copilot-custom-endpoint 2.1.5 → 2.1.7

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 / K2.7 Code / K2.6** | Moonshot | **Yes** | ✅ | [Manual setup](docs/models/kimi.md) |
26
- | **MiMo V2.5** | Xiaomi | Optional (recommended) | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) ★ / [Manual setup](docs/models/mimo.md) |
27
- | **MiMo V2.5 Pro** | Xiaomi | Optional (recommended) | ❌ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) ★ / [Manual setup](docs/models/mimo.md) |
28
- | **Qwen 3.7 Plus** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
29
- | **Qwen 3.7 Max** | DashScope | Optional (recommended) | ❌ | [Manual setup](docs/models/qwen.md) |
30
- | **Qwen 3.8 Max** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
31
- | **MiniMax M3** | MiniMax | No | ✅ | [Extension](https://github.com/tugudush/minimax-copilot) ★ / [Manual setup](docs/models/minimax.md) |
32
- | **GLM 5.3 / 5.2 / 5.1** | Z.ai | No | ✅ via extension proxy | [Manual setup](docs/models/glm.md) |
33
- | **GLM 5V Turbo** | Z.ai | No | ✅ | [Manual setup](docs/models/glm.md) |
34
- | **DeepSeek V4 Pro / Flash 0731** | DeepSeek | No (uses an extension) | ❌ (0731) | [Extension](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) / [setup notes](docs/models/deepseek.md) |
23
+ | Model | Provider | Needs proxy? | Vision | Setup guide |
24
+ | ------------------------------ | --------- | ---------------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
25
+ | **Kimi K3 / K2.7 Code / K2.6** | Moonshot | **Yes** | ✅ | [Manual setup](docs/models/kimi.md) |
26
+ | **MiMo V2.5** | Xiaomi | Optional (recommended) | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) ★ / [Manual setup](docs/models/mimo.md) |
27
+ | **MiMo V2.5 Pro** | Xiaomi | Optional (recommended) | ❌ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) ★ / [Manual setup](docs/models/mimo.md) |
28
+ | **Qwen 3.7 Plus** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
29
+ | **Qwen 3.7 Max** | DashScope | Optional (recommended) | ❌ | [Manual setup](docs/models/qwen.md) |
30
+ | **Qwen 3.8 Max** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
31
+ | **MiniMax M3** | MiniMax | No | ✅ | [Extension](https://github.com/tugudush/minimax-copilot) ★ / [Manual setup](docs/models/minimax.md) |
32
+ | **GLM 5.3 Flash** | Z.ai | No | ✅ | [Manual setup](docs/models/glm.md) |
33
+ | **GLM 5.3 / 5.2 / 5.1** | Z.ai | No | ✅ via extension proxy | [Manual setup](docs/models/glm.md) |
34
+ | **GLM 5V Turbo** | Z.ai | No | ✅ | [Manual setup](docs/models/glm.md) |
35
+ | **DeepSeek V4 Flash 0731** | 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
 
@@ -65,7 +67,7 @@ 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 Flash** — if you have the [DeepSeek V4 for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) extension installed (fastest, ~$0.10/session).
70
+ - **DeepSeek V4 Flash** — if you have the [DeepSeek V4 for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) extension installed (fastest, ~$0.35/session at peak rates).
69
71
  - **MiMo V2.5** — if you already have Xiaomi MiMo configured (cheapest custom-endpoint option, ~$0.10/session).
70
72
  - **Default** — if you still have native Copilot model access, this lets VS Code use its built-in fast model.
71
73
  4. The setting takes effect immediately — no restart needed.
@@ -105,15 +107,15 @@ npx copilot-custom-endpoint clean # Remove debug_log/
105
107
 
106
108
  ## Pricing snapshot
107
109
 
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.
110
+ 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 V4 estimates use peak rates; official off-peak rates are half.
