copilot-custom-endpoint 2.1.4 → 2.1.5

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
@@ -29,7 +29,7 @@ That's it. No code, no servers to manage (unless the model specifically needs th
29
29
  | **Qwen 3.7 Max** | DashScope | Optional (recommended) | ❌ | [Manual setup](docs/models/qwen.md) |
30
30
  | **Qwen 3.8 Max** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
31
31
  | **MiniMax M3** | MiniMax | No | ✅ | [Extension](https://github.com/tugudush/minimax-copilot) ★ / [Manual setup](docs/models/minimax.md) |
32
- | **GLM 5.2 / 5.1** | Z.ai | No | ✅ via extension proxy | [Manual setup](docs/models/glm.md) |
32
+ | **GLM 5.3 / 5.2 / 5.1** | Z.ai | No | ✅ via extension proxy | [Manual setup](docs/models/glm.md) |
33
33
  | **GLM 5V Turbo** | Z.ai | No | ✅ | [Manual setup](docs/models/glm.md) |
34
34
  | **DeepSeek V4 Pro / Flash 0731** | DeepSeek | No (uses an extension) | ❌ (0731) | [Extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) / [setup notes](docs/models/deepseek.md) |
35
35
 
@@ -120,6 +120,7 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
120
120
  | **Gemini 3.7 Flash** ¹³ | Google | **~$0.013** | **56** | ~$0.75 | ✅ | 1M |
121
121
  | **Qwen 3.6 Plus** ¹⁶ | DashScope | **~$0.014** | **40.0** | ~$0.55 | ✅ | 1M |
122
122
  | **Gemini 3.6 Flash** ⁸ | Google | **~$0.015** | **51.6** | ~$0.75 | ✅ | 1M |
123
+ | **GLM 5.3** ¹⁷ | Z.ai | **~$0.019** | **59.5** | ~$1.14 | ❌ | 1M |
123
124
  | **Kimi K2.6** | Moonshot | **~$0.020** | **45.0** | ~$0.88 | ✅ | 262K |
124
125
  | **GPT-5.4 mini** | OpenAI | **~$0.020** | **40.9** | ~$0.83 | ❌ | 400K |
125
126
  | **Kimi K2.7 Code** | Moonshot | **~$0.020** | **43.0** | ~$0.88 | ✅ | 262K |
@@ -174,6 +175,8 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
174
175
 
175
176
  ¹⁶ **Qwen 3.6 Plus** (DashScope, released April 2, 2026) — AA Intelligence Index **40.0**. Priced at $0.50 / $3.00 per MTok input/output ($0.05 cached). 1M context, text + image + video input. **Deprecated** in favor of Qwen 3.7 Plus.
176
177
 
178
+ ¹⁷ **GLM 5.3** (Z.ai, released August 18, 2026) — new flagship. AA Intelligence Index **59.5** (OpenRouter AA-sourced; AA page lists rounded **60**, #8/182). Priced identically to GLM 5.2: $1.40 / $0.26 / $4.40 per 1M input/cached/output. 1M context, text-only, always-thinking with `reasoning_effort` (low/high/max, default max). Released too recently for Arena rankings. See the [AA model page](https://artificialanalysis.ai/models/glm-5-3) and [Z.ai docs](https://docs.z.ai/guides/llm/glm-5.3).
179
+
177
180
  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).
178
181
 
