copilot-custom-endpoint 1.6.11 → 1.7.1
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 +32 -28
- package/docs/example-config.md +19 -2
- package/docs/models/minimax.md +78 -6
- package/docs/pricing.md +36 -31
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -26,7 +26,8 @@ That's it. No code, no servers to manage (unless the model specifically needs th
|
|
|
26
26
|
| **Kimi K2.7 Code / K2.6** | Moonshot | **Yes** | ✅ | [Manual setup](docs/models/kimi.md) |
|
|
27
27
|
| **Qwen 3.7 Plus** | DashScope | Optional (recommended) | ✅ | [Manual setup](docs/models/qwen.md) |
|
|
28
28
|
| **Qwen 3.7 Max** | DashScope | Optional (recommended) | ❌ | [Manual setup](docs/models/qwen.md) |
|
|
29
|
-
| **MiniMax M3** | MiniMax | No | ✅ | [Manual setup](docs/models/minimax.md)
|
|
29
|
+
| **MiniMax M3** | MiniMax | No | ✅ | [Extension (PAYG, source build)](https://github.com/tugudush/minimax-copilot) ★ / [Manual setup](docs/models/minimax.md) |
|
|
30
|
+
| **MiniMax M3 Priority** | MiniMax | No | ✅ | [Extension (PAYG, source build)](https://github.com/tugudush/minimax-copilot) ★ / [Manual setup](docs/models/minimax.md#m3-priority-tier) |
|
|
30
31
|
| **GLM 5.2** | Z.ai | No | ✅ via extension | [Extension](https://marketplace.visualstudio.com/items?itemName=ikaros.glm-for-vscode-copilot) ★ / [Manual setup](docs/models/glm.md) |
|
|
31
32
|
| **GLM 5.1** | Z.ai | No | ✅ via extension | [Extension](https://marketplace.visualstudio.com/items?itemName=yijiazhen-qi.glm-for-github-copilot-chat) ★ / [Manual setup](docs/models/glm.md) |
|
|
32
33
|
| **GLM 5V Turbo** | Z.ai | No | ✅ | [Manual setup](docs/models/glm.md) |
|
|
@@ -92,33 +93,34 @@ npx copilot-custom-endpoint clean # Remove debug_log/
|
|
|
92
93
|
|
|
93
94
|
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
|
|
|
95
|
-
| Model
|
|
96
|
-
|
|
|
97
|
-
| **DeepSeek V4 Flash**
|
|
98
|
-
| **MiMo V2.5**
|
|
99
|
-
| **MiniMax M3**
|
|
100
|
-
| **DeepSeek V4 Pro**
|
|
101
|
-
| **MiMo V2.5 Pro**
|
|
102
|
-
| **Qwen 3.7 Plus**
|
|
103
|
-
| **
|
|
104
|
-
| **
|
|
105
|
-
| **Kimi K2.
|
|
106
|
-
| **
|
|
107
|
-
| **
|
|
108
|
-
| **GLM 5.
|
|
109
|
-
| **GLM
|
|
110
|
-
| **
|
|
111
|
-
| **
|
|
112
|
-
| **
|
|
113
|
-
| **
|
|
114
|
-
| **
|
|
115
|
-
| **Claude
|
|
116
|
-
| **Claude Opus 4.
