copilot-custom-endpoint 1.5.0 → 1.5.2

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.
Files changed (3) hide show
  1. package/README.md +34 -19
  2. package/docs/pricing.md +32 -68
  3. package/package.json +2 -2
package/README.md CHANGED
@@ -90,25 +90,40 @@ npx copilot-custom-endpoint clean # Remove debug_log/
90
90
 
91
91
  ## Pricing snapshot
92
92
 
93
- All prices are **USD per 1M tokens** (cache miss). 1 AI credit = $0.01. **MiniMax M3** figures reflect a permanent 50% off list price — see the model doc for the full rate card. Context window ¹ covers input + output combined.
94
-
95
- | Model | Input | Output | Context ¹ |
96
- | ---------------------------- | ----- | ------ | --------- |
97
- | **MiMo V2 Flash** 🏆 | $0.10 | $0.30 | 256K |
98
- | **DeepSeek V4 Flash** 🏆 | $0.14 | $0.28 | 1M |
99
- | **Kimi K2.6** (non-thinking) | $0.16 | $0.95 | 262K |
100
- | **Kimi K2.6** (thinking) | $0.16 | $4.00 | 262K |
101
- | **Kimi K2.7 Code** | $0.19 | $4.00 | 262K |
102
- | **MiniMax M3** | $0.30 | $1.20 | 1M |
103
- | **MiMo V2.5** | $0.40 | $2.00 | 1M |
104
- | **Qwen 3.7 Plus** | $0.40 | $1.60 | 1M |
105
- | **MAI-Code-1-Flash** | $0.75 | $4.50 | — |
106
- | **MiMo V2.5 Pro** | $1.00 | $3.00 | 1M |
107
- | **GLM 5V Turbo** | $1.20 | $4.00 | 200K |
108
- | **GLM 5.1** | $1.40 | $4.40 | 200K |
109
- | **Qwen 3.7 Max** | $2.50 | $7.50 | 1M |
110
-
111
- For the full pricing comparison (cached rates, full Copilot roster, footnotes, sources) 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).
93
+ 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.
94
+
95
+ | Model | Provider | Intelligence per cost | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
96
+ | ---------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
97
+ | **DeepSeek V4 Flash** | DeepSeek | **403** | **40.3** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
98
+ | **MiniMax M3** | MiniMax | **164** | **44.4** | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | ~$0.27 | 1M |
99
+ | **DeepSeek V4 Pro** | DeepSeek | **148** | **44.3** | $0.435 | $0.003625 | $0.87 | ~$0.30 | 1M |
100
+ | **Qwen 3.7 Plus** | DashScope | **108** | **39.0** | $0.40 (≤256K) / $1.20 (>256K) | — | $1.60 (≤256K) / $4.80 (>256K) | ~$0.36 | 1M |
101
+ | **MiMo V2.5 Pro** | Xiaomi | **53** | **42.2** | $1.00 | $0.20 | $3.00 | ~$0.80 | 1M |
102
+ | **Kimi K2.6** | Moonshot | **49** | **42.8** | $0.95 | $0.16 | $4.00 | ~$0.88 | 256K |
103
+ | **GPT-5.4 mini** | OpenAI | **48** | **40.0** | $0.75 | $0.075 | $4.50 | ~$0.83 | 400K |
104
+ | **GLM 5.1** | Z.ai | **35** | **40.2** | $1.40 | $0.26 | $4.40 | ~$1.14 | 200K |
105
+ | **Gemini 3.5 Flash** | Google | **30** | **50.2** | $1.50 | $0.15 | $9.00 | ~$1.65 | 1M |
106
+ | **Qwen 3.7 Max** | DashScope | **23** | **46.0** | $2.50 (≤1M) | — | $7.50 (≤1M) | ~$2.00 | 1M |
107
+ | **Gemini 3.1 Pro** | Google | **21** | **46.5** | $2.00¹ | $0.20 | $12.00¹ | ~$2.20 | 1M |
108
+ | **GPT-5.4** | OpenAI | **19** | **51.4** | $2.50 | $0.25 | $15.00 | ~$2.75 | 1M |
109
+ | **Claude Sonnet 4.6** | Anthropic | **16** | **47.2** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
110
+ | **Claude Opus 4.8** | Anthropic | **11** | **55.7** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
111
+ | **Claude Opus 4.7** | Anthropic | **11** | **53.5** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
112
+ | **GPT-5.5** | OpenAI | **10** | **54.8** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
113
+ | **MiMo V2 Flash** | Xiaomi | — | — | $0.10 | $0.01 | $0.30 | ~$0.08 | 256K |
114
+ | **Raptor mini** | GitHub | — | — | $0.25 | $0.025 | $2.00 | ~$0.33 | 264K |
115
+ | **MiMo V2.5** | Xiaomi | — | — | $0.40 | $0.08 | $2.00 | ~$0.40 | 1M |
116
+ | **Gemini 3 Flash** | Google | — | — | $0.50 | $0.05 | $3.00 | ~$0.55 | 173K |
117
+ | **MAI-Code-1-Flash** ² | Microsoft | — | — | $0.75 | $0.075 | $4.50 | ~$0.83 | — |
118
+ | **Kimi K2.7 Code** | Moonshot | — | — | $0.95 | $0.19 | $4.00 | ~$0.88 | 262K |
119
+ | **Claude Haiku 4.5** | Anthropic | — | — | $1.00 | $0.10 | $5.00 | ~$1.00 | 160K |
120
+ | **GLM 5V Turbo** | Z.ai | — | — | $1.20 | $0.24 | $4.00 | ~$1.00 | 200K |
121
+ | **GPT-5.3-Codex** | OpenAI | — | — | $1.75 | $0.175 | $14.00 | ~$2.28 | 400K |
122
+
123
+ ¹ Gemini 3.1 Pro pricing applies to prompts ≤200K tokens.
124
+ ² MAI-Code-1-Flash is a continuously improving model — performance and behavior may evolve over time as new checkpoints are released.
125
+
126
+ 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).
112
127
 