179
182
  > **👤 Personal picks** —
@@ -186,11 +189,11 @@ For footnotes, sources, and detailed notes (cache behavior, tiered pricing, free
186
189
  >
187
190
  > **MiniMax M3** (45.4, ~$0.27/session) is still the best **direct** custom-endpoint option — no proxy or extension, vision, 1M context, strong coding — but it no longer leads on value now that DeepSeek V4 Flash scores higher at a third of the cost. Pick M3 when you want a plug-and-play custom endpoint with vision.
188
191
  >
189
- > For **plan mode / architecture & design thinking**, **Qwen 3.8 Max**, **Kimi K3**, **GLM 5.2**, **GPT-5.6 Luna**, and **DeepSeek V4 Flash 0731** are worth considering:
192
+ > For **plan mode / architecture & design thinking**, **Qwen 3.8 Max**, **Kimi K3**, **GLM 5.3**, **GPT-5.6 Luna**, and **DeepSeek V4 Flash 0731** are worth considering:
190
193
  >
191
194
  > - **Qwen 3.8 Max** — scores **58.1** (#5 overall, the #2 custom-endpoint model) — the default planning pick. Near-flagship intelligence at ~$1.60/session (roughly half Kimi K3's cost), with 1M context and vision. Strong for whole-codebase planning, architecture, and large spec review.
192
195
  > - **Kimi K3** — new flagship. Highest intelligence score among custom-endpoint models (**59.7**, #4 overall). Best for complex reasoning, long-horizon planning, and architecture decisions when you want the absolute best — but at ~$3.00/session it's ~2× Qwen 3.8 Max for +1.6 points, so **reserve it for hard problems**.
193
- > - **GLM 5.2** — scores **52.6**, reasoning-heavy planning at a lower price. 1M lossless context, ideal for whole-codebase planning and large spec review. ~$1.14/session is ~4× MiniMax M3, so **not a daily driver for agent mode** — reserve it for planning, then hand implementation off to a cheaper model.
196
+ > - **GLM 5.3** — new flagship, scores **59.5** (now the #2 custom-endpoint model, just behind Kimi K3's 59.7) at the same ~$1.14/session as GLM 5.2. 1M context, text-only, always-thinking. Best-in-class agentic coding per Z.ai (50% gain over 5.2 on their Code Bench) — ideal for whole-codebase planning and large spec review. ~4× MiniMax M3, so **not a daily driver for agent mode** — reserve it for planning, then hand implementation off to a cheaper model.
194
197
  > - **GPT-5.6 Luna** (Copilot native) — scores **52.3** and is now the cheapest 50+ model. OpenAI cut its API price to $0.20/$1.20 per 1M input/output tokens; in Copilot, the equivalent benefit is lower AI-credit consumption, while your subscription price and monthly allowance stay unchanged. Ideal for high-quality planning on a budget.
195
198
  > - **DeepSeek V4 Flash 0731** (extension) — scores **51.8** at ~$0.10/session — the budget planning pick. Text-only, so pair it with a vision model for design review, but for reasoning-heavy planning it delivers near-premium scores at a fraction of the cost.
196
199
  >
@@ -1,6 +1,6 @@
1
1
  # Full example config
2
2
 
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-5.2`, `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.
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`, `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
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.
6
6
  >
@@ -163,6 +163,22 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
163
163
  "apiKey": "",
164
164
  "apiType": "chat-completions",
165
165
  "models": [
166
+ {
167
+ "id": "glm-5.3",
168
+ "name": "GLM 5.3 (text)",
169
+ "url": "https://api.z.ai/api/paas/v4/chat/completions",
170
+ "toolCalling": true,
171
+ "vision": false,
172
+ "streaming": true,
173
+ "maxInputTokens": 1048576,
174
+ "maxOutputTokens": 131072,
175
+ "requestBody": {
176
+ "thinking": { "type": "enabled" },
177
+ "reasoning_effort": "max",
178
+ "temperature": 1.0,
179
+ "top_p": 0.95
180
+ }
181
+ },
166
182
  {
167
183
  "id": "glm-5.2",
168
184
  "name": "GLM 5.2 (text)",
@@ -221,6 +237,6 @@ If you only need one provider, jump straight to its setup guide:
221
237
  - [Qwen 3.7 Plus / 3.7 Max](qwen.md)
222
238
  - [Xiaomi MiMo (V2.5 / V2.5 Pro)](mimo.md)
223
239
  - [MiniMax M3 (Standard)](minimax.md) and [MiniMax M3 (Priority)](minimax.md#5-m3-priority-tier-optional)
224
- - [GLM (5.2 / 5.1 / 5V Turbo)](glm.md)
240
+ - [GLM (5.3 / 5.2 / 5.1 / 5V Turbo)](glm.md)
225
241
 
226
242
  > **DeepSeek V4 Pro / V4 Flash** use the [DeepSeek V4 for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) extension. They appear in `chatLanguageModels.json` as `vendor: "deepseek"` (not as a `customendpoint` provider) and are configured via the extension's settings block.
@@ -20,20 +20,21 @@
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 | 1M (`glm-5.2` Solid Lossless Context) |
23
+ | Context | 1M (`glm-5.3` / `glm-5.2` Solid Lossless Context) |
24
24
  | Max output | 131072 |
25
- | Required `requestBody` | `thinking: { type: "enabled" }` (recommended) |
25
+ | Required `requestBody` | `thinking: { type: "enabled" }` + `reasoning_effort: "max"` (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` |
28
28
  | Auth | `Authorization: Bearer $ZAI_API_KEY` |
29
29
 