|
|
117
|
-
| **
|
|
118
|
-
| **
|
|
119
|
-
| **
|
|
120
|
-
| **
|
|
121
|
-
| **
|
|
96
|
+
| Model | Provider | Cost per intelligence | Intelligence Score | Est. session | Vision | Context window |
|
|
97
|
+
| ------------------------ | --------- | --------------------- | ------------------ | ------------ | ------ | -------------- |
|
|
98
|
+
| **DeepSeek V4 Flash** | DeepSeek | **~$0.0025** | **40.3** | ~$0.10 | ✅ | 1M |
|
|
99
|
+
| **MiMo V2.5** | Xiaomi | **~$0.0025** | **40** ³ | ~$0.10 | ✅ | 1M |
|
|
100
|
+
| **MiniMax M3** | MiniMax | **~$0.0061** | **44.4** | ~$0.27 | ✅ | 1M |
|
|
101
|
+
| **DeepSeek V4 Pro** | DeepSeek | **~$0.0068** | **44.3** | ~$0.30 | ✅ | 1M |
|
|
102
|
+
| **MiMo V2.5 Pro** | Xiaomi | **~$0.0072** | **42.2** | ~$0.30 | ❌ | 1M |
|
|
103
|
+
| **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | ~$0.36 | ✅ | 1M |
|
|
104
|
+
| **MiniMax M3 Priority**⁴ | MiniMax | **~$0.0092** | **44.4** | ~$0.41 | ✅ | 1M |
|
|
105
|
+
| **Gemini 3 Flash** | Google | **~$0.020** | **27.0** ³ | ~$0.55 | ✅ | 173K |
|
|
106
|
+
| **Kimi K2.6** | Moonshot | **~$0.021** | **42.8** | ~$0.88 | ✅ | 262K |
|
|
107
|
+
| **Kimi K2.7 Code** | Moonshot | **~$0.021** | **42.0** | ~$0.88 | ✅ | 262K |
|
|
108
|
+
| **GPT-5.4 mini** | OpenAI | **~$0.021** | **40.0** | ~$0.83 | ❌ | 400K |
|
|
109
|
+
| **GLM 5.2** | Z.ai | **~$0.022** | **51.0** | ~$1.14 | ❌ | 1M |
|
|
110
|
+
| **GLM 5.1** | Z.ai | **~$0.028** | **40.2** | ~$1.14 | ❌ | 200K |
|
|
111
|
+
| **GLM 5V Turbo** | Z.ai | **~$0.029** | **34.0** ³ | ~$1.00 | ✅ | 200K |
|
|
112
|
+
| **Gemini 3.5 Flash** | Google | **~$0.033** | **50.2** | ~$1.65 | ✅ | 1M |
|
|
113
|
+
| **Qwen 3.7 Max** | DashScope | **~$0.043** | **46.0** | ~$2.00 | ❌ | 1M |
|
|
114
|
+
| **Gemini 3.1 Pro** | Google | **~$0.047** | **46.5** | ~$2.20 | ✅ | 1M |
|
|
115
|
+
| **GPT-5.4** | OpenAI | **~$0.054** | **51.4** | ~$2.75 | ✅ | 1M |
|
|
116
|
+
| **Claude Sonnet 4.6** | Anthropic | **~$0.064** | **47.2** | ~$3.00 | ✅ | 1M |
|
|
117
|
+
| **Claude Opus 4.8** | Anthropic | **~$0.090** | **55.7** | ~$5.00 | ✅ | 1M |
|
|
118
|
+
| **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | ~$5.00 | ✅ | 1M |
|
|
119
|
+
| **GPT-5.5** | OpenAI | **~$0.10** | **54.8** | ~$5.50 | ✅ | 1M |
|
|
120
|
+
| **Raptor mini** | GitHub | — | — | ~$0.33 | ❌ | 264K |
|
|
121
|
+
| **MAI-Code-1-Flash** ² | Microsoft | — | — | ~$0.83 | ❌ | — |
|
|
122
|
+
| **Claude Haiku 4.5** | Anthropic | — | — | ~$1.00 | ❌ | 160K |
|
|
123
|
+
| **GPT-5.3-Codex** | OpenAI | — | — | ~$2.28 | ❌ | 400K |
|
|
122
124
|
|
|
123
125
|
¹ Gemini 3.1 Pro pricing applies to prompts ≤200K tokens.
|
|
124
126
|
|
|
@@ -126,6 +128,8 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
|
|
|
126
128
|
|
|
127
129
|
³ Score is an **estimate** from Artificial Analysis (labelled "independent evaluation forthcoming"). Not a confirmed run of the full evaluation suite.
|
|
128
130
|
|
|
131
|
+
⁴ **MiniMax M3 Priority** is the same `MiniMax-M3` weights invoked with `"service_tier": "priority"` in the request body — **not a separate model**. Costs **1.5× Standard** (effective post-50%-off rates: $0.45 / $1.80 / $0.09 per 1M for input/output/cached ≤512K) in exchange for **priority admission** (faster responses, fewer failures during MiniMax peak hours). Capabilities, context window, vision, tools, rate limits, and thinking modes are identical to Standard. See [docs/research/minimax-m3-priority.md](docs/research/minimax-m3-priority.md).
