copilot-custom-endpoint 3.4.1 → 3.4.2
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 +7 -5
- package/docs/pricing.md +11 -5
- package/package.json +4 -4
package/README.md
CHANGED
|
@@ -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
|
|
124
|
+
The current AA values come from OpenRouter's 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 (#3)**, 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 snapshot records Gemini 3.8 Flash, Grok 4.7, GPT-6 Sol, GPT-6.1 Sol, GPT-6 Luna, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 as **Copilot-native** models, using current AA v4.3.2 composites. Claude Haiku 5.5 (released October 7, 2026) enters at **43** and, at **~$0.0023** per intelligence point, becomes the lowest cost per intelligence in the table; MiMo V2.6 Flash (**37.9**) remains the cheapest custom-endpoint option.
|
|
125
125
|
|
|
126
126
|
| Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
|
|
127
127
|
| ---------------------------- | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
|
|
128
|
+
| **Claude Haiku 5.5** | Anthropic | **~$0.0023** | **43** | ~$0.10 | ✅ | 1M |
|
|
128
129
|
| **MiMo V2.6 Flash** | Xiaomi | **~$0.0026** | **37.9** | ~$0.10 | ✅ | 1M |
|
|
129
130
|
| **GPT-6 Luna** | OpenAI | **~$0.0027** | **37.3** | ~$0.10 | ✅ | 1M |
|
|
130
131
|
| **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.8** | ~$0.13 | ✅ | 1M |
|
|
@@ -154,14 +155,15 @@ The current AA values come from OpenRouter's September 30 model metadata and ran
|
|
|
154
155
|
| **Claude Fable 5** | Anthropic | **~$0.2016** | **49.6** | ~$10.00 | ✅ | 1M |
|
|
155
156
|
|
|
156
157
|
> `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`'s composite (37.9) is OpenRouter's Artificial Analysis v4.3.2 value; Xiaomi's published launch benchmarks for it are recorded in [docs/benchmarks.md](docs/benchmarks.md).
|
|
157
|
-
> GPT-6 Sol, GPT-6.1 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: GPT-6 Sol and GPT-6.1 Sol require Pro+ or higher, Luna and Claude Sonnet 5.5 are available from Pro,
|
|
158
|
+
> GPT-6 Sol, GPT-6.1 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: GPT-6 Sol and GPT-6.1 Sol require Pro+ or higher, Luna and Claude Sonnet 5.5 are available from Pro, Claude Opus 5.5 requires Pro+ or higher, and Claude Haiku 5.5 is available on every paid plan (Pro through Enterprise).
|
|
159
|
+
> Claude Haiku 5.5 is the only current Claude model priced by prompt length: $0.10 / $0.01 cache read / $0.50 per 1M for prompts up to 100,000 tokens, and $0.50 / $0.05 / $2.50 above that. The table shows the sub-100K rates, which Anthropic says cover ~90% of Haiku-class requests.
|
|
158
160
|
|
|
159
161
|
> 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).
|
|
160
162
|
|
|
161
163
|
> **👤 Personal picks** —
|
|
162
164
|
>
|
|
163
|
-
> - **
|
|
164
|
-
> - **
|
|
165
|
+
> - **Claude Haiku 5.5** — the lowest cost per intelligence in this table (~$0.0023) and the best value among Copilot-native models, at about $0.10/session with vision.
|
|
166
|
+
> - **MiMo V2.6 Flash** — the lowest cost per intelligence among custom-endpoint models (~$0.0026), at about $0.10/session with vision.
|
|
165
167
|
> - **GLM 5.3 Flash** — the runner-up among custom-endpoint models (~$0.0030), at about $0.13/session with vision.
|
|
166
168
|
|
|
167
169
|
## Companion tools
|
|
@@ -215,7 +217,7 @@ GitHub ships a first-party MCP server (and it's even bundled into Copilot), so a
|
|
|
215
217
|
2. If the provider needs request rewriting, add a proxy under `proxy/`.
|
|
216
218
|
3. Submit a PR.
|
|
217
219
|
|
|
218
|
-
The current AA values come from OpenRouter's
|
|
220
|
+
The current AA values come from OpenRouter's 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 (#3)**, 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 snapshot records Gemini 3.8 Flash, Grok 4.7, GPT-6 Sol, GPT-6.1 Sol, GPT-6 Luna, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 as **Copilot-native** models, using current AA v4.3.2 composites.