113
128
  ## Companion tools
114
129
 
package/docs/pricing.md CHANGED
@@ -18,94 +18,58 @@
18
18
 
19
19
  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).
20
20
 
21
- ## Default GitHub Copilot models
21
+ All models are listed together below, sorted by Intelligence per cost (highest first). Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
22
22
 
23
- These are the models available through GitHub Copilot's model roster as of June 1, 2026.
23
+ | Model | Provider | Intelligence per cost | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
24
+ | ---------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
25
+ | **DeepSeek V4 Flash** | DeepSeek | **403** | **40.3** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
26
+ | **MiniMax M3** | MiniMax | **164** | **44.4** | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | ~$0.27 | 1M |
27
+ | **DeepSeek V4 Pro** | DeepSeek | **148** | **44.3** | $0.435 | $0.003625 | $0.87 | ~$0.30 | 1M |
28
+ | **Qwen 3.7 Plus** | DashScope | **108** | **39.0** | $0.40 (≤256K) / $1.20 (>256K) | — | $1.60 (≤256K) / $4.80 (>256K) | ~$0.36 | 1M |
29
+ | **MiMo V2.5 Pro** | Xiaomi | **53** | **42.2** | $1.00 | $0.20 | $3.00 | ~$0.80 | 1M |
30
+ | **Kimi K2.6** | Moonshot | **49** | **42.8** | $0.95 | $0.16 | $4.00 | ~$0.88 | 256K |
31
+ | **GPT-5.4 mini** | OpenAI | **48** | **40.0** | $0.75 | $0.075 | $4.50 | ~$0.83 | 400K |
32
+ | **GLM 5.1** | Z.ai | **35** | **40.2** | $1.40 | $0.26 | $4.40 | ~$1.14 | 200K |
33
+ | **Gemini 3.5 Flash** | Google | **30** | **50.2** | $1.50 | $0.15 | $9.00 | ~$1.65 | 1M |
34
+ | **Qwen 3.7 Max** | DashScope | **23** | **46.0** | $2.50 (≤1M) | — | $7.50 (≤1M) | ~$2.00 | 1M |
35
+ | **Gemini 3.1 Pro** | Google | **21** | **46.5** | $2.00¹ | $0.20 | $12.00¹ | ~$2.20 | 1M |
36
+ | **GPT-5.4** | OpenAI | **19** | **51.4** | $2.50 | $0.25 | $15.00 | ~$2.75 | 1M |
37
+ | **Claude Sonnet 4.6** | Anthropic | **16** | **47.2** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
38
+ | **Claude Opus 4.8** | Anthropic | **11** | **55.7** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
39
+ | **Claude Opus 4.7** | Anthropic | **11** | **53.5** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
40
+ | **GPT-5.5** | OpenAI | **10** | **54.8** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
41
+ | **MiMo V2 Flash** | Xiaomi | — | — | $0.10 | $0.01 | $0.30 | ~$0.08 | 256K |
42
+ | **Raptor mini** | GitHub | — | — | $0.25 | $0.025 | $2.00 | ~$0.33 | 264K |
43
+ | **MiMo V2.5** | Xiaomi | — | — | $0.40 | $0.08 | $2.00 | ~$0.40 | 1M |
44
+ | **Gemini 3 Flash** | Google | — | — | $0.50 | $0.05 | $3.00 | ~$0.55 | 173K |
45
+ | **MAI-Code-1-Flash** ² | Microsoft | — | — | $0.75 | $0.075 | $4.50 | ~$0.83 | — |
46
+ | **Kimi K2.7 Code** | Moonshot | — | — | $0.95 | $0.19 | $4.00 | ~$0.88 | 262K |
47
+ | **Claude Haiku 4.5** | Anthropic | — | — | $1.00 | $0.10 | $5.00 | ~$1.00 | 160K |
48
+ | **GLM 5V Turbo** | Z.ai | — | — | $1.20 | $0.24 | $4.00 | ~$1.00 | 200K |
49
+ | **GPT-5.3-Codex** | OpenAI | — | — | $1.75 | $0.175 | $14.00 | ~$2.28 | 400K |
24
50
 