|
|
132
|
+
|
|
129
133
|
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
134
|
|
|
131
135
|
> **👤 Personal picks** —
|
package/docs/example-config.md
CHANGED
|
@@ -111,7 +111,7 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
|
|
|
111
111
|
"models": [
|
|
112
112
|
{
|
|
113
113
|
"id": "MiniMax-M3",
|
|
114
|
-
"name": "MiniMax M3 (
|
|
114
|
+
"name": "MiniMax M3 (Standard)",
|
|
115
115
|
"url": "https://api.minimax.io/v1/chat/completions",
|
|
116
116
|
"toolCalling": true,
|
|
117
117
|
"vision": true,
|
|
@@ -124,6 +124,23 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
|
|
|
124
124
|
"temperature": 1,
|
|
125
125
|
"top_p": 0.95
|
|
126
126
|
}
|
|
127
|
+
},
|
|
128
|
+
{
|
|
129
|
+
"id": "MiniMax-M3-Priority",
|
|
130
|
+
"name": "MiniMax M3 (Priority)",
|
|
131
|
+
"url": "https://api.minimax.io/v1/chat/completions",
|
|
132
|
+
"toolCalling": true,
|
|
133
|
+
"vision": true,
|
|
134
|
+
"streaming": true,
|
|
135
|
+
"maxInputTokens": 1048576,
|
|
136
|
+
"maxOutputTokens": 131072,
|
|
137
|
+
"requestBody": {
|
|
138
|
+
"thinking": { "type": "adaptive" },
|
|
139
|
+
"reasoning_split": true,
|
|
140
|
+
"temperature": 1,
|
|
141
|
+
"top_p": 0.95,
|
|
142
|
+
"service_tier": "priority"
|
|
143
|
+
}
|
|
127
144
|
}
|
|
128
145
|
]
|
|
129
146
|
},
|
|
@@ -190,7 +207,7 @@ If you only need one provider, jump straight to its setup guide:
|
|
|
190
207
|
- [Kimi K2.6 / K2.7 Code](kimi.md)
|
|
191
208
|
- [Qwen 3.7 Plus / 3.7 Max](qwen.md)
|
|
192
209
|
- [Xiaomi MiMo (V2.5 / V2.5 Pro)](mimo.md)
|
|
193
|
-
- [MiniMax M3](minimax.md)
|
|
210
|
+
- [MiniMax M3 (Standard)](minimax.md) and [MiniMax M3 (Priority)](minimax.md#5-m3-priority-tier-optional)
|
|
194
211
|
- [GLM (5.2 / 5.1 / 5V Turbo)](glm.md)
|
|
195
212
|
|
|
196
213
|
> **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.
|
package/docs/models/minimax.md
CHANGED
|
@@ -2,11 +2,16 @@
|
|
|
2
2
|
|
|
3
3
|
> **TL;DR:** MiniMax-M3 works directly — no proxy needed. Use `thinking: { type: "adaptive" }` + `reasoning_split: true` in `requestBody` so the model can reason and the response arrives in a clean OpenAI format (`reasoning_details` field, separate from `content`). **Important:** `thinking: { type: "disabled" }` is **not** a hard override — the model still reasons internally and emits `<think>` tags / `reasoning_content` regardless.
|
|
4
4
|
>
|
|
5
|
+
> Want faster responses and fewer admission failures during peak hours? Add `"service_tier": "priority"` to `requestBody` (or register a second `MiniMax-M3-Priority` picker entry) — same model, **1.5× cost** for **priority admission**. See [M3 Priority tier](#5-m3-priority-tier-optional) below.
|
|
6
|
+
>
|
|
5
7
|
> The same `url`, `model id`, and `requestBody` work for **both** Pay-as-You-Go (account-balance billing) and Token Plan (monthly/annual subscription) — only the API key in the secret field changes.
|
|
6
8
|
>
|
|
7
|
-
> **🆕 Try
|
|
9
|
+
> **🆕 Try a MiniMax Copilot extension first** (no JSON editing):
|
|
10
|
+
>
|
|
11
|
+
> - **Token Plan subscription** (`sk-cp-…`): the [**klarkxy/minimax-vscode**](https://marketplace.visualstudio.com/items?itemName=klarkxy.minimax-vscode-copilot) extension is the most feature-rich — reasoning visibility, usage dashboard, status-bar quota monitoring, one-click region switching, and M3 1M context toggling. Subscription keys required.