30
30
  ### Models
31
31
 
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) |
32
+ | Model | Vision | Context | Max output | Notes |
33
+ | -------------- | ------ | ------- | ---------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
34
+ | `glm-5.3` | ❌ | 1M | 131072 | **New flagship** — ~50% coding gain over 5.2 on Z.ai Code Bench; always-thinking, `reasoning_effort` `low`/`high`/`max` (default `max`) ($1.40 / $4.40 per 1M) |
35
+ | `glm-5.2` | ❌ | 1M | 131072 | Previous flagship — "Opus-level" long-context engineering & agentic coding; thinking `enabled` ($1.40 / $4.40 per 1M) |
36
+ | `glm-5.1` | ❌ | 200K | 131072 | Previous flagship — long-horizon / 8h autonomous work; thinking `enabled` ($1.40 / $4.40 per 1M) |
37
+ | `glm-5v-turbo` | ✅ | 200K | 131072 | Multimodal **coding** model — vision-based agentic coding; thinking `enabled` ($1.20 / $4.00 per 1M) |
37
38
 
38
39
  > 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
40
 
@@ -63,6 +64,22 @@
63
64
  "apiKey": "",
64
65
  "apiType": "chat-completions",
65
66
  "models": [
67
+ {
68
+ "id": "glm-5.3",
69
+ "name": "GLM 5.3 (text)",
70
+ "url": "https://api.z.ai/api/paas/v4/chat/completions",
71
+ "toolCalling": true,
72
+ "vision": false,
73
+ "streaming": true,
74
+ "maxInputTokens": 1048576,
75
+ "maxOutputTokens": 131072,
76
+ "requestBody": {
77
+ "thinking": { "type": "enabled" },
78
+ "reasoning_effort": "max",
79
+ "temperature": 1.0,
80
+ "top_p": 0.95
81
+ }
82
+ },
66
83
  {
67
84
  "id": "glm-5.2",
68
85
  "name": "GLM 5.2 (text)",
@@ -134,25 +151,27 @@
134
151
  - **Sampling:** recommended `temperature: 1`, `top_p: 0.95`. Z.ai's `temperature` is **hard-capped at `1.0` server-side** — sending `> 1.0` will reject with a 400. Don't set `do_sample: false` from `requestBody` (it would make `temperature`/`top_p` be ignored).
135
152
  - **`tool_choice` only supports `auto`** — don't override it (VS Code's default is `auto`).
136
153
  - **`clear_thinking` defaults to `true` server-side**, which strips historical `reasoning_content` from prior turns before sending to the model. This is what makes multi-turn tool loops stable. **Do not** set `clear_thinking: false` from `requestBody` — VS Code can't forward `reasoning_content` and the request will fail.
137
- - **Vision** is supported only on `glm-5v-turbo` (OpenAI `image_url` content-part format — external URLs and base64 data URIs both work). `glm-5.2` and `glm-5.1` are text-only. For turnkey VS Code video understanding via `glm-5v-turbo`, see [**Video Context MCP**](https://www.videocontextmcp.com/).
154
+ - **GLM 5.3 is always-thinking** — `thinking.type` only supports `enabled`; disabling reasoning is **not supported**. `reasoning_effort` accepts `low`, `high`, or `max` (default `max`; `max` recommended for coding). If you previously sent `thinking.type: "disabled"` for other GLM models, switch it to `enabled` with `reasoning_effort: "low"` when moving to `glm-5.3`.
155
+ - **Vision** is supported only on `glm-5v-turbo` (OpenAI `image_url` content-part format — external URLs and base64 data URIs both work). `glm-5.3`, `glm-5.2` and `glm-5.1` are text-only. For turnkey VS Code video understanding via `glm-5v-turbo`, see [**Video Context MCP**](https://www.videocontextmcp.com/).
138
156
  - **Context caching** is automatic — `usage.prompt_tokens_details.cached_tokens` reports cache hits; cache writes are currently free.
139
157
 