109
111
 
110
112
  | Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
111
113
  | -------------------------- | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
112
- | **DeepSeek V4 Flash 0731** | DeepSeek | **~$0.0019** | **51.8** | ~$0.10 | ❌ | 1M |
114
+ | **GLM 5.3 Flash** ¹⁸ | Z.ai | **~$0.0022** | **57.5** | ~$0.13 | ✅ | 1M |
113
115
  | **MiMo V2.5** | Xiaomi | **~$0.0026** | **38.0** | ~$0.10 | ✅ | 1M |
114
116
  | **GPT-5.6 Luna** | OpenAI | **~$0.0042** | **52.3** | ~$0.22 | ✅ | 1M |
115
117
  | **MiniMax M3** | MiniMax | **~$0.0060** | **45.4** | ~$0.27 | ✅ | 1M |
116
- | **DeepSeek V4 Pro** | DeepSeek | **~$0.0066** | **45.3** | ~$0.30 | ✅ | 1M |
118
+ | **DeepSeek V4 Flash 0731** | DeepSeek | **~$0.0068** | **51.8** | ~$0.35 | ❌ | 1M |
117
119
  | **MiMo V2.5 Pro** | Xiaomi | **~$0.0070** | **42.9** | ~$0.30 | ❌ | 1M |
118
120
  | **Qwen 3.7 Plus** ¹² | DashScope | **~$0.0074** | **39.4** | ~$0.29 | ✅ | 1M |
119
121
  | **MiniMax M3 Priority**⁴ | MiniMax | **~$0.0090** | **45.4** | ~$0.41 | ✅ | 1M |
@@ -122,6 +124,7 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
122
124
  | **Gemini 3.6 Flash** ⁸ | Google | **~$0.015** | **51.6** | ~$0.75 | ✅ | 1M |
123
125
  | **GLM 5.3** ¹⁷ | Z.ai | **~$0.019** | **59.5** | ~$1.14 | ❌ | 1M |
124
126
  | **Kimi K2.6** | Moonshot | **~$0.020** | **45.0** | ~$0.88 | ✅ | 262K |
127
+ | **DeepSeek V4 Pro 0813** | DeepSeek | **~$0.020** | **53.2** | ~$1.06 | ❌ | 1M |
125
128
  | **GPT-5.4 mini** | OpenAI | **~$0.020** | **40.9** | ~$0.83 | ❌ | 400K |
126
129
  | **Kimi K2.7 Code** | Moonshot | **~$0.020** | **43.0** | ~$0.88 | ✅ | 262K |
127
130
  | **GLM 5.2** | Z.ai | **~$0.022** | **52.6** | ~$1.14 | ❌ | 1M |
@@ -177,30 +180,33 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
177
180
 
178
181
  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
182
 
183
+ ¹⁸ **GLM 5.3 Flash** (Z.ai, released August 26, 2026) — Z.ai's first native multimodal GLM-5 model (text + image input, text output). Hybrid sparse + linear attention architecture, 320B total / 18B active parameters (open weights, MIT), 1M context window. AA Intelligence Index **57.5** (Coding **71.5**, Agentic **58.2**). Priced at **$0.15 / $0.03 / $0.50** per 1M input/cached/output (list; 50% off launch promo through September 9, 2026). Always-thinking with `reasoning_effort` (low/high/max, default max). The cheapest cost-per-intelligence row in this table (~$0.0022, ~$0.13/session). See [docs/models/glm.md](docs/models/glm.md) and the [AA model page](https://artificialanalysis.ai/models/glm-5-3-flash).
184
+
180
185
  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).
181
186
 
182
187
  > **👤 Personal picks** —
183
188
  >
184
- > For serious coding work, **GPT-5.6 Luna** and **DeepSeek V4 Flash 0731** are now the top value picks:
189
+ > For serious coding work, **GPT-5.6 Luna** is the cheapest 50+ vision model, while **DeepSeek V4 Flash 0731** is the low-cost text-only pick:
185
190
  >
186
- > - **GPT-5.6 Luna** (Copilot native) — scores **52.3**, ~$0.22/session, vision-capable. Higher intelligence than MiniMax M3 (45.4) at a lower modeled cost, with reduced AI-credit consumption after OpenAI's July price cut.
187
- > - **DeepSeek V4 Flash 0731** (extension) — scores **51.8** after the AA v4.1.1 benchmark refresh, ~$0.10/session — the best intelligence-per-dollar in the lineup. Text-only, so pair it with a vision model when you need images.
191
+ > - **GPT-5.6 Luna** (Copilot native) — scores **52.3**, ~$0.22/session, vision-capable. It is cheaper than MiniMax M3 (45.4) and consumes fewer AI credits after OpenAI's July price cut.
192
+ > - **DeepSeek V4 Flash 0731** (extension) — scores **51.8** after the AA v4.1.1 benchmark refresh, ~$0.35/session at peak rates (~$0.18 off-peak). It is the lowest-cost text-only model above 50 in this table; pair it with a vision model when you need images.
188
193
  > - **Gemini 3.7 Flash** (Copilot native, new August 13) — scores **56** at ~$0.75/session under promotional pricing. The best-value Google model in Copilot: it beats Gemini 3.5 Flash (52.0) and Grok 4.5 (55.8) on intelligence at roughly half the session cost, with 1M context, full multimodal input, and AA's fastest output speed. A strong upgrade pick if you use Google models.
189
194
  >
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.
195
+ > **MiniMax M3** (45.4, ~$0.27/session) is still the best **direct** custom-endpoint option — no proxy or extension, vision, 1M context, strong coding. Pick M3 when you want a plug-and-play custom endpoint with vision.
191
196
  >
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:
197
+ > For **plan mode / architecture & design thinking**, **Qwen 3.8 Max**, **Kimi K3**, **GLM 5.3**, **GLM 5.3 Flash**, **GPT-5.6 Luna**, and **DeepSeek V4 Flash 0731** are worth considering:
193
198
  >
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.
199
+ > - **Qwen 3.8 Max** — scores **58.1** (#5 overall, the #2 custom-endpoint model) — the default **multimodal** planning pick. Near-flagship intelligence at ~$1.60/session, with 1M context and vision. Strong for whole-codebase planning, architecture, and large spec review.
195
200
  > - **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**.
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.
