copilot-custom-endpoint 3.3.0 → 3.3.2

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
@@ -67,7 +67,7 @@ Open the setup guide for the model you picked (links in the table above) and cop
67
67
  2. Search for **"Chat: Utility Small Model"** (setting ID: `chat.lm.utilitySmallModel`).
68
68
  3. Pick the **fastest, cheapest model** available to you from the dropdown. Good choices:
69
69
  - **GLM 5.3 Flash** — if you have [GLM configured](docs/models/glm.md) (cheapest custom-endpoint option, ~$0.13/session).
70
- - **GPT-5.6 Luna** — if it is available through your native Copilot models (fast, ~$0.22/session).
70
+ - **GPT-6 Luna** — if it is available through your native Copilot models (fast, ~$0.10/session).
71
71
  - **MiMo V2.6 Flash** — if you already have Xiaomi MiMo configured (low-cost multimodal option, ~$0.10/session).
72
72
  - **Default** — if you still have native Copilot model access, this lets VS Code use its built-in fast model.
73
73
  4. The setting takes effect immediately — no restart needed.
@@ -121,10 +121,11 @@ It approximates the cost of one point on the AA Intelligence Index under the com
121
121
 
122
122
  For example, GLM 5.3 Flash is `(0.5 × $0.15) + (0.1 × $0.50) = $0.125`, shown as `~$0.13`. Cached-input discounts are not included. Actual costs vary with context length, output length, caching, pricing tiers, promotions, and provider billing. DeepSeek estimates use peak rates; official off-peak rates are half.
123
123
 
124
- The current AA values come from OpenRouter's September 22 model metadata and ranking card; **every pricing cell comes from first-party provider pricing or GitHub Copilot's official billing table, never OpenRouter.** The OpenRouter ranking card places unversioned Qwen3.8 Max at **53.4 (#2)**, while the exact 0902 API metadata row is **45.4**. Qwen Cloud PAYG pricing remains **$2 / $0.25 implicit cache / $6** for Qwen3.8 Max; its separate Token Plan is not the PAYG rate table. This refresh records Gemini 3.8 Flash as **Copilot-native** and adds Xiaomi MiMo V2.6 and xAI Grok 4.7 as **Copilot-native** models, using the current AA v4.3.2 composites.
124
+ The current AA values come from OpenRouter's September 23 model metadata and ranking card; **every pricing cell comes from first-party provider pricing or GitHub Copilot's official billing table, never OpenRouter.** The OpenRouter ranking card places unversioned Qwen3.8 Max at **53.4 (#2)**, while the exact 0902 API metadata row is **45.4**. Qwen Cloud PAYG pricing remains **$2 / $0.25 implicit cache / $6** for Qwen3.8 Max; its separate Token Plan is not the PAYG rate table. This refresh records Gemini 3.8 Flash, Grok 4.7, GPT-6 Sol, GPT-6 Luna, and Claude Opus 5.5 as **Copilot-native** models, using current AA v4.3.2 composites.
125
125
 