25
- | Model | Provider | Tier | Input (per 1M) | Cached input | Output (per 1M) | Context window |
26
- | ---------------------- | --------- | ----------- | -------------- | ------------ | --------------- | -------------- |
27
- | **Raptor mini** | GitHub | Versatile | $0.25 | $0.025 | $2.00 | 264K |
28
- | **Gemini 3 Flash** | Google | Lightweight | $0.50 | $0.05 | $3.00 | 173K |
29
- | **GPT-5.4 mini** | OpenAI | Lightweight | $0.75 | $0.075 | $4.50 | 400K |
30
- | **MAI-Code-1-Flash** ² | Microsoft | Lightweight | $0.75 | $0.075 | $4.50 | — |
31
- | **Claude Haiku 4.5** | Anthropic | Versatile | $1.00 | $0.10 | $5.00 | 160K |
32
- | **Gemini 2.5 Pro** | Google | Powerful | $1.25¹ | $0.125 | $10.00¹ | 173K |
33
- | **Gemini 3.5 Flash** | Google | Lightweight | $1.50 | $0.15 | $9.00 | 1M |
34
- | **GPT-5.3-Codex** | OpenAI | Powerful | $1.75 | $0.175 | $14.00 | 400K |
35
- | **Gemini 3.1 Pro** | Google | Powerful | $2.00¹ | $0.20 | $12.00¹ | 1M |
36
- | **GPT-5.4** | OpenAI | Versatile | $2.50 | $0.25 | $15.00 | 1M |
37
- | **Claude Sonnet 4.6** | Anthropic | Versatile | $3.00 | $0.30 | $15.00 | 1M |
38
- | **Claude Opus 4.8** | Anthropic | Powerful | $5.00 | $0.50 | $25.00 | 1M |
39
- | **Claude Opus 4.7** | Anthropic | Powerful | $5.00 | $0.50 | $25.00 | 1M |
40
- | **GPT-5.5** | OpenAI | Powerful | $5.00 | $0.50 | $30.00 | 1M |
41
-
42
- ¹ Gemini 3.1 Pro and 2.5 Pro pricing applies to prompts ≤200K tokens.
51
+ ¹ Gemini 3.1 Pro pricing applies to prompts ≤200K tokens.
43
52
  ² MAI-Code-1-Flash is a continuously improving model — performance and behavior may evolve over time as new checkpoints are released.
44
53
 
45
- ## Custom-endpoint alternatives
46
-
47
- | Model | Provider | Input (per 1M) | Cached input | Output (per 1M) | Context window |
48
- | --------------------- | --------- | ----------------------------- | ----------------------------- | --------------------------------------- | -------------- |
49
- | **MiMo V2 Flash** | Xiaomi | $0.10 | $0.01 | $0.30 | 256K |
50
- | **DeepSeek V4 Flash** | DeepSeek | $0.14 | $0.0028 | $0.28 | 1M |
51
- | **Kimi K2.6** | Moonshot | $0.16 | — | $0.95 (non-thinking) / $4.00 (thinking) | 256K |
52
- | **Kimi K2.7 Code** | Moonshot | $0.19 | $0.95 | $4.00 | 262K |
53
- | **Qwen 3.7 Plus** | DashScope | $0.40 (≤256K) / $1.20 (>256K) | — | $1.60 (≤256K) / $4.80 (>256K) | 1M |
54
- | **MiMo V2.5** | Xiaomi | $0.40 | $0.08 | $2.00 | 1M |
55
- | **DeepSeek V4 Pro** | DeepSeek | $0.435 | $0.003625 | $0.87 | 1M |
56
- | **MiniMax M3** | MiniMax | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | 1M |
57
- | **MiMo V2.5 Pro** | Xiaomi | $1.00 | $0.20 | $3.00 | 1M |
58
- | **GLM 5V Turbo** | Z.ai | $1.20 | $0.24 | $4.00 | 200K |
59
- | **GLM 5.1** | Z.ai | $1.40 | $0.26 | $4.40 | 200K |
60
- | **Qwen 3.7 Max** | DashScope | $2.50 (≤1M) | — | $7.50 (≤1M) | 1M |
54
+ Intelligence per cost = Intelligence Index score ÷ estimated session cost. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
61
55
 