201
+ > - **GLM 5.3** — new flagship, scores **59.5** (now the #2 custom-endpoint model, just behind Kimi K3's 59.7) at ~$1.14/session. 1M context, text-only, always-thinking. It is the strongest text-only planning value above 59 and offers 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.
202
+ > - **GLM 5.3 Flash** — new (Aug 26): scores **57.5** at just ~$0.13/session (list) — the **cheapest 57+ model** in the table and the first native multimodal GLM-5. Near-GLM-5.3 agentic coding (Z.ai: DeepSWE v1.1 63.4 vs 46.2) at ~9× less cost, with vision. A strong daily-driver planning + image-review pick until the 50% promo ends.
197
203
  > - **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.
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.
204
+ > - **DeepSeek V4 Flash 0731** (extension) — scores **51.8** at ~$0.35/session at peak rates (~$0.18 off-peak) — the lower-cost planning pick. Text-only, so pair it with a vision model for design review, but it remains strong for reasoning-heavy planning.
199
205
  >
200
206
  > Cheaper alternatives for simpler tasks:
201
207
  >
202
- > - **Qwen 3.7 Plus** — ~$0.29/session after the August 7 price cut, 39.4 score, vision-capable — the best cost-per-intelligence value in the custom-endpoint lineup
203
- > - **MiMo V2.5** — ~$0.10/session, 38.0 score (solid fallback, vision-capable)
208
+ > - **Qwen 3.7 Plus** — ~$0.29/session after the August 7 price cut, 39.4 score, vision-capable — the budget option among the Qwen entries
209
+ > - **MiMo V2.5** — ~$0.10/session, 38.0 score, vision-capable — the lowest modeled cost-per-intelligence option in the table
204
210
 
205
211
  ## Companion tools
206
212
 
@@ -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-5.3`, `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.
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
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-flash",
168
+ "name": "GLM 5.3 Flash (multimodal)",
169
+ "url": "https://api.z.ai/api/paas/v4/chat/completions",
170
+ "toolCalling": true,
171
+ "vision": true,
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-5.3",
168
184
  "name": "GLM 5.3 (text)",
@@ -237,6 +253,6 @@ If you only need one provider, jump straight to its setup guide:
237
253
  - [Qwen 3.7 Plus / 3.7 Max](qwen.md)
238
254
  - [Xiaomi MiMo (V2.5 / V2.5 Pro)](mimo.md)
239
255
  - [MiniMax M3 (Standard)](minimax.md) and [MiniMax M3 (Priority)](minimax.md#5-m3-priority-tier-optional)
240
- - [GLM (5.3 / 5.2 / 5.1 / 5V Turbo)](glm.md)
256
+ - [GLM (5.3 Flash / 5.3 / 5.2 / 5.1 / 5V Turbo)](glm.md)
241
257
 
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.
258
+ > **DeepSeek V4 Pro 0813 / V4 Flash 0731** 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.
@@ -2,6 +2,17 @@
2
2
 
3
3
  DeepSeek V4 Pro and Flash are provided by the [DeepSeek V4 for Copilot Chat](https://marketplace.visualstudio.com/items?itemName=Vizards.deepseek-v4-for-copilot) extension. They do not use this repository's `chatLanguageModels.json` custom-endpoint configuration.
4
4
 
5
+ ## Current builds
6
+
7
+ The API model IDs remain stable while DeepSeek rolls newer builds behind them:
8
+
9
+ | API model | Current version | Update | Context | Modality | Parameters |
10
+ | ------------------- | ---------------------- | --------------------------------------------- | ------- | ------------------ | ----------------------- |
11
+ | `deepseek-v4-flash` | DeepSeek-V4-Flash-0731 | July 31, 2026; re-post-trained public release | 1M | Text in / text out | 284B total / 13B active |
12
+ | `deepseek-v4-pro` | DeepSeek-V4-Pro-0813 | August 13, 2026; GA release | 1M | Text in / text out | 1.6T total / 49B active |
13
+
14
+ The [DeepSeek API change log](https://api-docs.deepseek.com/updates/) says both builds are selected with the plain API model ID. Do not add the version suffix to the API request or the extension override.
15
+
5
16
  ## Model ID overrides
6
17
 
7
18
  The extension's `deepseek-copilot.modelIdOverrides` setting changes the upstream API model IDs while keeping the normal DeepSeek entries in the Copilot model picker. The official DeepSeek Chat Completions API only accepts two `model` values — `deepseek-v4-flash` and `deepseek-v4-pro` — so the correct map for the official endpoint is just the defaults:
@@ -15,11 +26,33 @@ The extension's `deepseek-copilot.modelIdOverrides` setting changes the upstream
15
26
  }
16
27
  ```
17
28
 
18
- > **Warning:** Do **not** use the human-readable version label as a model ID. `DeepSeek-V4-Flash-0731` is only the version string shown on the pricing page, not a valid `model` field. Sending `deepseek-v4-flash-0731` to the official `https://api.deepseek.com` endpoint returns **HTTP 400 "Invalid request body format"**. The official endpoint already serves the latest (0731) build under the plain `deepseek-v4-flash` ID, so no override is needed there.