126
126
  | Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
127
127
  | ---------------------------- | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
128
+ | **GPT-6 Luna** | OpenAI | **~$0.0027** | **37.3** | ~$0.10 | ✅ | 1M |
128
129
  | **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.8** | ~$0.13 | ✅ | 1M |
129
130
  | **GPT-5.6 Luna** | OpenAI | **~$0.0059** | **37.3** | ~$0.22 | ✅ | 1M |
130
131
  | **MiMo V2.6 Pro** | Xiaomi | **~$0.0066** | **46.3** | ~$0.30 | ✅ | 1M |
@@ -137,10 +138,12 @@ The current AA values come from OpenRouter's September 22 model metadata and ran
137
138
  | **Grok 4.7** | xAI | **~$0.0345** | **46.4** | ~$1.60 | ✅ | 500K |
138
139
  | **Qwen 3.8 Max (0902)** | DashScope | **~$0.0352** | **45.4** | ~$1.60 | ✅ | 1M |
139
140
  | **Grok 4.6** | xAI | **~$0.0361** | **44.3** | ~$1.60 | ✅ | 500K |
141
+ | **GPT-6 Sol** | OpenAI | **~$0.0421** | **47.5** | ~$2.00 | ✅ | 1M |
140
142
  | **GPT-5.6 Terra** | OpenAI | **~$0.0523** | **42.1** | ~$2.20 | ✅ | 1M |
141
143
  | **Claude Sonnet 5** | Anthropic | **~$0.0524** | **38.2** | ~$2.00 | ✅ | 1M |
142
144
  | **MiMo V2.6 Pro UltraSpeed** | Xiaomi | **~$0.0658** | **46.3** | ~$3.05 | ✅ | 1M |
143
145
  | **Kimi K3** | Moonshot | **~$0.0688** | **43.6** | ~$3.00 | ✅ | 1M |
146
+ | **Claude Opus 5.5** | Anthropic | **~$0.0694** | **57.6** | ~$4.00 | ✅ | 1M |
144
147
  | **GPT-5.6 Sol** | OpenAI | **~$0.0851** | **47.0** | ~$4.00 | ✅ | 1M |
145
148
  | **Claude Opus 5** | Anthropic | **~$0.0984** | **50.8** | ~$5.00 | ✅ | 1M |
146
149
  | **Claude Fable 5.1** | Anthropic | **~$0.1873** | **53.4** | ~$10.00 | ✅ | 1M |
@@ -148,14 +151,15 @@ The current AA values come from OpenRouter's September 22 model metadata and ran
148
151
  | **Claude Fable 5** | Anthropic | **~$0.2016** | **49.6** | ~$10.00 | ✅ | 1M |
149
152
  | **MiMo V2.6 Flash** | Xiaomi | — | — | ~$0.10 | ✅ | 1M |
150
153
 
151
- > `MiMo V2.6 Pro UltraSpeed` uses the MiMo V2.6 Pro benchmark score because it is the same-quality latency tier; no independent composite is published. `MiniMax M3 Priority` is intentionally omitted from this snapshot because it is the same model with a priority service tier; the full pricing table documents its separate tier cost.
154
+ > `MiMo V2.6 Pro UltraSpeed` uses the MiMo V2.6 Pro benchmark score because it is the same-quality latency tier; no independent composite is published. `MiniMax M3 Priority` is intentionally omitted from this snapshot because it is the same model with a priority service tier; the full pricing table documents its separate tier cost. `MiMo V2.6 Flash` has no OpenRouter composite score; Xiaomi's published launch benchmarks for it are recorded in [docs/benchmarks.md](docs/benchmarks.md).
155
+ > GPT-6 Sol and Luna use standard rates up to 272K input tokens; requests above that threshold have higher input/cache and output rates. GitHub Copilot also bills cache writes separately. Plan access differs: Sol requires Pro+ or higher, Luna is available from Pro, and Claude Opus 5.5 requires Pro+ or higher.
152
156
 
153
157
  > Detailed pricing, benchmark provenance, and model-specific notes live in [docs/pricing.md](docs/pricing.md) and [docs/benchmarks.md](docs/benchmarks.md). This page stays focused on setup and model selection. For a copy-paste config containing **all providers at once**, see [docs/example-config.md](docs/example-config.md).
154
158
 
155
159
  > **👤 Personal picks** —
156
160
  >
157
- > - **GLM 5.3 Flash** — the lowest cost per intelligence in this table (~$0.0030), at about $0.13/session with vision.
158
- > - **GPT-5.6 Luna** — the lowest cost per intelligence among Copilot-native scored models (~$0.0059), at about $0.22/session with vision.
161
+ > - **GPT-6 Luna** — the lowest cost per intelligence in this table (~$0.0027), at about $0.10/session with vision.
162
+ > - **GLM 5.3 Flash** — the lowest cost per intelligence among custom-endpoint models (~$0.0030), at about $0.13/session with vision.
159
163
 
