteInfo,
63
- maxTokens:
64
- payload.max_tokens ??
65
- payload.max_completion_tokens ??
66
- payload.max_output_tokens,
67
- messageCount: messages.length,
68
- messageRoles: messages.map((message) => message?.role).slice(0, 16),
69
- topLevelKeys: Object.keys(payload).sort()
70
- }
71
- }
72
-
73
- function rewriteMiMo(payload) {
74
- // Determine if a tool is actually being invoked:
75
- // - tool_choice is set and not "none"
76
- // - OR there is a "tool" role message in the conversation
77
- const messages = Array.isArray(payload.messages) ? payload.messages : []
78
- const hasToolRole = messages.some((message) => message?.role === 'tool')
79
- const toolChoice = payload.tool_choice
80
- const hasActiveToolCall =
81
- hasToolRole ||
82
- (toolChoice !== undefined && toolChoice !== 'none' && toolChoice !== null)
83
- const hasTools = hasActiveToolCall
84
- const incomingThinkingType = payload?.thinking?.type
85
-
86
- if (disableThinkingWithTools && hasTools) {
87
- // Tool-enabled request: suppress thinking to avoid reasoning_content issues
88
- payload.thinking = { type: 'disabled' }
89
- } else {
90
- // Plain chat: remove thinking so the model uses its default (enabled for V2.5 models)
91
- delete payload.thinking
92
- }
93
-
94
- const rewrittenThinkingType =
95
- disableThinkingWithTools && hasTools ? 'disabled' : undefined
96
-
97
- const summary = summarizePayload(payload, hasTools, {
98
- incomingThinkingType,
99
- rewrittenThinkingType
100
- })
101
-
102
- const modeTag = hasTools ? '[tools]' : '[chat]'
103
- const consoleMsg = `${modeTag} thinking.type=${String(incomingThinkingType)} -> ${
104
- hasTools && disableThinkingWithTools ? '"disabled"' : '<deleted>'
105
- }, model=${payload.model ?? '?'}`
106
-
107
- return { summary, consoleMsg }
108
- }
109
-
110
53
  // ---- Create and start ----
111
54
 
112
55
  const { start } = createProxy({
@@ -114,8 +57,12 @@ const { start } = createProxy({
114
57
  port,
115
58
  logPath,
116
59
  label: 'mimo-proxy',
117
- healthCheckExtras: { disableThinkingWithTools },
118
- rewriteRequest: rewriteMiMo,
60
+ healthCheckExtras: {
61
+ disableThinkingWithTools,
62
+ preserveV26ThinkingWithReasoningContent: true
63
+ },
64
+ rewriteRequest: (payload) =>
65
+ rewriteMiMo(payload, { disableThinkingWithTools }),
119
66
  startupMessages: (_port, _upstreamUrl) => [
120
67
  `[mimo-proxy] listening on http://127.0.0.1:${_port}/v1/chat/completions`,
121
68
  `[mimo-proxy] forwarding to ${_upstreamUrl}`,