copilot-custom-endpoint 1.7.2 → 1.7.4
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 +3 -0
- package/docs/models/glm.md +7 -7
- package/docs/models/kimi.md +27 -16
- package/docs/models/mimo.md +25 -7
- package/docs/models/minimax.md +29 -24
- package/docs/models/qwen.md +53 -29
- package/docs/pricing.md +5 -2
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -113,6 +113,7 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
|
|
|
113
113
|
| **Qwen 3.7 Max** | DashScope | **~$0.043** | **46.0** | ~$2.00 | ❌ | 1M |
|
|
114
114
|
| **Gemini 3.1 Pro** | Google | **~$0.047** | **46.5** | ~$2.20 | ✅ | 1M |
|
|
115
115
|
| **GPT-5.4** | OpenAI | **~$0.054** | **51.4** | ~$2.75 | ✅ | 1M |
|
|
116
|
+
| **Claude Sonnet 5** ⁵ | Anthropic | **~$0.057** | **53.0** | ~$3.00 | ✅ | 1M |
|
|
116
117
|
| **Claude Sonnet 4.6** | Anthropic | **~$0.064** | **47.2** | ~$3.00 | ✅ | 1M |
|
|
117
118
|
| **Claude Opus 4.8** | Anthropic | **~$0.090** | **55.7** | ~$5.00 | ✅ | 1M |
|
|
118
119
|
| **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | ~$5.00 | ✅ | 1M |
|
|
@@ -130,6 +131,8 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
|
|
|
130
131
|
|
|
131
132
|
⁴ **MiniMax M3 Priority** is the same `MiniMax-M3` weights invoked with `"service_tier": "priority"` in the request body — **not a separate model**. Costs **1.5× Standard** (effective post-50%-off rates: $0.45 / $1.80 / $0.09 per 1M for input/output/cached ≤512K) in exchange for **priority admission** (faster responses, fewer failures during MiniMax peak hours). Capabilities, context window, vision, tools, rate limits, and thinking modes are identical to Standard. See [docs/research/minimax-m3-priority.md](docs/research/minimax-m3-priority.md).
|
|
132
133
|
|
|
134
|
+
⁵ **Claude Sonnet 5** has introductory pricing of **$2.00 / $10.00** per MTok (input/output) through **August 31, 2026**. Standard pricing of $3.00 / $15.00 shown above takes effect September 1, 2026. Released June 30, 2026 — Arena rankings pending. AA Intelligence Index score of **53.0** confirmed by [Artificial Analysis](https://artificialanalysis.ai/models/claude-sonnet-5).
|
|
135
|
+
|
|
133
136
|
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).
|
|
134
137
|
|
|
135
138
|
> **👤 Personal picks** —
|
package/docs/models/glm.md
CHANGED
|
@@ -20,8 +20,8 @@
|
|
|
20
20
|
| Billing | **Pay-as-You-Go** (PaaS API) — Coding Plan subscription exists but is **not usable** from VS Code custom endpoints |
|
|
21
21
|
| Vision | ✅ Yes (`glm-5v-turbo` only) |
|
|
22
22
|
| Tool calling | ✅ Yes (native multimodal tool use on `glm-5v-turbo`) |
|
|
23
|
-
| Context
|
|
24
|
-
| Max output
|
|
23
|
+
| Context | 1M (`glm-5.2` Solid Lossless Context) |
|
|
24
|
+
| Max output | 131072 |
|
|
25
25
|
| Required `requestBody` | `thinking: { type: "enabled" }` (recommended) |
|
|
26
26
|
| Endpoint (intl) | `https://api.z.ai/api/paas/v4/chat/completions` |
|
|
27
27
|
| Endpoint (China) | `https://open.bigmodel.cn/api/paas/v4/chat/completions` |
|
|
@@ -29,11 +29,11 @@
|
|
|
29
29
|
|
|
30
30
|
### Models
|
|
31
31
|
|
|
32
|
-
| Model | Vision | Context | Max output |
|
|
33
|
-
| -------------- | ------ | ------- | ---------- |
|
|
34
|
-
| `glm-5.2` | ❌ | 1M | 131072 |
|
|
35
|
-
| `glm-5.1` | ❌ | 200K | 131072 | `enabled`
|
|
36
|
-
| `glm-5v-turbo` | ✅ | 200K | 131072 | `enabled`
|
|
32
|
+
| Model | Vision | Context | Max output | Notes |
|
|
33
|
+
| -------------- | ------ | ------- | ---------- | ---------------------------------------------------------------------------------------------------------------- |
|
|
34
|
+
| `glm-5.2` | ❌ | 1M | 131072 | New Flagship — "Opus-level" long-context engineering & agentic coding; thinking `enabled` ($1.40 / $4.40 per 1M) |
|
|
35
|
+
| `glm-5.1` | ❌ | 200K | 131072 | Previous flagship — long-horizon / 8h autonomous work; thinking `enabled` ($1.40 / $4.40 per 1M) |
|
|
36
|
+
| `glm-5v-turbo` | ✅ | 200K | 131072 | Multimodal **coding** model — vision-based agentic coding; thinking `enabled` ($1.20 / $4.00 per 1M) |
|
|
37
37
|
|
|
38
38
|
> Other GLM models (`glm-5`, `glm-5-turbo`, `glm-4.5-air`, etc.) are callable on the same endpoint but are intentionally **not** added to the default `chatLanguageModels.json` block below. Add them in the same shape if you need them. Note: `glm-4.6v-flashx` was previously in the default block but has been **removed** because live testing showed it is not reliable for tool calling.
