copilot-custom-endpoint 1.5.5 → 1.5.7
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 +30 -30
- package/docs/models/qwen.md +1 -1
- package/docs/pricing.md +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -92,40 +92,38 @@ npx copilot-custom-endpoint clean # Remove debug_log/
|
|
|
92
92
|
|
|
93
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
94
|
|
|
95
|
-
| Model
|
|
96
|
-
|
|
|
97
|
-
| **DeepSeek V4 Flash**
|
|
98
|
-
|
|
|
99
|
-
| **
|
|
100
|
-
| **
|
|
101
|
-
| **
|
|
102
|
-
| **
|
|
103
|
-
| **
|
|
104
|
-
| **
|
|
105
|
-
| **
|
|
106
|
-
| **
|
|
107
|
-
| **
|
|
108
|
-
| **
|
|
109
|
-
| **
|
|
110
|
-
| **
|
|
111
|
-
| **
|
|
112
|
-
| **
|
|
113
|
-
| **GPT-5.
|
|
114
|
-
| **
|
|
115
|
-
| **
|
|
116
|
-
| **
|
|
117
|
-
| **
|
|
118
|
-
|
|
|
119
|
-
| **
|
|
120
|
-
|
|
|
121
|
-
|
|
|
95
|
+
| Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
|
|
96
|
+
| ---------------------- | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
|
|
97
|
+
| **DeepSeek V4 Flash** | DeepSeek | **~$0.0025** | **40.3** | ~$0.10 | ✅ | 1M |
|
|
98
|
+
| **MiniMax M3** | MiniMax | **~$0.0061** | **44.4** | ~$0.27 | ✅ | 1M |
|
|
99
|
+
| **DeepSeek V4 Pro** | DeepSeek | **~$0.0068** | **44.3** | ~$0.30 | ✅ | 1M |
|
|
100
|
+
| **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | ~$0.36 | ✅ | 1M |
|
|
101
|
+
| **MiMo V2.5 Pro** | Xiaomi | **~$0.019** | **42.2** | ~$0.80 | ❌ | 1M |
|
|
102
|
+
| **Kimi K2.6** | Moonshot | **~$0.021** | **42.8** | ~$0.88 | ✅ | 262K |
|
|
103
|
+
| **Kimi K2.7 Code** | Moonshot | **~$0.021** | **42.0** | ~$0.88 | ✅ | 262K |
|
|
104
|
+
| **GPT-5.4 mini** | OpenAI | **~$0.021** | **40.0** | ~$0.83 | ❌ | 400K |
|
|
105
|
+
| **GLM 5.1** | Z.ai | **~$0.028** | **40.2** | ~$1.14 | ❌ | 200K |
|
|
106
|
+
| **Gemini 3.5 Flash** | Google | **~$0.033** | **50.2** | ~$1.65 | ✅ | 1M |
|
|
107
|
+
| **Qwen 3.7 Max** | DashScope | **~$0.043** | **46.0** | ~$2.00 | ❌ | 1M |
|
|
108
|
+
| **Gemini 3.1 Pro** | Google | **~$0.047** | **46.5** | ~$2.20 | ✅ | 1M |
|
|
109
|
+
| **GPT-5.4** | OpenAI | **~$0.054** | **51.4** | ~$2.75 | ✅ | 1M |
|
|
110
|
+
| **Claude Sonnet 4.6** | Anthropic | **~$0.064** | **47.2** | ~$3.00 | ✅ | 1M |
|
|
111
|
+
| **Claude Opus 4.8** | Anthropic | **~$0.090** | **55.7** | ~$5.00 | ✅ | 1M |
|
|
112
|
+
| **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | ~$5.00 | ✅ | 1M |
|
|
113
|
+
| **GPT-5.5** | OpenAI | **~$0.10** | **54.8** | ~$5.50 | ✅ | 1M |
|
|
114
|
+
| **MiMo V2 Flash** | Xiaomi | — | — | ~$0.08 | ❌ | 256K |
|
|
115
|
+
| **Raptor mini** | GitHub | — | — | ~$0.33 | ❌ | 264K |
|
|
116
|
+
| **MiMo V2.5** | Xiaomi | — | — | ~$0.40 | ✅ | 1M |
|
|
117
|
+
| **Gemini 3 Flash** | Google | — | — | ~$0.55 | ✅ | 173K |
|
|
118
|
+
| **MAI-Code-1-Flash ²** | Microsoft | — | — | ~$0.83 | ❌ | — |
|
|
119
|
+
| **GLM 5V Turbo** | Z.ai | — | — | ~$1.00 | ✅ | 200K |
|
|
120
|
+
| **Claude Haiku 4.5** | Anthropic | — | — | ~$1.00 | ❌ | 160K |
|
|
121
|
+
| **GPT-5.3-Codex** | OpenAI | — | — | ~$2.28 | ❌ | 400K |
|
|
122
122
|
|
|
123
123
|
¹ Gemini 3.1 Pro pricing applies to prompts ≤200K tokens.