29
+ > **Warning:** Do **not** use the human-readable version labels as model IDs. `DeepSeek-V4-Flash-0731` and `DeepSeek-V4-Pro-0813` are version strings, not valid `model` fields. The official endpoint serves those builds under the plain `deepseek-v4-flash` and `deepseek-v4-pro` IDs, so no version-suffixed override is needed there. Sending a version-suffixed ID to `https://api.deepseek.com` can return **HTTP 400 "Invalid request body format"**.
19
30
 
20
31
  Only add an override when the configured `deepseek-copilot.baseUrl` expects a different model name (e.g., a third-party proxy). The left-hand keys are the extension's logical model keys; they are not arbitrary picker labels. The right-hand values are sent verbatim as the provider's `model` field.
21
32
 
22
- For Flash, select **DeepSeek V4 Flash** in Copilot Chat after reloading the window. The picker may still display “DeepSeek V4 Flash”; that is expected. The override is not a model registration or a way to add a new picker entry.
33
+ For Flash or Pro, select the corresponding **DeepSeek V4** entry in Copilot Chat after reloading the window. The picker may still display the family name without the build suffix; that is expected. The override is not a model registration or a way to add a new picker entry.
34
+
35
+ ## Updated benchmarks
36
+
37
+ DeepSeek's official August updates report the following agent-focused results, measured with the DeepSeek Harness at max effort for Flash and the GA Pro release:
38
+
39
+ - **Flash 0731:** Terminal-Bench 2.1 **82.7**, NL2Repo **54.2**, Cybergym **76.7**, DeepSWE **54.4**, Toolathlon Verified **70.3**, Agents' Last Exam **25.2**, AutomationBench (Public) **25.1**, DSBench-FullStack **68.7**, and DSBench-Hard **59.6**.
40
+ - **Pro 0813:** HLE without/with tools **42.7/60.0**, Terminal-Bench 2.1 **87.9**, NL2Repo **61.5**, Cybergym **83.3**, DeepSWE **62.7**, Toolathlon Verified **74.1**, Agents' Last Exam **25.7**, AutomationBench (Public) **31.8**, DSBench-FullStack **71.1**, and DSBench-Hard **67.2**.
41
+
42
+ The current Artificial Analysis snapshot exposed through OpenRouter reports **Flash 51.8 AA Intelligence / 69.1 Coding / 48.4 Agentic** and **Pro 53.2 AA Intelligence / 68.8 Coding / 49.6 Agentic**. The AA values are independent composite scores; DeepSeek's agent results above are vendor-reported and should not be treated as the same metric.
43
+
44
+ Sources: [DeepSeek update log](https://api-docs.deepseek.com/updates/), [Flash benchmark snapshot](https://openrouter.ai/deepseek/deepseek-v4-flash-0731), [Pro benchmark snapshot](https://openrouter.ai/deepseek/deepseek-v4-pro-0813), [Flash AA page](https://artificialanalysis.ai/models/deepseek-v4-flash), and [Pro AA page](https://artificialanalysis.ai/models/deepseek-v4-pro).
45
+
46
+ ## Current API pricing
47
+
48
+ DeepSeek switched V4 pricing to peak/off-peak rates at **16:00 UTC on August 16, 2026**. Prices below are USD per 1M tokens. Peak hours are **01:00-04:00 and 06:00-10:00 UTC**; off-peak rates are half the peak rates.
49
+
50
+ | API model | Cache hit | Cache miss | Output |
51
+ | ------------------- | ----------------------------- | --------------------------- | --------------------------- |
52
+ | `deepseek-v4-flash` | $0.007 off-peak / $0.014 peak | $0.22 off-peak / $0.44 peak | $0.66 off-peak / $1.32 peak |
53
+ | `deepseek-v4-pro` | $0.022 off-peak / $0.044 peak | $0.66 off-peak / $1.32 peak | $1.98 off-peak / $3.96 peak |
54
+
55
+ See the [official Models & Pricing page](https://api-docs.deepseek.com/quick_start/pricing) for the live rates and concurrency limits.