|
|
39
39
|
|
package/docs/models/kimi.md
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
# Kimi — VS Code Custom Endpoint Setup Guide
|
|
1
|
+
# Kimi (Moonshot) — VS Code Custom Endpoint Setup Guide
|
|
2
2
|
|
|
3
3
|
> **TL;DR:** Kimi models require the local proxy. The K2 family locks `temperature: 1` and `top_p: 0.95`. K2.6 needs `thinking: { type: "disabled" }` on tool turns; **K2.7 Code is always-thinking and rejects `thinking: disabled`**, so the proxy detects `kimi-k2.7*` and skips that rewrite while keeping sampling enforcement. Direct VS Code → Moonshot is not viable.
|
|
4
4
|
>
|
|
@@ -6,21 +6,24 @@
|
|
|
6
6
|
|
|
7
7
|
## At a Glance
|
|
8
8
|
|
|
9
|
-
| Field
|
|
10
|
-
|
|
|
11
|
-
| Mode
|
|
12
|
-
| Billing
|
|
13
|
-
| Vision
|
|
14
|
-
| Tool calling
|
|
15
|
-
|
|
|
16
|
-
|
|
|
9
|
+
| Field | Value |
|
|
10
|
+
| -------------- | --------------------------------------------- |
|
|
11
|
+
| Mode | **Proxy required** (local on `:3457`) |
|
|
12
|
+
| Billing | **Pay-as-You-Go only** — no subscription |
|
|
13
|
+
| Vision | ✅ Yes |
|
|
14
|
+
| Tool calling | ✅ Yes |
|
|
15
|
+
| Context | _see Models table_ |
|
|
16
|
+
| Max output | _see Models table_ |
|
|
17
|
+
| Endpoint | `https://api.moonshot.ai/v1/chat/completions` |
|
|
18
|
+
| Proxy endpoint | `http://127.0.0.1:3457/v1/chat/completions` |
|
|
19
|
+
| Auth | `Authorization: Bearer $KIMI_API_KEY` |
|
|
17
20
|
|
|
18
21
|
### Models
|
|
19
22
|
|
|
20
|
-
| Model
|
|
21
|
-
| ---------------- | ------- | ---------- | --------------------------------------------------------------------------------- |
|
|
22
|
-
| `kimi-k2.6` | 262K | 32768 | Proxy forces `thinking: { type: "disabled" }` on tool turns |
|
|
23
|
-
| `kimi-k2.7-code` | 262K | 4096 | Always-thinking; rejects `thinking: disabled`. Keep `maxOutputTokens` low (4096). |
|
|
23
|
+
| Model | Vision | Context | Max output | Notes |
|
|
24
|
+
| ---------------- | ------ | ------- | ---------- | --------------------------------------------------------------------------------- |
|
|
25
|
+
| `kimi-k2.6` | ✅ Yes | 262K | 32768 | Proxy forces `thinking: { type: "disabled" }` on tool turns |
|
|
26
|
+
| `kimi-k2.7-code` | ✅ Yes | 262K | 4096 | Always-thinking; rejects `thinking: disabled`. Keep `maxOutputTokens` low (4096). |
|
|
24
27
|
|
|
25
28
|
> Deprecated K2 ids (`kimi-k2-0905-preview`, `kimi-k2-turbo-preview`, `kimi-k2-thinking`, etc.) were discontinued May 25, 2026 — use K2.6 or K2.7.