140
158
  ## Troubleshooting
141
159
 
142
- | Symptom | Likely cause | Fix |
143
- | -------------------------------------------------------- | --------------------------------------------------------------------- | -------------------------------------------------------------------- |
144
- | Model not in picker | Config not reloaded, or JSON syntax error | Restart VS Code; validate JSON |
145
- | HTTP 400 on the first turn | `requestBody` removed `do_sample` semantics or invalid `temperature` | Ensure `temperature ≤ 1.0` and `top_p ∈ [0.01, 1.0]` |
146
- | `invalid temperature: only values ≤ 1.0 are allowed` | Set `temperature > 1.0` | Lower it to `1.0` or below |
147
- | Tool call succeeds but follow-up turn degrades | `clear_thinking: false` set in `requestBody` | Remove the `clear_thinking` key and let the server default to `true` |
148
- | `tool_choice: required` rejected | GLM only supports `auto` | Don't override `tool_choice` (VS Code's default is `auto`) |
149
- | `Failed to download multimodal content` on a vision call | Z.ai's servers couldn't reach the image URL | Use a base64 `data:image/...` URI instead |
150
- | 401 Unauthorized | Region mismatch (international key used on China URL, or vice versa) | Match your key to the regional endpoint |
151
- | Upstream complains about `reasoning_content is missing` | You set `clear_thinking: false` from a client that doesn't forward it | Drop `clear_thinking` from `requestBody` |
152
- | 429 / "concurrency limit exceeded" | Too many in-flight requests | Reduce concurrent agent sessions, or upgrade your Z.ai plan |
160
+ | Symptom | Likely cause | Fix |
161
+ | -------------------------------------------------------- | --------------------------------------------------------------------- | ----------------------------------------------------------------------------- |
162
+ | Model not in picker | Config not reloaded, or JSON syntax error | Restart VS Code; validate JSON |
163
+ | HTTP 400 on the first turn | `requestBody` removed `do_sample` semantics or invalid `temperature` | Ensure `temperature ≤ 1.0` and `top_p ∈ [0.01, 1.0]` |
164
+ | `invalid temperature: only values ≤ 1.0 are allowed` | Set `temperature > 1.0` | Lower it to `1.0` or below |
165
+ | Tool call succeeds but follow-up turn degrades | `clear_thinking: false` set in `requestBody` | Remove the `clear_thinking` key and let the server default to `true` |
166
+ | `tool_choice: required` rejected | GLM only supports `auto` | Don't override `tool_choice` (VS Code's default is `auto`) |
167
+ | `thinking.type: disabled` rejected on `glm-5.3` | GLM 5.3 only supports enabled thinking; reasoning cannot be disabled | Use `thinking: { "type": "enabled" }` + `reasoning_effort: "low"` (or higher) |
168
+ | `Failed to download multimodal content` on a vision call | Z.ai's servers couldn't reach the image URL | Use a base64 `data:image/...` URI instead |
169
+ | 401 Unauthorized | Region mismatch (international key used on China URL, or vice versa) | Match your key to the regional endpoint |
170
+ | Upstream complains about `reasoning_content is missing` | You set `clear_thinking: false` from a client that doesn't forward it | Drop `clear_thinking` from `requestBody` |
171
+ | 429 / "concurrency limit exceeded" | Too many in-flight requests | Reduce concurrent agent sessions, or upgrade your Z.ai plan |
153
172
 
154
173
  ## Pricing
155
174
 
156
175
  All prices are **USD per 1M tokens** (cache miss) on the Z.ai international platform. Per-model input/output rates are listed in the `Cost` column of the [Models](#models) table above.
157
176
 
158
- > **Cache writes** are currently **Limited-time Free** for all models. Cached-input pricing is roughly 18% of the input price (e.g. `$1.40` input → `$0.25` cached for `glm-5.1` / `glm-5.2`). China platform (`bigmodel.cn`) prices in CNY; see the [China pricing page](https://bigmodel.cn/pricing). For the cross-provider comparison, see [docs/pricing.md](../pricing.md).
177
+ > **Cache writes** are currently **Limited-time Free** for all models. Cached-input pricing is roughly 18% of the input price (e.g. `$1.40` input → `$0.26` cached for `glm-5.3` / `glm-5.2` / `glm-5.1`). China platform (`bigmodel.cn`) prices in CNY; see the [China pricing page](https://bigmodel.cn/pricing). For the cross-provider comparison, see [docs/pricing.md](../pricing.md).
package/docs/pricing.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # Pricing
2
2
 