160
164
  ## Companion tools
161
165
 
@@ -208,7 +212,7 @@ GitHub ships a first-party MCP server (and it's even bundled into Copilot), so a
208
212
  2. If the provider needs request rewriting, add a proxy under `proxy/`.
209
213
  3. Submit a PR.
210
214
 
211
- ## Limitations
215
+ The current AA values come from OpenRouter's September 23 model metadata and ranking card; **every pricing cell comes from first-party provider pricing or GitHub Copilot's official billing table, never OpenRouter.** The OpenRouter ranking card places unversioned Qwen3.8 Max at **53.4 (#2)**, while the exact 0902 API metadata row is **45.4**. Qwen Cloud PAYG pricing remains **$2 / $0.25 implicit cache / $6** for Qwen3.8 Max; its separate Token Plan is not the PAYG rate table. This refresh records Gemini 3.8 Flash, Grok 4.7, GPT-6 Sol, GPT-6 Luna, and Claude Opus 5.5 as **Copilot-native** models, using current AA v4.3.2 composites.
212
216
 
213
217
  - **Chat only.** Inline completions, semantic search, and next-edit suggestions still need a GitHub-hosted model.
214
218
  - Each proxy is tuned for a specific provider family. Don't point the Kimi proxy at an arbitrary OpenAI-compatible endpoint.
package/docs/pricing.md CHANGED
@@ -1,6 +1,6 @@
1
1
  # Pricing
2
2
 
3
- > **Latest refresh (September 23, 2026):** OpenRouter's current metadata uses Artificial Analysis v4.3.2 composites. MiMo V2.6 Pro is **46.3**, Grok 4.7 is **46.4**, and the current values for existing rows are refreshed below. Gemini 3.8 Flash is now available as a GitHub Copilot native model. Xiaomi released the V2.6 Pro, Flash, and Pro UltraSpeed models on September 22; the September 23 roster cleanup removes two retired legacy models. xAI released Grok 4.7 on September 21 at the same short-context rates as Grok 4.6: **$2 / $0.50 cache hit / $6**. The table preserves Qwen's 0803 ranking-card value (**53.4**) and 0902 metadata value (**45.4**) as separate records. The current table is authoritative for present comparisons.
3
+ > **Latest refresh (September 23, 2026):** OpenRouter's current metadata uses Artificial Analysis v4.3.2 composites. The September 22 Copilot releases add Claude Opus 5.5 (**57.6**), GPT-6 Sol (**47.5**), and GPT-6 Luna (**37.3**) to the roster. The API list rates are **$4 / $0.20 cache hit / $20** for Opus 5.5, **$2 / $0.20 / $10** for Sol, and **$0.10 / $0.01 / $0.50** for Luna. MiMo V2.6 Pro is **46.3**, Grok 4.7 is **46.4**, and current values for existing rows are refreshed below. Gemini 3.8 Flash is also available as a GitHub Copilot native model. Xiaomi released the V2.6 Pro, Flash, and Pro UltraSpeed models on September 22; the September 23 roster cleanup removes two retired legacy models. xAI released Grok 4.7 on September 21 at the same short-context rates as Grok 4.6: **$2 / $0.50 cache hit / $6**. The table preserves Qwen's 0803 ranking-card value (**53.4**) and 0902 metadata value (**45.4**) as separate records. The current table is authoritative for present comparisons.
4
4
 
5
5
  > **⏰ June 1, 2026 — GitHub Copilot switched to usage-based billing (AI Credits) today.**
6
6
  >
@@ -24,6 +24,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
24
24
 