|
|
26
29
|
|
|
@@ -87,7 +90,9 @@ Kimi is **Pay-as-You-Go only** — no subscription. A single Open Platform API k
|
|
|
87
90
|
|
|
88
91
|
> VS Code replaces `"apiKey": ""` with a `${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.
|
|
89
92
|
|
|
90
|
-
|
|
93
|
+
## Local Proxy
|
|
94
|
+
|
|
95
|
+
The `proxy/kimi-proxy.mjs` is **required** for Kimi — K2-family sampling constraints and tool-turn thinking behaviour cannot be satisfied by VS Code's direct path. See [Quick Start](#quick-start) for the launch command.
|
|
91
96
|
|
|
92
97
|
| Setting | Value |
|
|
93
98
|
| ------------ | ----------------------------------------------------- |
|
|
@@ -97,7 +102,7 @@ Kimi is **Pay-as-You-Go only** — no subscription. A single Open Platform API k
|
|
|
97
102
|
| Start | `npm run proxy:kimi` (or `node proxy/kimi-proxy.mjs`) |
|
|
98
103
|
| Help | `node proxy/kimi-proxy.mjs --help` |
|
|
99
104
|
|
|
100
|
-
|
|
105
|
+
### Environment variables
|
|
101
106
|
|
|
102
107
|
Set in `.env` at the repo root (the proxy `import 'dotenv/config'` automatically).
|
|
103
108
|
|
|
@@ -111,7 +116,7 @@ Set in `.env` at the repo root (the proxy `import 'dotenv/config'` automatically
|
|
|
111
116
|
| `KIMI_PROXY_DISABLE_THINKING_WITH_TOOLS` | `1` | Force `thinking={"type":"disabled"}` when tools present |
|
|
112
117
|
| `KIMI_PROXY_LOG` | `debug_log/kimi-proxy.ndjson` | Redacted NDJSON log path |
|
|
113
118
|
|
|
114
|
-
|
|
119
|
+
### What the proxy does
|
|
115
120
|
|
|
116
121
|
- Forwards your `Authorization` header upstream.
|
|
117
122
|
- Rewrites plain-chat requests to `temperature: 1`, `top_p: 0.95`.
|
|
@@ -120,6 +125,12 @@ Set in `.env` at the repo root (the proxy `import 'dotenv/config'` automatically
|
|
|
120
125
|
- Preserves streaming responses (SSE).
|
|
121
126
|
- Writes redacted request summaries to `debug_log/kimi-proxy.ndjson`.
|
|
122
127
|
|
|
128
|
+
## Notes
|
|
129
|
+
|
|
130
|
+
- **K2.7 Code** is always-thinking. `max_tokens` and `maxOutputTokens` are intentionally conservative at **4096** — reasoning tokens inflate response size and values above 24K triggered VS Code's "Response too long" error in agent mode.
|
|
131
|
+
- **K2 platform rebranding:** the Kimi Platform (formerly Moonshot) rebranded to `platform.kimi.ai` in 2026 — `api.moonshot.ai` still resolves and the proxy targets it unchanged.
|
|
132
|
+
- **`tool_choice` only supports `auto`** — don't override it (VS Code's default is `auto`).
|
|
133
|
+
|
|
123
134
|
## Troubleshooting
|
|
124
135
|
|
|
125
136
|
| Symptom | Likely cause | Fix |
|
package/docs/models/mimo.md
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
# Xiaomi MiMo — VS Code
|
|
1
|
+
# Xiaomi MiMo — VS Code Custom Endpoint Setup Guide
|
|
2
2
|
|
|
3
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.
|
|
4
4
|
|
|
@@ -8,19 +8,23 @@
|
|
|
8
8
|
| ---------------------- | -------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
9
9
|
| **Recommended method** | **[Xiaomi MiMo for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot)** VS Code extension |
|
|
10
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`) |
|
|
11
13
|
| Vision | ✅ Yes (`mimo-v2.5` only) |
|
|
12
14
|
| Tool calling | ✅ Yes (with thinking disabled, OR thinking enabled via the extension's reasoning cache) |
|
|
13
15
|
| Context | 917K (extension) / 1M (custom endpoint) |
|
|
14
16
|
| Max output | 131072 (V2.5 Pro) / 32768 (V2.5) |
|
|
15
|
-
|
|
|
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` |
|
|
16
20
|
|
|
17
21
|
### Models
|
|
18
22
|
|
|
19
|
-
| Model | Vision | Context |
|
|
20
|
-
| -------------------------- | ------ | ------- | --------------------------------------------------------------------- |
|
|
21
|
-
| `mimo-v2.5-pro-ultraspeed` | ❌ | 917K | Fast Pro reasoning for latency-sensitive agent tasks (extension only) |
|
|
22
|
-
| `mimo-v2.5-pro` | ❌ | 917K | Flagship text-only — best for deep reasoning |
|
|
23
|
-
| `mimo-v2.5` | ✅ | 917K | Omnimodal — text + image + video + audio |
|
|
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 |
|
|
24
28
|
|
|
25
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`.