|
|
12
|
+
> - **Pay-as-You-Go** (Open Platform API Key): the [**tugudush/minimax-copilot**](https://github.com/tugudush/minimax-copilot) extension is a PAYG-native alternative — same Anthropic-compatible API surface, but designed for pay-as-you-go keys. Collapsible reasoning block, region auto-detection, walkthrough for first-time setup. See [docs/research/minimax-vscode-extension.md](../research/minimax-vscode-extension.md) for the full side-by-side comparison.
|
|
8
13
|
>
|
|
9
|
-
>
|
|
14
|
+
> If you'd rather not install an extension, the manual setup below works with both PAYG and Token Plan keys via the OpenAI-compatible endpoint.
|
|
10
15
|
|
|
11
16
|
## At a Glance
|
|
12
17
|
|
|
@@ -110,6 +115,62 @@ When the Token Plan 5-hour or weekly quota is exhausted, the request fails with
|
|
|
110
115
|
|
|
111
116
|
> API keys are region-specific. The same PAYG-vs-Token-Plan distinction applies to the China region (`api.minimaxi.com`); Subscription Keys are issued at `platform.minimaxi.com/user-center/payment/token-plan`.
|
|
112
117
|
|
|
118
|
+
### 5. M3 Priority tier (optional)
|
|
119
|
+
|
|
120
|
+
MiniMax exposes M3 with a per-request **`service_tier`** switch that promotes the request into MiniMax's priority admission queue. Priority is **not** a separate model — it is the same `MiniMax-M3` weights invoked with `"service_tier": "priority"` in the request body, costing **1.5× Standard** 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.
|
|
121
|
+
|
|
122
|
+
To add a separate Priority entry to your picker, add a second model block to the same `MiniMax` group with a distinct `id` and `name`, and set `"service_tier": "priority"` in `requestBody`:
|
|
123
|
+
|
|
124
|
+
```json
|
|
125
|
+
{
|
|
126
|
+
"name": "MiniMax",
|
|
127
|
+
"vendor": "customendpoint",
|
|
128
|
+
"apiKey": "",
|
|
129
|
+
"apiType": "chat-completions",
|
|
130
|
+
"models": [
|
|
131
|
+
{
|
|
132
|
+
"id": "MiniMax-M3",
|
|
133
|
+
"name": "MiniMax M3 (Standard)",
|
|
134
|
+
"url": "https://api.minimax.io/v1/chat/completions",
|
|
135
|
+
"toolCalling": true,
|
|
136
|
+
"vision": true,
|
|
137
|
+
"streaming": true,
|
|
138
|
+
"maxInputTokens": 1048576,
|
|
139
|
+
"maxOutputTokens": 131072,
|
|
140
|
+
"requestBody": {
|
|
141
|
+
"thinking": { "type": "adaptive" },
|
|
142
|
+
"reasoning_split": true,
|
|
143
|
+
"temperature": 1,
|
|
144
|
+
"top_p": 0.95
|
|
145
|
+
}
|
|
146
|
+
},
|
|
147
|
+
{
|
|
148
|
+
"id": "MiniMax-M3-Priority",
|
|
149
|
+
"name": "MiniMax M3 (Priority)",
|
|
150
|
+
"url": "https://api.minimax.io/v1/chat/completions",
|
|
151
|
+
"toolCalling": true,
|
|
152
|
+
"vision": true,
|
|
153
|
+
"streaming": true,
|
|
154
|
+
"maxInputTokens": 1048576,
|
|
155
|
+
"maxOutputTokens": 131072,
|
|
156
|
+
"requestBody": {
|
|
157
|
+
"thinking": { "type": "adaptive" },
|
|
158
|
+
"reasoning_split": true,
|
|
159
|
+
"temperature": 1,
|
|
160
|
+
"top_p": 0.95,
|
|
161
|
+
"service_tier": "priority"
|
|
162
|
+
}
|
|
163
|
+
}
|
|
164
|
+
]
|
|
165
|
+
}
|
|
166
|
+
```
|
|
167
|
+
|
|
168
|
+
Or, if you only ever want Priority, add `"service_tier": "priority"` to the single `MiniMax-M3` entry from step 1.