3
- > **Updated:** August 15, 2026 — **Claude Fable 5** and **Qwen 3.6 Plus** added (footnotes ¹⁶–¹⁷); **Grok 4.5 / 4.6** and **Claude Fable 5** are now **GitHub Copilot native** (footnotes ¹², ¹⁴, ¹⁶). **Grok 4.6** and **Gemini 3.7 Flash** added August 14 (footnotes ¹⁴–¹⁵). **Gemini 3.6 Flash promotional price cut** to $0.75 / $3.75 (footnote ⁹). **Qwen 3.7 Max / 3.7 Plus price cuts** (see footnote ¹³). OpenRouter is running limited-time promos on GPT-5.6 Terra/Luna (⁸), GLM 5.2 (⁴), GLM 5.1, MiMo V2.5/V2.5 Pro, and MiniMax M3.
3
+ > **Updated:** August 19, 2026 — **GLM 5.3** added (footnote ¹⁸): Z.ai's new flagship (August 18, 2026), AA Intelligence Index **59.5**, priced identically to GLM 5.2 ($1.40 / $0.26 / $4.40). August 17: **GLM 5.2** OpenRouter promo refreshed (footnote ⁴): NovitaAI cut to 48% off; Open Sail Research now cheapest at $0.50 / $3.15. August 15: **Claude Fable 5** and **Qwen 3.6 Plus** added (footnotes ¹⁶–¹⁷); **Grok 4.5 / 4.6** and **Claude Fable 5** are now **GitHub Copilot native** (footnotes ¹², ¹⁴, ¹⁶). **Grok 4.6** and **Gemini 3.7 Flash** added August 14 (footnotes ¹⁴–¹⁵). **Gemini 3.6 Flash promotional price cut** to $0.75 / $3.75 (footnote ⁹). **Qwen 3.7 Max / 3.7 Plus price cuts** (see footnote ¹³). OpenRouter is running limited-time promos on GPT-5.6 Terra/Luna (⁸), GLM 5.2 (⁴), GLM 5.1, MiMo V2.5/V2.5 Pro, and MiniMax M3.
4
4
 
5
5
  > **⏰ June 1, 2026 — GitHub Copilot switched to usage-based billing (AI Credits) today.**
6
6
  >
@@ -35,6 +35,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
35
35
  | **Gemini 3.7 Flash** ¹⁵ | Google | **~$0.013** | **56** | $0.75 | $0.075 | $3.75 | ~$0.75 | 1M |
36
36
  | **Qwen 3.6 Plus** ¹⁷ | DashScope | **~$0.014** | **40.0** | $0.50 | $0.05 | $3.00 | ~$0.55 | 1M |
37
37
  | **Gemini 3.6 Flash** ⁹ | Google | **~$0.015** | **51.6** | $0.75 | $0.075 | $3.75 | ~$0.75 | 1M |
38
+ | **GLM 5.3** ¹⁸ | Z.ai | **~$0.019** | **59.5** | $1.40 | $0.26 | $4.40 | ~$1.14 | 1M |
38
39
  | **Kimi K2.6** | Moonshot | **~$0.020** | **45.0** | $0.95 | $0.16 | $4.00 | ~$0.88 | 256K |
39
40
  | **GPT-5.4 mini** | OpenAI | **~$0.020** | **40.9** | $0.75 | $0.075 | $4.50 | ~$0.83 | 400K |
40
41
  | **Kimi K2.7 Code** | Moonshot | **~$0.020** | **43.0** | $0.95 | $0.19 | $4.00 | ~$0.88 | 262K |
@@ -63,7 +64,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
63
64
 
64
65
  ³ Score is an **estimate** from Artificial Analysis (labelled "independent evaluation forthcoming"). Not a confirmed run of the full evaluation suite. As of August 7, 2026, **GLM 5V Turbo (35.0)** is the only remaining estimate in this table — MiMo V2.5 is now a measured 38.0.
65
66
 
66
- ⁴ GLM 5.2 is Z.ai's newly released flagship model (Opus-level intelligence / 1M Solid context). AA Intelligence Index score (**52.6**) and pricing of **$1.40** (input), **$0.26** (cached), and **$4.40** (output) per 1M tokens confirmed on its [model page](https://artificialanalysis.ai/models/glm-5-2). Session cost is identical to GLM 5.1 (~$1.14). OpenRouter's cheapest provider (NovitaAI) is currently running a temporary 52%-off promo at $0.679 / $2.134 per 1M.
67
+ ⁴ GLM 5.2 was Z.ai's previous flagship (superseded by **GLM 5.3** on August 18, 2026 — see footnote ¹⁸). AA Intelligence Index score (**52.6**) and pricing of **$1.40** (input), **$0.26** (cached), and **$4.40** (output) per 1M tokens confirmed on its [model page](https://artificialanalysis.ai/models/glm-5-2). Session cost is identical to GLM 5.1 (~$1.14). As of August 17, 2026, OpenRouter's cheapest provider is **Open Sail Research** at **$0.50 / $3.15** per 1M (listed price, no promo); NovitaAI's temporary promo has been reduced from 52% to **48% off** (effective **$0.7238 / $2.275** per 1M, cache reads $0.1344).
67
68
 