|
|
26
30
|
|
|
@@ -189,6 +193,20 @@ Token Plan subscribers use different base URLs and `tp-` prefixed keys from pay-
|
|
|
189
193
|
|
|
190
194
|
The extension has a built-in multi-region endpoint selector covering all Token Plan regions (China, Singapore, Amsterdam). With the custom endpoint method, update the `url` in `chatLanguageModels.json` and swap the key.
|
|
191
195
|
|
|
196
|
+
## Local Proxy
|
|
197
|
+
|
|
198
|
+
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).
|
|
199
|
+
|
|
200
|
+
| Setting | Value |
|
|
201
|
+
| ------------ | ----------------------------------------------------- |
|
|
202
|
+
| Script | `proxy/mimo-proxy.mjs` |
|
|
203
|
+
| Listen URL | `http://127.0.0.1:3459/v1/chat/completions` |
|
|
204
|
+
| Health check | `curl http://127.0.0.1:3459/healthz` |
|
|
205
|
+
| Start | `npm run proxy:mimo` (or `node proxy/mimo-proxy.mjs`) |
|
|
206
|
+
| Help | `node proxy/mimo-proxy.mjs --help` |
|
|
207
|
+
|
|
208
|
+
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.
|
|
209
|
+
|
|
192
210
|
## Notes
|
|
193
211
|
|
|
194
212
|
- **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.
|
package/docs/models/minimax.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
|
|
3
3
|
> **TL;DR:** MiniMax-M3 works directly — no proxy needed. Use `thinking: { type: "adaptive" }` + `reasoning_split: true` in `requestBody` so the model can reason and the response arrives in a clean OpenAI format (`reasoning_details` field, separate from `content`). **Important:** `thinking: { type: "disabled" }` is **not** a hard override — the model still reasons internally and emits `<think>` tags / `reasoning_content` regardless.
|
|
4
4
|
>
|
|
5
|
-
> Want faster responses and fewer admission failures during peak hours? Add `"service_tier": "priority"` to `requestBody` (or register a second `MiniMax-M3-Priority` picker entry) — same model, **1.5× cost** for **priority admission**. See [M3 Priority tier](#
|
|
5
|
+
> Want faster responses and fewer admission failures during peak hours? Add `"service_tier": "priority"` to `requestBody` (or register a second `MiniMax-M3-Priority` picker entry) — same model, **1.5× cost** for **priority admission**. See [M3 Priority tier](#4-m3-priority-tier-optional) below.
|
|
6
6
|
>
|
|
7
7
|
> The same `url`, `model id`, and `requestBody` work for **both** Pay-as-You-Go (account-balance billing) and Token Plan (monthly/annual subscription) — only the API key in the secret field changes.