25
25
  | Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
26
26
  | ---------------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
27
+ | **GPT-6 Luna** | OpenAI | **~$0.0027** | **37.3** | $0.10 | $0.01 | $0.50 | ~$0.10 | 1M |
27
28
  | **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.8** | $0.15 | $0.03 | $0.50 | ~$0.13 | 1M |
28
29
  | **GPT-5.6 Luna** | OpenAI | **~$0.0059** | **37.3** | $0.20 | $0.02 | $1.20 | ~$0.22 | 1M |
29
30
  | **MiMo V2.6 Pro** | Xiaomi | **~$0.0066** | **46.3** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
@@ -37,10 +38,12 @@ All models are listed together below, sorted by Cost per intelligence ascending
37
38
  | **Grok 4.7** | xAI | **~$0.0345** | **46.4** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
38
39
  | **Qwen 3.8 Max (0902)** | DashScope | **~$0.0352** | **45.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
39
40
  | **Grok 4.6** | xAI | **~$0.0361** | **44.3** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
41
+ | **GPT-6 Sol** | OpenAI | **~$0.0421** | **47.5** | $2.00 | $0.20 | $10.00 | ~$2.00 | 1M |
40
42
  | **GPT-5.6 Terra** | OpenAI | **~$0.0523** | **42.1** | $2.00 | $0.20 | $12.00 | ~$2.20 | 1M |
41
43
  | **Claude Sonnet 5** | Anthropic | **~$0.0524** | **38.2** | $2.00 | $0.20 | $10.00 | ~$2.00 | 1M |
42
44
  | **MiMo V2.6 Pro UltraSpeed** | Xiaomi | **~$0.0658** | **46.3** | $4.35 | $0.036 | $8.70 | ~$3.05 | 1M |
43
45
  | **Kimi K3** | Moonshot | **~$0.0688** | **43.6** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
46
+ | **Claude Opus 5.5** | Anthropic | **~$0.0694** | **57.6** | $4.00 | $0.20 | $20.00 | ~$4.00 | 1M |
44
47
  | **GPT-5.6 Sol** | OpenAI | **~$0.0851** | **47.0** | $4.00 | $0.40 | $20.00 | ~$4.00 | 1M |
45
48
  | **Claude Opus 5** | Anthropic | **~$0.0984** | **50.8** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
46
49
  | **Claude Fable 5.1** | Anthropic | **~$0.1873** | **53.4** | $10.00 | $0.25 | $50.00 | ~$10.00 | 1M |
@@ -54,26 +57,35 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
54
57
  >
55
58
  > - **DeepSeek** input pricing shown is the **peak cache miss** price. Peak cache hits are $0.006/M for V4.1 Flash and $0.044/M for Pro; off-peak rates are half. See the [DeepSeek pricing page](https://api-docs.deepseek.com/quick_start/pricing) for the full schedule.
56
59
  > - **MiMo** input pricing shown is the **cache miss** price. Cache hits are essentially free for V2.6 Pro ($0.0036/M, ~120× cheaper), V2.6 Flash ($0.0028/M, ~50× cheaper), and V2.6 Pro UltraSpeed ($0.036/M, ~120× cheaper). A Xiaomi price cut took effect on 2026-05-27.
57
- > - **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 5, Sonnet 5, and Fable 5 / 5.1 use a new tokenizer that produces approximately 30% more tokens for the same text.
58
- > - **OpenAI** models support cached input at 0.1× base input rate.
60
+ > - **Anthropic (Claude)** cache reads and cache writes are billed separately. Claude Opus 5.5 cache reads are $0.20/M; cache writes are $5/M for 5 minutes or $8/M for 1 hour. Fast mode costs $8/M input and $40/M output. Opus 5.5, Opus 5, Sonnet 5, and Fable 5 / 5.1 use a newer tokenizer that produces approximately 30% more tokens for the same text.
61
+ > - **OpenAI** models support cached input at 0.1× base input rate. GPT-6 Sol and Luna also bill cache writes separately at 1.25× input. The GPT-6 rows show standard rates through 272K input; for requests >272K, input and cache-read rates double and output is 1.5×.
59
62
  > - **Qwen** models use **tiered pricing** — determined by total input tokens per request. Prices above are for non-thinking mode.
60
63
  > - **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.
61
64
  > - **DashScope** offers a **free quota** of 1M input + 1M output tokens per model, valid for 90 days.
62
65
  > - **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.
63
66
  > - **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.
64
67
  > - **GLM** models support prompt caching — cache hits are priced at $0.26/M for 5.3 and $0.03/M for 5.3 Flash (list; $0.015/M during the launch promo).
65
- > - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion.
68
+ > - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion. MiMo V2.6 Flash has no OpenRouter composite score; Xiaomi's published launch benchmarks for it are recorded in [docs/benchmarks.md](benchmarks.md).
66
69
  > - For typical Copilot chat usage (short-to-medium prompts), you'll almost always fall in the lowest pricing tier.
67
70
 