62
56
  > **Notes:**
63
57
  >
64
- > - **MAI-Code-1-Flash** is a continuously improving model — performance and behavior may evolve over time as new checkpoints are released.
65
58
  > - **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).
66
59
  > - **MiMo** input pricing shown is the **cache miss** price. Cache hits are 5× cheaper for V2.5 Pro ($0.20/M) and V2.5 ($0.08/M), and 10× cheaper for V2 Flash ($0.01/M).
67
60
  > - **Gemini 3 Flash** is priced at $0.50/MTok input (text/image/video) and $1.00/MTok input for audio.
68
61
  > - **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+ use a new tokenizer that may use up to 35% more tokens for the same text.
69
62
  > - **OpenAI** models support cached input at 0.1× base input rate.
70
63
  > - **Qwen** models use **tiered pricing** — determined by total input tokens per request. Prices above are for non-thinking mode.
64
+ > - **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.
71
65
  > - **Kimi K2.6** pricing is from the **Moonshot platform** (direct). Via DashScope: $0.89 input / $3.71 output.
72
66
  > - **DashScope** offers a **free quota** of 1M input + 1M output tokens per model, valid for 90 days.
73
67
  > - **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.
74
68
  > - **GLM** models support prompt caching — cache hits are priced at $0.24/M for 5V Turbo and $0.26/M for 5.1.
75
69
  > - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion.
70
+ > - **MAI-Code-1-Flash** is a continuously improving model — performance and behavior may evolve over time as new checkpoints are released.
76
71
  > - For typical Copilot chat usage (short-to-medium prompts), you'll almost always fall in the lowest pricing tier.
77
72
 
78
- ## Quick cost comparison
79
-
80
- For a typical coding session (~10K input + ~2K output tokens per turn, 50 turns):
81
-
82
- | Model | Estimated session cost |
83
- | ------------------------ | ---------------------- |
84
- | MiMo V2 Flash | ~$0.08 |
85
- | DeepSeek V4 Flash | ~$0.10 |
86
- | Kimi K2.6 (non-thinking) | ~$0.18 |
87
- | MiniMax M3 (50% off) | ~$0.27 |
88
- | DeepSeek V4 Pro | ~$0.30 |
89
- | Raptor mini | ~$0.33 |
90
- | Qwen 3.7 Plus | ~$0.36 |
91
- | MiMo V2.5 | ~$0.40 |
92
- | Kimi K2.6 (thinking) | ~$0.48 |
93
- | Kimi K2.7 Code | ~$0.50 |
94
- | Gemini 3 Flash | ~$0.55 |
95
- | MiMo V2.5 Pro | ~$0.80 |
96
- | MAI-Code-1-Flash | ~$0.83 |
97
- | GPT-5.4 mini | ~$0.83 |
98
- | Claude Haiku 4.5 | ~$1.00 |
99
- | Qwen 3.7 Max | ~$1.33 |
100
- | Gemini 2.5 Pro | ~$1.63 |
101
- | Gemini 3.5 Flash | ~$1.65 |
102
- | Gemini 3.1 Pro | ~$2.20 |
103
- | GPT-5.3-Codex | ~$2.28 |
104
- | GPT-5.4 | ~$2.75 |
105
- | Claude Sonnet 4.6 | ~$3.00 |
106
- | Claude Opus 4.8 / 4.7 | ~$5.00 |
107
- | GPT-5.5 | ~$5.50 |
108
-
109
73
  > **How long does 7,000 credits last?** A Pro+ subscriber running 50-turn sessions could afford roughly **13 GPT-5.5 sessions**, **23 Opus sessions**, or **212 Raptor mini sessions** per month — or mix and match. (Multiply session cost by 100 to convert to AI credits.)
110
74
 
111
75
  > Prices last verified: June 14, 2026. Always check the official pages for the latest rates:
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "copilot-custom-endpoint",
3
- "version": "1.5.0",
3
+ "version": "1.5.2",
4
4
  "description": "Local proxies for VS Code Copilot custom endpoints — Kimi K2, Qwen 3.x & MiMo V2.5",
5
5
  "license": "MIT",
6
6
  "type": "module",
@@ -57,4 +57,4 @@
57
57
  "dependencies": {
58
58
  "dotenv": "^17.4.2"
59
59
  }
60
- }
60
+ }