|
|
124
124
|
|
|
125
125
|
² MAI-Code-1-Flash is a continuously improving model — performance and behavior may evolve over time as new checkpoints are released.
|
|
126
126
|
|
|
127
|
-
³ Score is an **estimate** from Artificial Analysis (labelled "independent evaluation forthcoming"). Not a confirmed run of the full evaluation suite.
|
|
128
|
-
|
|
129
127
|
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).
|
|
130
128
|
|
|
131
129
|
> **👤 Personal picks** —
|
|
@@ -136,10 +134,12 @@ For footnotes, sources, and detailed notes (cache behavior, tiered pricing, free
|
|
|
136
134
|
> - Only ~$0.27/session with vision + 1M context
|
|
137
135
|
> - No local proxy required — works direct
|
|
138
136
|
>
|
|
137
|
+
> **DeepSeek V4 Pro** is a strong backup — nearly identical intelligence (44.3 vs 44.4) and cost (~$0.0068 vs ~$0.0061 per intelligence point), but noticeably faster in practice.
|
|
138
|
+
>
|
|
139
139
|
> Cheaper alternatives for simpler tasks:
|
|
140
140
|
>
|
|
141
141
|
> - **DeepSeek V4 Flash** — ~$0.10/session, 40.3 score (solid fallback)
|
|
142
|
-
> - **MiMo V2 Flash** — ~$0.08/session
|
|
142
|
+
> - **MiMo V2 Flash** — ~$0.08/session (cheapest, but unreliable for multi-step agentic work)
|
|
143
143
|
|
|
144
144
|
## Companion tools
|
|
145
145
|
|
package/docs/models/qwen.md
CHANGED
|
@@ -332,4 +332,4 @@ Conclusion: not a DashScope or Qwen model incompatibility. Evidence points to an
|
|
|
332
332
|
- DashScope model index: `https://help.aliyun.com/zh/model-studio/getting-started/models`
|
|
333
333
|
- DashScope vision model guide: `https://help.aliyun.com/zh/model-studio/vision`
|
|
334
334
|
- DashScope pricing: `https://www.alibabacloud.com/help/en/model-studio/billing-for-model-studio`
|
|
335
|
-
- Kimi K2.6 validation record (separate provider): [kimi
|
|
335
|
+
- Kimi K2.6 validation record (separate provider): [kimi.md](kimi.md)
|
package/docs/pricing.md
CHANGED
|
@@ -23,7 +23,6 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
23
23
|
| Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
|
|
24
24
|
| ---------------------- | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
|
|
25
25
|
| **DeepSeek V4 Flash** | DeepSeek | **~$0.0025** | **40.3** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
|
|
26
|
-
| **MiMo V2 Flash** | Xiaomi | **~$0.0035** | **23.0** ³ | $0.10 | $0.01 | $0.30 | ~$0.08 | 256K |
|
|
27
26
|
| **MiniMax M3** | MiniMax | **~$0.0061** | **44.4** | $0.60 (≤512K) / $1.20 (>512K) | $0.12 (≤512K) / $0.24 (>512K) | $2.40 (≤512K) / $4.80 (>512K) | ~$0.27 | 1M |
|
|
28
27
|
| **DeepSeek V4 Pro** | DeepSeek | **~$0.0068** | **44.3** | $0.435 | $0.003625 | $0.87 | ~$0.30 | 1M |
|
|
29
28
|
| **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | $0.40 (≤256K) / $1.20 (>256K) | — | $1.60 (≤256K) / $4.80 (>256K) | ~$0.36 | 1M |
|
|
@@ -43,6 +42,7 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
43
42
|
| **Claude Opus 4.8** | Anthropic | **~$0.090** | **55.7** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
|
|
44
43
|
| **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
|
|
45
44
|
| **GPT-5.5** | OpenAI | **~$0.10** | **54.8** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
|
|
45
|
+
| **MiMo V2 Flash** | Xiaomi | — | — | $0.10 | $0.01 | $0.30 | ~$0.08 | 256K |
|
|
46
46
|
| **Raptor mini** | GitHub | — | — | $0.25 | $0.025 | $2.00 | ~$0.33 | 264K |
|
|
47
47
|
| **MiMo V2.5** | Xiaomi | — | — | $0.40 | $0.08 | $2.00 | ~$0.40 | 1M |
|
|
48
48
|
| **MAI-Code-1-Flash** ² | Microsoft | — | — | $0.75 | $0.075 | $4.50 | ~$0.83 | — |
|