|
|
169
|
+
|
|
170
|
+
> The `id` field is purely a VS Code picker identifier — VS Code does not forward it to MiniMax. Both entries hit the same `MiniMax-M3` model; the suffix is a local label. The `service_tier` parameter is supported on **both** the OpenAI-compatible and Anthropic-compatible endpoints.
|
|
171
|
+
|
|
172
|
+
For the full breakdown (effective pricing, session cost, when Priority is worth the 50% premium), see [docs/research/minimax-m3-priority.md](../research/minimax-m3-priority.md).
|
|
173
|
+
|
|
113
174
|
## Notes
|
|
114
175
|
|
|
115
176
|
- **`thinking: adaptive` + `reasoning_split: true`** is the recommended pair: the model decides when to reason, and the server returns reasoning in a structured `reasoning_details` field that keeps `content` clean for VS Code. The model still reasons regardless of `thinking.type` — the setting only changes the response field layout.
|
|
@@ -133,16 +194,27 @@ When the Token Plan 5-hour or weekly quota is exhausted, the request fails with
|
|
|
133
194
|
|
|
134
195
|
## Pricing
|
|
135
196
|
|
|
136
|
-
For the cross-provider comparison, see [docs/pricing.md](../pricing.md). MiniMax-M3 pay-as-you-go rates:
|
|
197
|
+
For the cross-provider comparison, see [docs/pricing.md](../pricing.md). MiniMax-M3 pay-as-you-go rates (effective — post-50%-off):
|
|
198
|
+
|
|
199
|
+
### Standard tier
|
|
200
|
+
|
|
201
|
+
| Token range | Input (Cache Hit) | Input (Cache Miss) | Output |
|
|
202
|
+
| --------------------- | ----------------- | ------------------ | ---------- |
|
|
203
|
+
| ≤ 512K input tokens | $0.06 / 1M | $0.30 / 1M | $1.20 / 1M |
|
|
204
|
+
| > 512K input tokens\* | $0.12 / 1M | $0.60 / 1M | $2.40 / 1M |
|
|
205
|
+
|
|
206
|
+
### Priority tier (`"service_tier": "priority"`)
|
|
207
|
+
|
|
208
|
+
Priority is the **same `MiniMax-M3` model** invoked with the `service_tier` admission preference. It costs **1.5× Standard** and earns priority admission during MiniMax peak hours.
|
|
137
209
|
|
|
138
210
|
| Token range | Input (Cache Hit) | Input (Cache Miss) | Output |
|
|
139
211
|
| --------------------- | ----------------- | ------------------ | ---------- |
|
|
140
|
-
| ≤ 512K input tokens | $0.
|
|
141
|
-
| > 512K input tokens\* | $0.
|
|
212
|
+
| ≤ 512K input tokens | $0.09 / 1M | $0.45 / 1M | $1.80 / 1M |
|
|
213
|
+
| > 512K input tokens\* | $0.18 / 1M | $0.90 / 1M | $3.60 / 1M |
|
|
142
214
|
|
|
143
215
|
\* Input tokens above 512K are available in limited quantity for a limited time.
|
|
144
216
|
|
|
145
|
-
> **Permanent 50% off:** A standing 50% discount applies to all MiniMax-M3 pay-as-you-go usage on both the Standard and Priority tiers (verified June 9, 2026). The effective rates are $0.
|
|
217
|
+
> **Permanent 50% off:** A standing 50% discount applies to all MiniMax-M3 pay-as-you-go usage on both the Standard and Priority tiers (verified June 9, 2026). The effective rates above are post-discount. List prices (pre-discount) are 2× higher: Standard ≤512K is $0.12 / $0.60 / $2.40; Priority ≤512K is $0.18 / $0.90 / $3.60. See [docs/research/minimax-m3-priority.md](../research/minimax-m3-priority.md) for the full breakdown of when Priority is worth the 50% premium.
|
|
146
218
|
|
|
147
219
|
### Token Plan (subscription)
|
|
148
220
|
|
package/docs/pricing.md
CHANGED
|
@@ -20,33 +20,34 @@ All prices below are in **USD per 1M tokens** (non-cached). To convert to AI cre
|
|
|
20
20
|
|
|
21
21
|
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.