|
|
8
8
|
>
|
|
@@ -15,19 +15,24 @@
|
|
|
15
15
|
|
|
16
16
|
## At a Glance
|
|
17
17
|
|
|
18
|
-
| Field | Value
|
|
19
|
-
| ------------------------ |
|
|
20
|
-
| Mode | **Direct** (no proxy)
|
|
21
|
-
| Billing | **Pay-as-You-Go** _or_ **Token Plan subscription** (same config)
|
|
22
|
-
| Vision | ✅ Yes (image + video)
|
|
23
|
-
| Tool calling | ✅ Yes
|
|
24
|
-
| Context | 1M (guaranteed 512K)
|
|
25
|
-
| Max output | 131072
|
|
26
|
-
| Required `requestBody` | `thinking: { type: "adaptive" }, reasoning_split: true`
|
|
27
|
-
| Endpoint (international) | `https://api.minimax.io/v1/chat/completions`
|
|
28
|
-
| Endpoint (China) | `https://api.minimaxi.com/v1/chat/completions`
|
|
29
|
-
|
|
|
30
|
-
|
|
18
|
+
| Field | Value |
|
|
19
|
+
| ------------------------ | ----------------------------------------------------------------------------------- |
|
|
20
|
+
| Mode | **Direct** (no proxy) |
|
|
21
|
+
| Billing | **Pay-as-You-Go** _or_ **Token Plan subscription** (same config) |
|
|
22
|
+
| Vision | ✅ Yes (image + video) |
|
|
23
|
+
| Tool calling | ✅ Yes |
|
|
24
|
+
| Context | 1M (guaranteed 512K) |
|
|
25
|
+
| Max output | 131072 |
|
|
26
|
+
| Required `requestBody` | `thinking: { type: "adaptive" }, reasoning_split: true` |
|
|
27
|
+
| Endpoint (international) | `https://api.minimax.io/v1/chat/completions` |
|
|
28
|
+
| Endpoint (China) | `https://api.minimaxi.com/v1/chat/completions` |
|
|
29
|
+
| Auth | `Authorization: Bearer $MINIMAX_API_KEY` (or Subscription Key, see [Setup](#setup)) |
|
|
30
|
+
|
|
31
|
+
### Models
|
|
32
|
+
|
|
33
|
+
| Model | Vision | Context | Max output | Notes |
|
|
34
|
+
| ------------ | ------ | ------- | ---------- | -------------------------------------------------------------------------------------- |
|
|
35
|
+
| `MiniMax-M3` | ✅ Yes | 1M | 131072 | Multimodal frontier coding model; adaptive reasoning; PAYG and Token Plan share config |
|
|
31
36
|
|
|
32
37
|
## Quick Start
|
|
33
38
|
|
|
@@ -37,6 +42,15 @@
|
|
|
37
42
|
|
|
38
43
|
## Setup
|
|
39
44
|
|
|
45
|
+
### Regional endpoints
|
|
46
|
+
|
|
47
|
+
> API keys are region-specific. The same PAYG-vs-Token-Plan distinction applies to the China region (`api.minimaxi.com`); Subscription Keys are issued at `platform.minimaxi.com/user-center/payment/token-plan`.
|
|
48
|
+
|
|
49
|
+
| Region | Endpoint |
|
|
50
|
+
| ------------- | ---------------------------------------------- |
|
|
51
|
+
| International | `https://api.minimax.io/v1/chat/completions` |
|
|
52
|
+
| China | `https://api.minimaxi.com/v1/chat/completions` |
|
|
53
|
+
|
|
40
54
|
### 1. VS Code configuration
|
|
41
55
|
|
|
42
56
|
| OS | Path |
|
|
@@ -106,16 +120,7 @@ The same `chatLanguageModels.json` block above is reused unchanged. Only the sec
|
|
|
106
120
|
|
|
107
121
|
When the Token Plan 5-hour or weekly quota is exhausted, the request fails with a Token Plan quota error (see [Troubleshooting](#troubleshooting)). At that point you can either wait for the quota window to reset, buy a Credits top-up at the same console (Credits use the same Subscription Key), or swap the key back to your Open Platform API Key to fall back to PAYG. The URL and `requestBody` do not change during the swap.
|
|
108
122
|
|
|
109
|
-
### 4.
|
|
110
|
-
|
|
111
|
-
| Region | Endpoint |
|
|
112
|
-
| ------------- | ---------------------------------------------- |
|
|
113
|
-
| International | `https://api.minimax.io/v1/chat/completions` |
|
|
114
|
-
| China | `https://api.minimaxi.com/v1/chat/completions` |
|
|
115
|
-
|
|
116
|
-
> API keys are region-specific. The same PAYG-vs-Token-Plan distinction applies to the China region (`api.minimaxi.com`); Subscription Keys are issued at `platform.minimaxi.com/user-center/payment/token-plan`.
|
|
117
|
-
|
|
118
|
-
### 5. M3 Priority tier (optional)
|
|
123
|
+
### 4. M3 Priority tier (optional)
|
|
119
124
|
|
|
120
125
|
MiniMax exposes M3 with a per-request **`service_tier`** switch that promotes the request into MiniMax's priority admission queue. Priority is **not** a separate model — it is the same `MiniMax-M3` weights invoked with `"service_tier": "priority"` in the request body, costing **1.5× Standard** 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.