|
|
219
221
|
|
|
220
222
|
- **Chat only.** Inline completions, semantic search, and next-edit suggestions still need a GitHub-hosted model.
|
|
221
223
|
- 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 +1,8 @@
|
|
|
1
1
|
# Pricing
|
|
2
2
|
|
|
3
|
-
> **Latest refresh (October
|
|
3
|
+
> **Latest refresh (October 8, 2026):** Claude Haiku 5.5 (released October 7, 2026; GA in GitHub Copilot the same day for Pro, Pro+, Max, Business, and Enterprise) is added at **$0.10 / $0.01 cache hit / $0.50** per 1M tokens for prompts up to 100,000 tokens, rising to **$0.50 / $0.05 / $2.50** above that threshold, with an Artificial Analysis v4.3.2 composite of **43**. At **~$0.0023** per intelligence point it becomes the lowest cost per intelligence in the table, just ahead of MiMo V2.6 Flash. The same Anthropic announcement halved Claude Sonnet 5.5's cache-read price to **$0.10** per 1M (from $0.20); its Cost per intelligence is unchanged because the modeled session cost does not include cached input. All other composites and first-party rates were re-checked against live OpenRouter metadata and provider pages with no changes.
|
|
4
|
+
>
|
|
5
|
+
> **Earlier refresh (October 7, 2026):** targeted re-check of the two Qwen entries against OpenRouter's model metadata and ranking card. The rankings card now places unversioned Qwen3.8 Max at **#3** (53.4, tied on score with Claude Fable 5.1), the `qwen/qwen3.8-max-0902` metadata row still reports **45.4**, and OpenRouter lists a newer higher-throughput `qwen/qwen3.8-max-prime` SKU (0923) at **$4 / $0.50 cache read / $12** per 1M — it has no AA composite yet, so it carries no Cost per intelligence row (see [docs/models/qwen.md](models/qwen.md)). No table values changed.
|
|
4
6
|
>
|
|
5
7
|
> **Earlier refresh (September 30, 2026):** GPT-6.1 Sol (released September 29 at OpenAI DevDay; GA in GitHub Copilot the same day for Pro+, Max, Business, and Enterprise) is added at **$2 / $0.10 cache hit / $10** per 1M tokens — identical input/output to GPT-6 Sol, with cache hits at half the rate ($0.10 vs $0.20) — and an Artificial Analysis v4.3.2 composite of **51.8**, so at **~$0.0386** per intelligence point it sorts between Grok 4.6 and GPT-6 Sol. OpenAI cancelled the planned **GPT-6.1 Astra** over safety concerns, so no such row exists. Every other composite and first-party rate was re-checked against live OpenRouter metadata and provider pages with no changes.
|
|
6
8
|
>
|
|
@@ -30,6 +32,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
30
32
|
|
|
31
33
|
| Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
|
|
32
34
|
| ---------------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
|
|
35
|
+
| **Claude Haiku 5.5** | Anthropic | **~$0.0023** | **43** | $0.10 (≤100K) / $0.50 (>100K) | $0.01 (≤100K) / $0.05 (>100K) | $0.50 (≤100K) / $2.50 (>100K) | ~$0.10 | 1M |
|
|
33
36
|
| **MiMo V2.6 Flash** | Xiaomi | **~$0.0026** | **37.9** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
|
|
34
37
|
| **GPT-6 Luna** | OpenAI | **~$0.0027** | **37.3** | $0.10 | $0.01 | $0.50 | ~$0.10 | 1M |
|
|
35
38
|
| **GLM 5.3 Flash** | Z.ai | **~$0.0030** | **41.8** | $0.15 | $0.03 | $0.50 | ~$0.13 | 1M |
|
|
@@ -44,7 +47,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
44
47
|
| **Qwen 3.8 Max (0803)** | DashScope | **~$0.0300** | **53.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
|
|
45
48
|
| **Grok 4.7** | xAI | **~$0.0345** | **46.4** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
|
|
46
49
|
| **Qwen 3.8 Max (0902)** | DashScope | **~$0.0352** | **45.4** | $2.00 | $0.25 | $6.00 | ~$1.60 | 1M |
|
|
47
|
-
| **Claude Sonnet 5.5** | Anthropic | **~$0.0357** | **56.0** | $2.00 | $0.