23
56
 
24
57
  ## Tool-list stabilization (`experimental.stabilizeToolList`)
25
58
 
@@ -18,9 +18,9 @@
18
18
  | ---------------------- | ------------------------------------------------------------------------------------------------------------------ |
19
19
  | Mode | **Direct** (no proxy) |
20
20
  | Billing | **Pay-as-You-Go** (PaaS API) — Coding Plan subscription exists but is **not usable** from VS Code custom endpoints |
21
- | Vision | ✅ Yes (`glm-5v-turbo` only) |
22
- | Tool calling | ✅ Yes (native multimodal tool use on `glm-5v-turbo`) |
23
- | Context | 1M (`glm-5.3` / `glm-5.2` Solid Lossless Context) |
21
+ | Vision | ✅ Yes (`glm-5.3-flash` / `glm-5v-turbo`) |
22
+ | Tool calling | ✅ Yes (native multimodal tool use on `glm-5.3-flash` / `glm-5v-turbo`) |
23
+ | Context | 1M (`glm-5.3-flash` / `glm-5.3` / `glm-5.2` Solid Lossless Context) |
24
24
  | Max output | 131072 |
25
25
  | Required `requestBody` | `thinking: { type: "enabled" }` + `reasoning_effort: "max"` (recommended) |
26
26
  | Endpoint (intl) | `https://api.z.ai/api/paas/v4/chat/completions` |
@@ -29,12 +29,13 @@
29
29
 
30
30
  ### Models
31
31
 
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) |
32
+ | Model | Vision | Context | Max output | Notes |
33
+ | --------------- | ------ | ------- | ---------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
34
+ | `glm-5.3-flash` | ✅ | 1M | 131072 | **New multimodal Flash** (Aug 26) — 320B/18B hybrid sparse+linear attention; AA **57.5**; always-thinking, `reasoning_effort` `low`/`high`/`max` (default `max`) ($0.15 / $0.50 per 1M) |
35
+ | `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) |
36
+ | `glm-5.2` | ❌ | 1M | 131072 | Previous flagship — "Opus-level" long-context engineering & agentic coding; thinking `enabled` ($1.40 / $4.40 per 1M) |
37
+ | `glm-5.1` | ❌ | 200K | 131072 | Previous flagship — long-horizon / 8h autonomous work; thinking `enabled` ($1.40 / $4.40 per 1M) |
38
+ | `glm-5v-turbo` | ✅ | 200K | 131072 | Multimodal **coding** model — vision-based agentic coding; thinking `enabled` ($1.20 / $4.00 per 1M) |
38
39
 
39
40
  > 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.
40
41
 
@@ -64,6 +65,22 @@
64
65
  "apiKey": "",
65
66
  "apiType": "chat-completions",
66
67
  "models": [
68
+ {
69
+ "id": "glm-5.3-flash",
70
+ "name": "GLM 5.3 Flash (multimodal)",
71
+ "url": "https://api.z.ai/api/paas/v4/chat/completions",
72
+ "toolCalling": true,
73
+ "vision": true,
74
+ "streaming": true,
75
+ "maxInputTokens": 1048576,
76
+ "maxOutputTokens": 131072,
77
+ "requestBody": {
78
+ "thinking": { "type": "enabled" },
79
+ "reasoning_effort": "max",
80
+ "temperature": 1.0,
81
+ "top_p": 0.95
82
+ }
83
+ },
67
84
  {
68
85
  "id": "glm-5.3",
69
86
  "name": "GLM 5.3 (text)",
@@ -150,10 +167,10 @@
150
167
 
151
168
  - **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).
152
169
  - **`tool_choice` only supports `auto`** — don't override it (VS Code's default is `auto`).
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.
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/).
156
- - **Context caching** is automatic — `usage.prompt_tokens_details.cached_tokens` reports cache hits; cache writes are currently free.
170
+ - **`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. (Note: Z.ai's GLM-5.3-Flash docs recommend `thinking.clear_thinking: false` for clients that **do** preserve `reasoning_content` — e.g. Claude Code / agent SDKs — not for the VS Code custom-endpoint path.)
171
+ - **GLM 5.3 and GLM 5.3 Flash are 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` / `glm-5.3-flash`.
172
+ - **Vision** is supported on `glm-5.3-flash` (native multimodal — the first in the GLM-5 series; text + image input, text output) and `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/). **Validated 2026-08-28 on `glm-5.3-flash`:** both vision surfaces work through the custom endpoint — chat image attachments (base64 `image_url`) and the `view_image` tool on workspace files. Fine-grained text, layout, and image content were read correctly in both tests.
173
+ - **Context caching** is automatic — `usage.prompt_tokens_details.cached_tokens` reports cache hits; cache writes are currently free. Cache reads for `glm-5.3-flash` are $0.03/M (list; $0.015/M during the launch promo).
157
174
 
158
175
  ## Troubleshooting
159
176
 
@@ -174,4 +191,6 @@
174
191
 
175
192
  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.
176
193
 
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).
194
+ > **Cache writes** are currently **Limited-time Free** for all models. Cached-input pricing is roughly 18–20% of the input price (e.g. `$1.40` input → `$0.26` cached for `glm-5.3` / `glm-5.2` / `glm-5.1`; `$0.15` → `$0.03` for `glm-5.3-flash`).
195
+ >
196
+ > **GLM 5.3 Flash** launched **August 26, 2026** at **$0.15 / $0.03 / $0.50** per 1M (input / cached / output) — currently **50% off** (effective **$0.075 / $0.015 / $0.25**) through **September 9, 2026** (24:00 UTC+8). 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 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.
3
+ > **Updated:** August 28, 2026 — **GLM 5.3 Flash** added (footnote ²⁰): Z.ai's first native multimodal GLM-5 model (August 26, 2026), AA Intelligence Index **57.5**, launch pricing **$0.15 / $0.03 / $0.50** (50% off through September 9). It is now the **cheapest cost-per-intelligence row** in the table (~$0.0022). August 20: **DeepSeek V4 Flash 0731** and **DeepSeek V4 Pro 0813** refreshed (footnote ¹⁹): current builds, AA Intelligence Index **51.8** / **53.2**, and peak/off-peak API pricing effective August 16. Pro's official GA agent benchmark update is documented in [docs/models/deepseek.md](models/deepseek.md). August 19: **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
  >
@@ -18,47 +18,48 @@
18
18
  >
19
19
  > Code completions remain unlimited and **not** billed. Auto model selection gets a 10% discount.