|
|
121
126
|
|
package/docs/models/qwen.md
CHANGED
|
@@ -4,35 +4,39 @@
|
|
|
4
4
|
|
|
5
5
|
## At a Glance
|
|
6
6
|
|
|
7
|
-
| Field
|
|
8
|
-
|
|
|
9
|
-
| Mode
|
|
10
|
-
| Billing
|
|
11
|
-
| Vision
|
|
12
|
-
| Tool calling
|
|
13
|
-
| Context
|
|
14
|
-
|
|
|
15
|
-
|
|
|
16
|
-
|
|
|
17
|
-
|
|
|
7
|
+
| Field | Value |
|
|
8
|
+
| ---------------------- | -------------------------------------------------------------------------------- |
|
|
9
|
+
| Mode | **Proxy** (local on `:3458`) **or** **Direct** (static `enable_thinking: false`) |
|
|
10
|
+
| Billing | **Pay-as-You-Go only** — 1M-token free quota for new users |
|
|
11
|
+
| Vision | ✅ Yes (`qwen3.7-plus`) |
|
|
12
|
+
| Tool calling | ✅ Yes |
|
|
13
|
+
| Context | 1M |
|
|
14
|
+
| Max output | _see Models table_ |
|
|
15
|
+
| Endpoint | `https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions` |
|
|
16
|
+
| Proxy endpoint | `http://127.0.0.1:3458/v1/chat/completions` |
|
|
17
|
+
| Auth | `Authorization: Bearer $DASHSCOPE_API_KEY` |
|
|
18
|
+
| `requestBody` (direct) | `enable_thinking: false` |
|
|
19
|
+
| `requestBody` (proxy) | _none — proxy injects based on tool activity_ |
|
|
18
20
|
|
|
19
21
|
### Models
|
|
20
22
|
|
|
21
|
-
| Model | Vision |
|
|
22
|
-
| -------------- | ------ | -------------------------------------- |
|
|
23
|
-
| `qwen3.7-plus` | ✅ Yes | Primary model with image understanding |
|
|
24
|
-
| `qwen3.7-max` | ❌ No | Larger text-only model |
|
|
23
|
+
| Model | Vision | Context | Max output | Notes |
|
|
24
|
+
| -------------- | ------ | ------- | --------------- | -------------------------------------- |
|
|
25
|
+
| `qwen3.7-plus` | ✅ Yes | 1M | _(unspecified)_ | Primary model with image understanding |
|
|
26
|
+
| `qwen3.7-max` | ❌ No | 1M | _(unspecified)_ | Larger text-only model |
|
|
25
27
|
|
|
26
28
|
> 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.
|
|
27
29
|
|
|
28
|
-
## Quick Start
|
|
30
|
+
## Quick Start
|
|
31
|
+
|
|
32
|
+
### With Proxy (recommended)
|
|
29
33
|
|
|
30
34
|
1. **Start the proxy:** `npm run proxy:qwen` (or `npx copilot-custom-endpoint qwen`).
|
|
31
35
|
2. **Use the proxy-path JSON snippet** below.
|
|
32
36
|
3. **Set your DashScope API key** via Command Palette → **Chat: Manage Language Models**.
|
|
33
37
|
4. **Restart VS Code.** Reasoning will be visible in plain chat and suppressed on tool turns.
|
|
34
38
|
|
|
35
|
-
|
|
39
|
+
### Direct (no proxy)
|
|
36
40
|
|
|
37
41
|
1. **Use the direct-path JSON snippet** below.
|
|
38
42
|
2. **Set your `DASHSCOPE_API_KEY`** via Command Palette → **Chat: Manage Language Models**.
|
|
@@ -134,11 +138,34 @@ DashScope is region-specific — your API key only works on the endpoint it was
|
|
|
134
138
|
}
|
|
135
139
|
```
|
|
136
140
|
|
|
137
|
-
> **Keep the proxy terminal open** while using Qwen via proxy.
|
|
141
|
+
> **Keep the proxy terminal open** while using Qwen via proxy. Configuration knobs are documented in [Local Proxy](#local-proxy) below.
|
|
142
|
+
|
|
143
|
+
### 2. API key
|
|
144
|
+
|
|
145
|
+
DashScope is **Pay-as-You-Go only** — but new Model Studio users get **1M input + 1M output tokens per model free for 90 days**. Prepaid token packages are also available.