|
|
50
|
+
| **Claude Sonnet 5.5** | Anthropic | **~$0.0357** | **56.0** | $2.00 | $0.10 | $10.00 | ~$2.00 | 1M |
|
|
48
51
|
| **Grok 4.6** | xAI | **~$0.0361** | **44.3** | $2.00 | $0.50 | $6.00 | ~$1.60 | 500K |
|
|
49
52
|
| **GPT-6.1 Sol** | OpenAI | **~$0.0386** | **51.8** | $2.00 | $0.10 | $10.00 | ~$2.00 | 1M |
|
|
50
53
|
| **GPT-6 Sol** | OpenAI | **~$0.0421** | **47.5** | $2.00 | $0.20 | $10.00 | ~$2.00 | 1M |
|
|
@@ -65,7 +68,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
|
|
|
65
68
|
>
|
|
66
69
|
> - **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.
|
|
67
70
|
> - **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.
|
|
68
|
-
> - **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 / 5.5, and Fable 5 / 5.1 use a newer tokenizer that produces approximately 30% more tokens for the same text. Claude
|
|
71
|
+
> - **Anthropic (Claude)** cache reads and cache writes are billed separately. Claude Opus 5.5 cache reads are $0.20/M and Sonnet 5.5 cache reads are $0.10/M (both 0.05× base input); cache writes are $5/M for 5 minutes or $8/M for 1 hour on Opus 5.5 and $2.50/M or $4/M on Sonnet 5.5. Fast mode costs $8/M input and $40/M output. Opus 5.5, Opus 5, Sonnet 5 / 5.5, Haiku 5.5, and Fable 5 / 5.1 use a newer tokenizer that produces approximately 30% more tokens for the same text. **Claude Haiku 5.5 is the only current Claude model with prompt-length tiering**: prompts up to 100,000 tokens cost $0.10 / $0.01 cache read / $0.50 per 1M, prompts over 100,000 tokens cost $0.50 / $0.05 / $2.50, cache writes are $0.125/M (5 min) and $0.20/M (1 h) below the threshold, and batch pricing is $0.05 / $0.25 (≤100K) and $0.25 / $1.25 (>100K); the table above shows the sub-100K rates that Anthropic says cover ~90% of Haiku-class requests. Anthropic states Haiku 5.5 costs about 75% less on average to run than Haiku 4.5. Claude Sonnet 5.5 keeps Sonnet 5's $2 / $10 rates, and Anthropic made them permanent: the Sonnet 5 increase to $3 / $15 scheduled for September 1 was cancelled — and as of October 7, 2026 its cache reads were halved to $0.10/M (batch $1 / $5). Artificial Analysis measured Sonnet 5.5 at 138.7 tokens/s but very verbose (410M output tokens to run the Intelligence Index vs an 88M median), and Haiku 5.5 at 244 tokens/s but also very verbose (440M vs a 100M median), so real sessions can cost more than this table's modeled token counts; Anthropic reports up to 30% fewer tokens per task than Sonnet 5.
|
|
69
72
|
> - **OpenAI** models support cached input at 0.1× base input rate — except **GPT-6.1 Sol**, whose cache hits are 0.05× ($0.10/M, half of GPT-6 Sol's $0.20/M). GPT-6 Sol, GPT-6.1 Sol, and Luna also bill cache writes separately at 1.25× input. The GPT-6 and GPT-6.1 rows show standard rates through 272K input; for requests >272K, input and cache-read rates double and output is 1.5×.
|
|
70
73
|
> - **Qwen** models use **tiered pricing** — determined by total input tokens per request. Prices above are for non-thinking mode.
|
|
71
74
|
> - **Kimi** official tables list **Cache Hit before Cache Miss** (opposite order to our table; Kimi K3 also bills cache writes separately at $3.00/M for a 5-minute TTL and $6.00/M for 1 hour). The rows below transpose them so "Input" = cache miss and "Cached input" = cache hit.
|
|
@@ -78,7 +81,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
|
|
|
78
81
|
|
|
79
82
|
> **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.