68
69
  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.
69
70
 
@@ -91,6 +92,8 @@ All models are listed together below, sorted by Cost per intelligence ascending
91
92
 
92
93
  ¹⁷ **Qwen 3.6 Plus** (DashScope, released **April 2, 2026**) — AA Intelligence Index **40.0**. Priced at **$0.50 / $0.05 / $3.00** per 1M input/cached/output (≤256K input tier; explicit cache read $0.05). 1M context window, text + image + video input, reasoning model. **Deprecated** — superseded by Qwen 3.7 Plus; AA marks it deprecated and no longer refreshes performance benchmarks beyond the default workload. See the [AA model page](https://artificialanalysis.ai/models/qwen3-6-plus).
93
94
 
95
+ ¹⁸ **GLM 5.3** is Z.ai's newest flagship (released **August 18, 2026**) — same base model as GLM 5.2 with post-training improvements (~50% coding gain over 5.2 on Z.ai Code Bench). AA Intelligence Index **59.5** (OpenRouter's AA-sourced benchmark; AA's [model page](https://artificialanalysis.ai/models/glm-5-3) lists a rounded **60**, **#8/182**), Coding **74.8**, Agentic **59.1**. Pricing is identical to GLM 5.2: **$1.40** input, **$0.26** cached, **$4.40** output per 1M tokens (so the modeled session cost is the same, ~$1.14). 1M context window, 753B params, text-only. Always-thinking: `thinking.type` only supports `enabled` and `reasoning_effort` accepts `low` / `high` / `max` (default `max`). See the [Z.ai model page](https://docs.z.ai/guides/llm/glm-5.3).
96
+
94
97
  Cost per intelligence = estimated session cost ÷ Intelligence Index score. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
95
98
 
96
99
  > **Notes:**
@@ -105,13 +108,13 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
105
108
  > - **DashScope** offers a **free quota** of 1M input + 1M output tokens per model, valid for 90 days.
106
109
  > - **MiniMax M3** uses **tiered pricing** — input price doubles above 512K input tokens. Cache hits are priced at 20% of the input rate ($0.12/M ≤512K, $0.24/M >512K). A **permanent 50% off** discount applies to all MiniMax-M3 pay-as-you-go usage (Standard and Priority tiers), making the effective rates half the list prices above.
107
110
  > - **MiniMax M3 Priority** is not a separate model — it is the same `MiniMax-M3` weights invoked with `"service_tier": "priority"` in the request body. Priority costs **1.5× Standard** across input, output, and cache reads, in exchange for **priority admission** (faster responses, fewer failures during MiniMax peak hours — typically 15:00–17:30 weekdays). Capabilities, context window (1M, guaranteed 512K), vision, tool calling, rate limits (200 RPM / 10M TPM), and thinking modes are identical to Standard. See [docs/research/minimax-m3-priority.md](research/minimax-m3-priority.md) for the full breakdown.
108
- > - **GLM** models support prompt caching — cache hits are priced at $0.24/M for 5V Turbo and $0.26/M for 5.1.
111
+ > - **GLM** models support prompt caching — cache hits are priced at $0.26/M for 5.3, 5.2, and 5.1; $0.24/M for 5V Turbo.
109
112
  > - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion.
110
113
  > - For typical Copilot chat usage (short-to-medium prompts), you'll almost always fall in the lowest pricing tier.
111
114
 
112
115
  > **How long does 7,000 credits last?** A Pro+ subscriber running 50-turn sessions could afford roughly **13 GPT-5.5 sessions** or **23 Opus sessions** per month — or mix and match. (Multiply session cost by 100 to convert to AI credits.)
113
116
 
114
- > Prices last verified: August 15, 2026. Always check the official pages for the latest rates:
117
+ > Prices last verified: August 19, 2026. Always check the official pages for the latest rates:
115
118
  >
116
119
  > - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
117
120
  > - [OpenAI pricing](https://openai.com/api/pricing/)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "copilot-custom-endpoint",
3
- "version": "2.1.4",
3
+ "version": "2.1.5",
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",