68
71
  > **How long does 7,000 credits last?** A Pro+ subscriber running 50-turn sessions can estimate monthly capacity by multiplying each modeled session cost by 100 to convert it to AI credits, then mixing models as needed.
69
72
 
70
- > Prices last verified: September 22, 2026. Always check the official pages for the latest rates:
73
+ > Prices last verified: September 23, 2026. Always check the official pages for the latest rates:
71
74
  >
72
75
  > - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
73
76
  > - [OpenAI pricing](https://openai.com/api/pricing/)
74
77
  > - [OpenAI GPT-5.6 announcement](https://openai.com/index/gpt-5-6/)
75
78
  > - [OpenAI GPT-5.6 price update](https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/)
79
+ > - [OpenAI GPT-6 Sol and Luna announcement](https://openai.com/index/introducing-gpt-6-sol-and-luna/)
80
+ > - [OpenAI GPT-6 Sol API details](https://developers.openai.com/api/docs/models/gpt-6-sol)
81
+ > - [OpenAI GPT-6 Luna API details](https://developers.openai.com/api/docs/models/gpt-6-luna)
76
82
  > - [Anthropic (Claude) pricing](https://platform.claude.com/docs/en/about-claude/pricing)
83
+ > - [Anthropic Claude Opus 5.5 announcement](https://www.anthropic.com/claude-opus-5-5)
84
+ > - [Anthropic Opus 5.5 API docs](https://platform.claude.com/docs/en/models/opus-5-5/overview)
85
+ > - [GitHub Copilot GPT-6 Sol and Luna release](https://github.blog/changelog/2026-09-22-openais-gpt-6-sol-and-gpt-6-luna-now-available)
86
+ > - [GitHub Copilot Claude Opus 5.5 release](https://github.blog/changelog/2026-09-22-claude-opus-5-5-is-now-available-in-github-copilot)
87
+ > - [GitHub Copilot supported models](https://docs.github.com/en/copilot/reference/ai-models/supported-models)
88
+ > - [Artificial Analysis GPT-6 Sol](https://artificialanalysis.ai/models/gpt-6-sol), [GPT-6 Luna](https://artificialanalysis.ai/models/gpt-6-luna), and [Claude Opus 5.5](https://artificialanalysis.ai/models/claude-opus-5-5)
77
89
  > - [Google Gemini pricing](https://ai.google.dev/pricing)
78
90
  > - [DashScope pricing](https://www.alibabacloud.com/help/en/model-studio/billing-for-model-studio)
79
91
  > - [DeepSeek pricing](https://api-docs.deepseek.com/quick_start/pricing)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "copilot-custom-endpoint",
3
- "version": "3.3.0",
3
+ "version": "3.3.2",
4
4
  "description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2, Qwen 3.x & MiMo V2.6",
5
5
  "license": "MIT",
6
6
  "type": "module",
@@ -57,4 +57,4 @@
57
57
  "dependencies": {
58
58
  "dotenv": "^17.4.2"
59
59
  }
60
- }
60
+ }