|
|
22
22
|
|
|
23
|
-
| Model
|
|
24
|
-
|
|
|
25
|
-
| **DeepSeek V4 Flash**
|
|
26
|
-
| **MiMo V2.5**
|
|
27
|
-
| **MiniMax M3**
|
|
28
|
-
| **DeepSeek V4 Pro**
|
|
29
|
-
| **MiMo V2.5 Pro**
|
|
30
|
-
| **Qwen 3.7 Plus**
|
|
31
|
-
| **
|
|
32
|
-
| **
|
|
33
|
-
| **Kimi K2.
|
|
34
|
-
| **
|
|
35
|
-
| **
|
|
36
|
-
| **GLM 5.
|
|
37
|
-
| **GLM
|
|
38
|
-
| **
|
|
39
|
-
| **
|
|
40
|
-
| **
|
|
41
|
-
| **
|
|
42
|
-
| **GPT-5.
|
|
43
|
-
| **
|
|
44
|
-
| **Claude
|
|
45
|
-
| **Claude Opus 4.
|
|
46
|
-
| **
|
|
47
|
-
| **
|
|
48
|
-
| **
|
|
49
|
-
| **
|
|
23
|
+
| Model | Provider | Cost per intelligence | Intelligence Score | Input (per 1M) | Cached input | Output (per 1M) | Est. session | Context window |
|
|
24
|
+
| ------------------------ | --------- | --------------------- | ------------------ | ----------------------------- | ----------------------------- | ----------------------------- | ------------ | -------------- |
|
|
25
|
+
| **DeepSeek V4 Flash** | DeepSeek | **~$0.0025** | **40.3** | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
|
|
26
|
+
| **MiMo V2.5** | Xiaomi | **~$0.0025** | **40** ³ | $0.14 | $0.0028 | $0.28 | ~$0.10 | 1M |
|
|
27
|
+
| **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
|
+
| **DeepSeek V4 Pro** | DeepSeek | **~$0.0068** | **44.3** | $0.435 | $0.003625 | $0.87 | ~$0.30 | 1M |
|
|
29
|
+
| **MiMo V2.5 Pro** | Xiaomi | **~$0.0072** | **42.2** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
|
|
30
|
+
| **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | $0.40 (≤256K) / $1.20 (>256K) | — | $1.60 (≤256K) / $4.80 (>256K) | ~$0.36 | 1M |
|
|
31
|
+
| **MiniMax M3 Priority**⁵ | MiniMax | **~$0.0092** | **44.4** | $0.90 (≤512K) / $1.80 (>512K) | $0.18 (≤512K) / $0.36 (>512K) | $3.60 (≤512K) / $7.20 (>512K) | ~$0.41 | 1M |
|
|
32
|
+
| **Gemini 3 Flash** | Google | **~$0.020** | **27.0** ³ | $0.50 | $0.05 | $3.00 | ~$0.55 | 173K |
|
|
33
|
+
| **Kimi K2.6** | Moonshot | **~$0.021** | **42.8** | $0.95 | $0.16 | $4.00 | ~$0.88 | 256K |
|
|
34
|
+
| **Kimi K2.7 Code** | Moonshot | **~$0.021** | **42.0** | $0.95 | $0.19 | $4.00 | ~$0.88 | 262K |
|
|
35
|
+
| **GPT-5.4 mini** | OpenAI | **~$0.021** | **40.0** | $0.75 | $0.075 | $4.50 | ~$0.83 | 400K |
|
|
36
|
+
| **GLM 5.2** ⁴ | Z.ai | **~$0.022** | **51.0** | $1.40 | $0.26 | $4.40 | ~$1.14 | 1M |
|
|
37
|
+
| **GLM 5.1** | Z.ai | **~$0.028** | **40.2** | $1.40 | $0.26 | $4.40 | ~$1.14 | 200K |
|
|
38
|
+
| **GLM 5V Turbo** | Z.ai | **~$0.029** | **34.0** ³ | $1.20 | $0.24 | $4.00 | ~$1.00 | 200K |
|
|
39
|
+
| **Gemini 3.5 Flash** | Google | **~$0.033** | **50.2** | $1.50 | $0.15 | $9.00 | ~$1.65 | 1M |
|
|
40
|
+
| **Qwen 3.7 Max** | DashScope | **~$0.043** | **46.0** | $2.50 (≤1M) | — | $7.50 (≤1M) | ~$2.00 | 1M |
|
|
41
|
+
| **Gemini 3.1 Pro** | Google | **~$0.047** | **46.5** | $2.00¹ | $0.20 | $12.00¹ | ~$2.20 | 1M |
|
|
42
|
+
| **GPT-5.3-Codex** | OpenAI | **~$0.052** | **44.0** ³ | $1.75 | $0.175 | $14.00 | ~$2.28 | 400K |
|
|
43
|
+
| **GPT-5.4** | OpenAI | **~$0.054** | **51.4** | $2.50 | $0.25 | $15.00 | ~$2.75 | 1M |