|
|
146
|
+
|
|
147
|
+
1. Open the Command Palette (`Ctrl+Shift+P`).
|
|
148
|
+
2. Run **Chat: Manage Language Models**.
|
|
149
|
+
3. Find the **Qwen** group → **Update API Key**.
|
|
150
|
+
4. Paste your DashScope API key.
|
|
151
|
+
|
|
152
|
+
> VS Code replaces `"apiKey": ""` with a `${input:chat.lm.secret.<id>}` reference. Keys are region-specific.
|
|
138
153
|
|
|
139
|
-
|
|
154
|
+
## Local Proxy
|
|
140
155
|
|
|
141
|
-
|
|
156
|
+
The `proxy/qwen-proxy.mjs` adds dynamic thinking suppression on top of the direct integration. Reasoning stays ON in plain chat and turns OFF automatically only when tools are invoked. If you don't need reasoning visibility, the direct path (`### Direct (no proxy)` above) is simpler.
|
|
157
|
+
|
|
158
|
+
| Setting | Value |
|
|
159
|
+
| ------------ | ----------------------------------------------------- |
|
|
160
|
+
| Script | `proxy/qwen-proxy.mjs` |
|
|
161
|
+
| Listen URL | `http://127.0.0.1:3458/v1/chat/completions` |
|
|
162
|
+
| Health check | `curl http://127.0.0.1:3458/healthz` |
|
|
163
|
+
| Start | `npm run proxy:qwen` (or `node proxy/qwen-proxy.mjs`) |
|
|
164
|
+
| Help | `node proxy/qwen-proxy.mjs --help` |
|
|
165
|
+
|
|
166
|
+
### Environment variables
|
|
167
|
+
|
|
168
|
+
Set in `.env` at the repo root (the proxy `import 'dotenv/config'` automatically).
|
|
142
169
|
|
|
143
170
|
| Variable | Default | Purpose |
|
|
144
171
|
| ---------------------------------------- | ------------------------------------------------------------------------- | -------------------------------------------------- |
|
|
@@ -147,7 +174,7 @@ Set in `.env` at the repo root.
|
|
|
147
174
|
| `QWEN_PROXY_LOG` | `debug_log/qwen-proxy.ndjson` | Redacted NDJSON log path |
|
|
148
175
|
| `QWEN_PROXY_DISABLE_THINKING_WITH_TOOLS` | `1` | Set to `0` to skip tool-aware thinking suppression |
|
|
149
176
|
|
|
150
|
-
|
|
177
|
+
### What the proxy does
|
|
151
178
|
|
|
152
179
|
The proxy detects active tool use by examining the conversation state (a `"tool"`-role message in history or a non-default `tool_choice`), not just the presence of a `tools` array. This correctly handles tool-enabled conversations even when the client sends `tools` in an earlier request but omits it from subsequent turns.
|
|
153
180
|
|
|
@@ -156,16 +183,13 @@ The proxy detects active tool use by examining the conversation state (a `"tool"
|
|
|
156
183
|
| Tool-role message in history **or** non-default `tool_choice` | Inject `enable_thinking: false` |
|
|
157
184
|
| Plain chat (no tool activity) | Delete `enable_thinking` (default ON) |
|
|
158
185
|
|
|
159
|
-
###
|
|
160
|
-
|
|
161
|
-
DashScope is **Pay-as-You-Go only** — but new Model Studio users get **1M input + 1M output tokens per model free for 90 days**. Prepaid token packages are also available.
|
|
186
|
+
### Forwards header & streaming
|
|
162
187
|
|
|
163
|
-
|
|
164
|
-
|
|
165
|
-
|
|
166
|
-
4. Paste your DashScope API key.
|
|
188
|
+
- Forwards your `Authorization` header upstream unchanged.
|
|
189
|
+
- Preserves streaming responses (SSE).
|
|
190
|
+
- Writes redacted request summaries to `debug_log/qwen-proxy.ndjson`.
|
|
167
191
|
|
|
168
|
-
>
|
|
192
|
+
> **Keep the proxy terminal open** while using Qwen via proxy.