20
20
 
21
- All prices below are in **USD per 1M tokens** (non-cached). To convert to AI credits, multiply by 100 (e.g., $5.00/1M = 500 credits/1M).
21
+ All prices below are in **USD per 1M tokens** (non-cached). To convert to AI credits, multiply by 100 (e.g., $5.00/1M = 500 credits/1M). DeepSeek V4 rows use peak rates for the comparison; its official off-peak rates are half.
22
22
 
23
23
  All models are listed together below, sorted by Cost per intelligence ascending (lower is better). Models without a Cost per intelligence are ordered by estimated session cost ascending. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
24
24
 
25
- | Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
26
- | -------------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
27
- | **DeepSeek V4 Flash 0731** | DeepSeek | **~$0.0019** | **51.8** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
28
- | **MiMo V2.5** | Xiaomi | **~$0.0026** | **38.0** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
29
- | **GPT-5.6 Luna** | OpenAI | **~$0.0042** | **52.3** | $0.20 | $0.02 | $1.20 | ~$0.22 | 1M |
30
- | **MiniMax M3** | MiniMax | **~$0.0060** | **45.4** | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | ~$0.27 | 1M |
31
- | **DeepSeek V4 Pro** | DeepSeek | **~$0.0066** | **45.3** | $0.435 | $0.003625 | $0.87 | ~$0.30 | 1M |
32
- | **MiMo V2.5 Pro** | Xiaomi | **~$0.0070** | **42.9** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
33
- | **Qwen 3.7 Plus** ¹³ | DashScope | **~$0.0074** | **39.4** | $0.32 (≤256K) / $0.40 (>256K) | $0.064 | $1.28 (≤256K) / $1.60 (>256K) | ~$0.29 | 1M |
34
- | **MiniMax M3 Priority**⁵ | MiniMax | **~$0.0090** | **45.4** | $0.90 (≤512K) / $1.80 (>512K) | $0.18 (≤512K) / $0.36 (>512K) | $3.60 (≤512K) / $7.20 (>512K) | ~$0.41 | 1M |
35
- | **Gemini 3.7 Flash** ¹⁵ | Google | **~$0.013** | **56** | $0.75 | $0.075 | $3.75 | ~$0.75 | 1M |
36
- | **Qwen 3.6 Plus** ¹⁷ | DashScope | **~$0.014** | **40.0** | $0.50 | $0.05 | $3.00 | ~$0.55 | 1M |
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 |
39
- | **Kimi K2.6** | Moonshot | **~$0.020** | **45.0** | $0.95 | $0.16 | $4.00 | ~$0.88 | 256K |
40
- | **GPT-5.4 mini** | OpenAI | **~$0.020** | **40.9** | $0.75 | $0.075 | $4.50 | ~$0.83 | 400K |
41
- | **Kimi K2.7 Code** | Moonshot | **~$0.020** | **43.0** | $0.95 | $0.19 | $4.00 | ~$0.88 | 262K |
42
- | **GLM 5.2** ⁴ | Z.ai | **~$0.022** | **52.6** | $1.40 | $0.26 | $4.40 | ~$1.14 | 1M |
43
- | **Qwen 3.7 Max** ¹³ | DashScope | **~$0.025** | **46.7** | $1.475 (≤1M) | $0.295 | $4.425 (≤1M) | ~$1.18 | 1M |
44
- | **Grok 4.6** ¹⁴ | xAI | **~$0.026** | **61** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
45
- | **Qwen 3.8 Max** ¹¹ | DashScope | **~$0.028** | **58.1** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
46
- | **GLM 5.1** | Z.ai | **~$0.028** | **41.0** | $1.40 | $0.26 | $4.40 | ~$1.14 | 200K |
47
- | **GLM 5V Turbo** | Z.ai | **~$0.029** | **35.0** ³ | $1.20 | $0.24 | $4.00 | ~$1.00 | 200K |
48
- | **Grok 4.5** ¹² | xAI | **~$0.029** | **55.8** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
49
- | **Gemini 3.5 Flash** | Google | **~$0.032** | **52.0** | $1.50 | $0.15 | $9.00 | ~$1.65 | 1M |
50
- | **GPT-5.6 Terra** | OpenAI | **~$0.039** | **56.6** | $2.00 | $0.20 | $12.00 | ~$2.20 | 1M |
51
- | **Gemini 3.1 Pro** | Google | **~$0.046** | **47.7** | $2.00¹ | $0.20 | $12.00¹ | ~$2.20 | 1M |
52
- | **Kimi K3** ⁷ | Moonshot | **~$0.050** | **59.7** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
53
- | **GPT-5.4** | OpenAI | **~$0.052** | **53.1** | $2.50 | $0.25 | $15.00 | ~$2.75 | 1M |
54
- | **Claude Sonnet 5** ⁶ | Anthropic | **~$0.054** | **55.3** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
55
- | **Claude Sonnet 4.6** | Anthropic | **~$0.062** | **48.4** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
56
- | **Claude Opus 5** ¹⁰ | Anthropic | **~$0.079** | **63.1** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
57
- | **Claude Opus 4.8** | Anthropic | **~$0.087** | **57.3** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
58
- | **GPT-5.6 Sol** | OpenAI | **~$0.090** | **60.9** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
59
- | **Claude Opus 4.7** | Anthropic | **~$0.091** | **55.0** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