|
|
44
|
+
| **Claude Sonnet 4.6** | Anthropic | **~$0.064** | **47.2** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
|
|
45
|
+
| **Claude Opus 4.8** | Anthropic | **~$0.090** | **55.7** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
|
|
46
|
+
| **Claude Opus 4.7** | Anthropic | **~$0.093** | **53.5** | $5.00 | $0.50 | $25.00 | ~$5.00 | 1M |
|
|
47
|
+
| **GPT-5.5** | OpenAI | **~$0.10** | **54.8** | $5.00 | $0.50 | $30.00 | ~$5.50 | 1M |
|
|
48
|
+
| **Raptor mini** | GitHub | — | — | $0.25 | $0.025 | $2.00 | ~$0.33 | 264K |
|
|
49
|
+
| **MAI-Code-1-Flash** ² | Microsoft | — | — | $0.75 | $0.075 | $4.50 | ~$0.83 | — |
|
|
50
|
+
| **Claude Haiku 4.5** | Anthropic | — | — | $1.00 | $0.10 | $5.00 | ~$1.00 | 160K |
|
|
50
51
|
|
|
51
52
|
¹ Gemini 3.1 Pro pricing applies to prompts ≤200K tokens.
|
|
52
53
|
|
|
@@ -56,6 +57,8 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
56
57
|
|
|
57
58
|
⁴ GLM 5.2 is Z.ai's newly released flagship model (Opus-level intelligence / 1M Solid context). AA Intelligence Index score (**51.0**) and pricing of **$1.40** (input), **$0.26** (cached), and **$4.40** (output) per 1M tokens confirmed on its [model page](https://artificialanalysis.ai/models/glm-5-2). Session cost is identical to GLM 5.1 (~$1.14).
|
|
58
59
|
|
|
60
|
+
⁵ **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 (list prices shown above; effective rates after the standing 50% off are $0.45/$1.80/$0.09 ≤512K and $0.90/$3.60/$0.18 >512K), 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. To enable it on a custom-endpoint entry, add `"service_tier": "priority"` to `requestBody`. See [docs/research/minimax-m3-priority.md](research/minimax-m3-priority.md) for the full breakdown.
|
|
61
|
+
|
|
59
62
|
Cost per intelligence = estimated session cost ÷ Intelligence Index score. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
|
|
60
63
|
|
|
61
64
|
> **Notes:**
|
|
@@ -70,10 +73,12 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
|
|
|
70
73
|
> - **Kimi K2.6** pricing is from the **Moonshot platform** (direct). Via DashScope: $0.89 input / $3.71 output.
|
|
71
74
|
> - **DashScope** offers a **free quota** of 1M input + 1M output tokens per model, valid for 90 days.
|
|
72
75
|
> - **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.
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
> - **
|
|
76
|
-
> -
|
|
76
|
+
|
|
77
|
+
- **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.
|
|
78
|
+
> - **GLM** models support prompt caching — cache hits are priced at $0.24/M for 5V Turbo and $0.26/M for 5.1.
|
|
79
|
+
> - **MiMo** offers a **Token Plan** subscription model with discounted rates and a free cache-writing promotion.
|
|
80
|
+
> - **MAI-Code-1-Flash** is a continuously improving model — performance and behavior may evolve over time as new checkpoints are released.
|
|
81
|
+
> - For typical Copilot chat usage (short-to-medium prompts), you'll almost always fall in the lowest pricing tier.
|
|
77
82
|
|
|
78
83
|
> **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.)
|
|
79
84
|
|