|
|
169
193
|
|
|
170
194
|
## Notes
|
|
171
195
|
|
package/docs/pricing.md
CHANGED
|
@@ -41,6 +41,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
41
41
|
| **Gemini 3.1 Pro** | Google | **~$0.047** | **46.5** | $2.00¹ | $0.20 | $12.00¹ | ~$2.20 | 1M |
|
|
42
42
|
| **GPT-5.3-Codex** | OpenAI | **~$0.052** | **44.0** ³ | $1.75 | $0.175 | $14.00 | ~$2.28 | 400K |
|
|
43
43
|
| **GPT-5.4** | OpenAI | **~$0.054** | **51.4** | $2.50 | $0.25 | $15.00 | ~$2.75 | 1M |
|
|
44
|
+
| **Claude Sonnet 5** ⁶ | Anthropic | **~$0.057** | **53.0** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
|
|
44
45
|
| **Claude Sonnet 4.6** | Anthropic | **~$0.064** | **47.2** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
|
|
45
46
|
| **Claude Opus 4.8** | Anthropic | **~$0.090** | **55.7** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
|
|
46
47
|
| **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
|
|
@@ -59,6 +60,8 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
59
60
|
|
|
60
61
|
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 a custom-endpoint entry, add `"service_tier": "priority"` to `requestBody`. See [docs/research/minimax-m3-priority.md](research/minimax-m3-priority.md) for the full breakdown.
|
|
61
62
|
|
|
63
|
+
⁶ **Claude Sonnet 5** has introductory pricing of **$2.00 / $0.20 / $10.00** (input / cached / output) through **August 31, 2026**, after which the standard pricing of $3.00 / $0.30 / $15.00 shown above takes effect. See [Anthropic's pricing page](https://claude.com/pricing) for the latest.
|
|
64
|
+
|
|
62
65
|
Cost per intelligence = estimated session cost ÷ Intelligence Index score. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
|
|
63
66
|
|
|
64
67
|
> **Notes:**
|
|
@@ -66,7 +69,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
|
|
|
66
69
|
> - **DeepSeek V4** input pricing shown is the **cache miss** price. Cache hits are significantly cheaper ($0.0028/M for Flash, $0.003625/M for Pro).
|
|
67
70
|
> - **MiMo** input pricing shown is the **cache miss** price. Cache hits are essentially free for V2.5 Pro ($0.0036/M, ~120× cheaper) and V2.5 ($0.0028/M, ~50× cheaper). A Xiaomi price cut took effect on 2026-05-27.
|
|
68
71
|
> - **Gemini 3 Flash** is priced at $0.50/MTok input (text/image/video) and $1.00/MTok input for audio.
|
|
69
|
-
> - **Anthropic (Claude)** models also have a cache write cost ($6.25/MTok for Opus, $3.75/MTok for Sonnet, $1.25/MTok for Haiku). Opus 4.7
|
|
72
|
+
> - **Anthropic (Claude)** models also have a cache write cost ($6.25/MTok for Opus, $3.75/MTok for Sonnet, $1.25/MTok for Haiku). Opus 4.7+, Sonnet 5, and Fable 5 use a new tokenizer that produces approximately 30% more tokens for the same text.
|
|
70
73
|
> - **OpenAI** models support cached input at 0.1× base input rate.
|
|
71
74
|
> - **Qwen** models use **tiered pricing** — determined by total input tokens per request. Prices above are for non-thinking mode.
|
|
72
75
|
> - **Kimi** official tables list **Cache Hit before Cache Miss** (opposite order to our table). The rows below transpose them so "Input" = cache miss and "Cached input" = cache hit.
|
|
@@ -82,7 +85,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
|
|
|
82
85
|
|
|
83
86
|
> **How long does 7,000 credits last?** A Pro+ subscriber running 50-turn sessions could afford roughly **13 GPT-5.5 sessions**, **23 Opus sessions**, or **212 Raptor mini sessions** per month — or mix and match. (Multiply session cost by 100 to convert to AI credits.)
|
|
84
87
|
|
|
85
|
-
> Prices last verified:
|
|
88
|
+
> Prices last verified: July 2, 2026. Always check the official pages for the latest rates:
|
|
86
89
|
>
|
|
87
90
|
> - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
|
|
88
91
|
> - [Microsoft MAI-Code-1-Flash model card](https://docs.github.com/en/copilot/reference/ai-models/model-comparison#task-general-purpose-coding-and-writing)
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "copilot-custom-endpoint",
|
|
3
|
-
"version": "1.7.
|
|
3
|
+
"version": "1.7.4",
|
|
4
4
|
"description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2, Qwen 3.x & MiMo V2.5",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"type": "module",
|
|
@@ -57,4 +57,4 @@
|
|
|
57
57
|
"dependencies": {
|
|
58
58
|
"dotenv": "^17.4.2"
|
|
59
59
|
}
|
|
60
|
-
}
|
|
60
|
+
}
|