60
- | **GPT-5.5** | OpenAI | **~$0.098** | **56.3** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
61
- | **Claude Fable 5** ¹⁶ | Anthropic | **~$0.161** | **62.1** | $10.00 | $1.00 | $50.00 | ~$10.00 | 1M |
25
+ | Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
26
+ | ----------------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
27
+ | **GLM 5.3 Flash** ²⁰ | Z.ai | **~$0.0022** | **57.5** | $0.15 | $0.03 | $0.50 | ~$0.13 | 1M |
28
+ | **MiMo V2.5** | Xiaomi | **~$0.0026** | **38.0** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
29
+ | **GPT-5.6 Luna** | OpenAI | **~$0.0042** | **52.3** | $0.20 | $0.02 | $1.20 | ~$0.22 | 1M |
30
+ | **MiniMax M3** | MiniMax | **~$0.0060** | **45.4** | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | ~$0.27 | 1M |
31
+ | **DeepSeek V4 Flash 0731** ¹⁹ | DeepSeek | **~$0.0068** | **51.8** | $0.44 | $0.014 | $1.32 | ~$0.35 | 1M |
32
+ | **MiMo V2.5 Pro** | Xiaomi | **~$0.0070** | **42.9** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
33
+ | **Qwen 3.7 Plus** ¹³ | DashScope | **~$0.0074** | **39.4** | $0.32 (≤256K) / $0.40 (>256K) | $0.064 | $1.28 (≤256K) / $1.60 (>256K) | ~$0.29 | 1M |
34
+ | **MiniMax M3 Priority**⁵ | MiniMax | **~$0.0090** | **45.4** | $0.90 (≤512K) / $1.80 (>512K) | $0.18 (≤512K) / $0.36 (>512K) | $3.60 (≤512K) / $7.20 (>512K) | ~$0.41 | 1M |
35
+ | **Gemini 3.7 Flash** ¹⁵ | Google | **~$0.013** | **56** | $0.75 | $0.075 | $3.75 | ~$0.75 | 1M |
36
+ | **Qwen 3.6 Plus** ¹⁷ | DashScope | **~$0.014** | **40.0** | $0.50 | $0.05 | $3.00 | ~$0.55 | 1M |
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 |
39
+ | **Kimi K2.6** | Moonshot | **~$0.020** | **45.0** | $0.95 | $0.16 | $4.00 | ~$0.88 | 256K |
40
+ | **DeepSeek V4 Pro 0813** ¹⁹ | DeepSeek | **~$0.020** | **53.2** | $1.32 | $0.044 | $3.96 | ~$1.06 | 1M |
41
+ | **GPT-5.4 mini** | OpenAI | **~$0.020** | **40.9** | $0.75 | $0.075 | $4.50 | ~$0.83 | 400K |
42
+ | **Kimi K2.7 Code** | Moonshot | **~$0.020** | **43.0** | $0.95 | $0.19 | $4.00 | ~$0.88 | 262K |
43
+ | **GLM 5.2** ⁴ | Z.ai | **~$0.022** | **52.6** | $1.40 | $0.26 | $4.40 | ~$1.14 | 1M |
44
+ | **Qwen 3.7 Max** ¹³ | DashScope | **~$0.025** | **46.7** | $1.475 (≤1M) | $0.295 | $4.425 (≤1M) | ~$1.18 | 1M |
45
+ | **Grok 4.6** ¹⁴ | xAI | **~$0.026** | **61** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
46
+ | **Qwen 3.8 Max** ¹¹ | DashScope | **~$0.028** | **58.1** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
47
+ | **GLM 5.1** | Z.ai | **~$0.028** | **41.0** | $1.40 | $0.26 | $4.40 | ~$1.14 | 200K |
48
+ | **GLM 5V Turbo** | Z.ai | **~$0.029** | **35.0** ³ | $1.20 | $0.24 | $4.00 | ~$1.00 | 200K |
49
+ | **Grok 4.5** ¹² | xAI | **~$0.029** | **55.8** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
50
+ | **Gemini 3.5 Flash** | Google | **~$0.032** | **52.0** | $1.50 | $0.15 | $9.00 | ~$1.65 | 1M |
51
+ | **GPT-5.6 Terra** | OpenAI | **~$0.039** | **56.6** | $2.00 | $0.20 | $12.00 | ~$2.20 | 1M |
52
+ | **Gemini 3.1 Pro** | Google | **~$0.046** | **47.7** | $2.00¹ | $0.20 | $12.00¹ | ~$2.20 | 1M |
53
+ | **Kimi K3** ⁷ | Moonshot | **~$0.050** | **59.7** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
54
+ | **GPT-5.4** | OpenAI | **~$0.052** | **53.1** | $2.50 | $0.25 | $15.00 | ~$2.75 | 1M |
55
+ | **Claude Sonnet 5** ⁶ | Anthropic | **~$0.054** | **55.3** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
56
+ | **Claude Sonnet 4.6** | Anthropic | **~$0.062** | **48.4** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
57
+ | **Claude Opus 5** ¹⁰ | Anthropic | **~$0.079** | **63.1** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
58
+ | **Claude Opus 4.8** | Anthropic | **~$0.087** | **57.3** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
59
+ | **GPT-5.6 Sol** | OpenAI | **~$0.090** | **60.9** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
60
+ | **Claude Opus 4.7** | Anthropic | **~$0.091** | **55.0** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
61
+ | **GPT-5.5** | OpenAI | **~$0.098** | **56.3** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
62
+ | **Claude Fable 5** ¹⁶ | Anthropic | **~$0.161** | **62.1** | $10.00 | $1.00 | $50.00 | ~$10.00 | 1M |
62
63
 
63
64
  ¹ Gemini 3.1 Pro pricing applies to prompts ≤200K tokens.