|
|
80
83
|
|
|
81
|
-
> Prices last verified:
|
|
84
|
+
> Prices last verified: October 8, 2026. Always check the official pages for the latest rates:
|
|
82
85
|
>
|
|
83
86
|
> - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
|
|
84
87
|
> - [OpenAI pricing](https://openai.com/api/pricing/)
|
|
@@ -93,12 +96,15 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
|
|
|
93
96
|
> - [Anthropic Claude Opus 5.5 announcement](https://www.anthropic.com/claude-opus-5-5)
|
|
94
97
|
> - [Anthropic Opus 5.5 API docs](https://platform.claude.com/docs/en/models/opus-5-5/overview)
|
|
95
98
|
> - [Anthropic Claude Sonnet 5.5 announcement](https://www.anthropic.com/claude-sonnet-5-5)
|
|
99
|
+
> - [Anthropic Claude Haiku 5.5 announcement](https://www.anthropic.com/claude-haiku-5-5)
|
|
100
|
+
> - [Anthropic Claude Haiku 5.5 system card](https://www.anthropic.com/claude-haiku-5-5-system-card)
|
|
101
|
+
> - [GitHub Copilot Claude Haiku 5.5 release](https://github.blog/changelog/2026-10-07-claude-haiku-5-5-in-github-copilot)
|
|
96
102
|
> - [GitHub Copilot Claude Sonnet 5.5 release](https://github.blog/changelog/2026-09-28-claude-sonnet-5-5-in-github-copilot)
|
|
97
103
|
> - [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)
|
|
98
104
|
> - [GitHub Copilot GPT-6.1 Sol release](https://github.blog/changelog/2026-09-29-gpt-6-1-sol-in-github-copilot)
|
|
99
105
|
> - [GitHub Copilot Claude Opus 5.5 release](https://github.blog/changelog/2026-09-22-claude-opus-5-5-is-now-available-in-github-copilot)
|
|
100
106
|
> - [GitHub Copilot supported models](https://docs.github.com/en/copilot/reference/ai-models/supported-models)
|
|
101
|
-
> - [Artificial Analysis GPT-6 Sol](https://artificialanalysis.ai/models/gpt-6-sol), [GPT-6 Luna](https://artificialanalysis.ai/models/gpt-6-luna), [GPT-6.1 Sol](https://artificialanalysis.ai/models/gpt-6-1-sol), [Claude Opus 5.5](https://artificialanalysis.ai/models/claude-opus-5-5), [Claude Sonnet 5.5](https://artificialanalysis.ai/models/claude-sonnet-5-5), and [MiMo-V2.6-Flash](https://artificialanalysis.ai/models/mimo-v2-6-flash)
|
|
107
|
+
> - [Artificial Analysis GPT-6 Sol](https://artificialanalysis.ai/models/gpt-6-sol), [GPT-6 Luna](https://artificialanalysis.ai/models/gpt-6-luna), [GPT-6.1 Sol](https://artificialanalysis.ai/models/gpt-6-1-sol), [Claude Opus 5.5](https://artificialanalysis.ai/models/claude-opus-5-5), [Claude Sonnet 5.5](https://artificialanalysis.ai/models/claude-sonnet-5-5), [Claude Haiku 5.5](https://artificialanalysis.ai/models/claude-haiku-5-5), and [MiMo-V2.6-Flash](https://artificialanalysis.ai/models/mimo-v2-6-flash)
|
|
102
108
|
> - [Google Gemini pricing](https://ai.google.dev/pricing)
|
|
103
109
|
> - [DashScope pricing](https://www.alibabacloud.com/help/en/model-studio/billing-for-model-studio)
|
|
104
110
|
> - [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": "3.4.
|
|
3
|
+
"version": "3.4.2",
|
|
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",
|
|
@@ -28,9 +28,9 @@
|
|
|
28
28
|
"test": "node --test tests/**/*.test.mjs",
|
|
29
29
|
"lint": "eslint .",
|
|
30
30
|
"lint:fix": "eslint . --fix",
|
|
31
|
-
"format": "prettier --
|
|
32
|
-
"format:
|
|
33
|
-
"lf": "npm run lint && npm run format
|
|
31
|
+
"format": "prettier --write .",
|
|
32
|
+
"format:check": "prettier --check .",
|
|
33
|
+
"lf": "npm run lint && npm run format"
|
|
34
34
|
},
|
|
35
35
|
"repository": {
|
|
36
36
|
"type": "git",
|