64
65
 
@@ -94,11 +95,15 @@ All models are listed together below, sorted by Cost per intelligence ascending
94
95
 
95
96
  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
97
 
98
+ ¹⁹ **DeepSeek V4 Flash 0731** and **DeepSeek V4 Pro 0813** are the current API builds. Flash's AA Intelligence Index is **51.8** and Pro's is **53.2** (current OpenRouter/Artificial Analysis snapshots). Both are text-only with 1M context; Flash has 284B total / 13B active parameters and Pro has 1.6T total / 49B active. DeepSeek's official V4 pricing changed on August 16, 2026 to peak/off-peak rates: Flash is **$0.44 / $0.014 / $1.32** and Pro is **$1.32 / $0.044 / $3.96** per 1M input/cache-hit/output at peak, with off-peak rates at half those values. See the [DeepSeek pricing page](https://api-docs.deepseek.com/quick_start/pricing), [update log](https://api-docs.deepseek.com/updates/), and [canonical model record](models/deepseek.md).
99
+
100
+ ²⁰ **GLM 5.3 Flash** (`glm-5.3-flash`) is Z.ai's first native multimodal model in the GLM-5 series (released **August 26, 2026**; tested pre-release as "ox-alpha"). Hybrid sparse + linear attention architecture with 320B total / 18B active parameters (open weights, MIT license) and a 1M-token context window; text + image input, text output. AA Intelligence Index **57.5** (OpenRouter's AA-sourced benchmark; AA's [model page](https://artificialanalysis.ai/models/glm-5-3-flash) lists a rounded **57** and ranks it **#3/110** within its open-weights size class), Coding **71.5**, Agentic **58.2**. Launch pricing is **$0.15** input / **$0.03** cached / **$0.50** output per 1M (list), with a **50% off** launch promo (effective **$0.075 / $0.015 / $0.25**) through **September 9, 2026** (24:00 UTC+8). At list price the modeled session cost is ~$0.13 and the cost per intelligence is ~$0.0022 — the cheapest row in this table. Always-thinking: `thinking.type` only supports `enabled`, `reasoning_effort` accepts `low` / `high` / `max` (default `max`). See the [Z.ai model page](https://docs.z.ai/guides/llm/glm-5.3-flash) and [AA model page](https://artificialanalysis.ai/models/glm-5-3-flash).
101
+
97
102
  Cost per intelligence = estimated session cost ÷ Intelligence Index score. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
98
103
 
99
104
  > **Notes:**
100
105
  >
101
- > - **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).
106
+ > - **DeepSeek V4** input pricing shown is the **peak cache miss** price. Peak cache hits are $0.014/M for Flash and $0.044/M for Pro; off-peak rates are half. See footnote ¹⁹ for the full schedule.
102
107
  > - **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.
103
108
  > - **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+, Opus 5, Sonnet 5, and Fable 5 use a new tokenizer that produces approximately 30% more tokens for the same text.
104
109
  > - **OpenAI** models support cached input at 0.1× base input rate.
@@ -108,13 +113,13 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
108
113
  > - **DashScope** offers a **free quota** of 1M input + 1M output tokens per model, valid for 90 days.
109
114
  > - **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.
110
115
  > - **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.
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.
116
+ > - **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; $0.03/M for 5.3 Flash (list; $0.015/M during the launch promo).
112
117
  > - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion.
113
118
  > - For typical Copilot chat usage (short-to-medium prompts), you'll almost always fall in the lowest pricing tier.
114
119
 
115
120
  > **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.)
116
121
 
117
- > Prices last verified: August 19, 2026. Always check the official pages for the latest rates:
122
+ > Prices last verified: August 28, 2026. Always check the official pages for the latest rates:
118
123
  >
119
124
  > - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
120
125
  > - [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": "2.1.5",
3
+ "version": "2.1.7",
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",