copilot-custom-endpoint 1.8.1 → 1.9.0
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/example-config.md +15 -1
- package/docs/models/kimi.md +43 -22
- package/docs/pricing.md +7 -6
- package/package.json +1 -1
- package/proxy/kimi-proxy.mjs +29 -9
package/README.md
CHANGED
|
@@ -22,6 +22,7 @@ That's it. No code, no servers to manage (unless the model specifically needs th
|
|
|
22
22
|
|
|
23
23
|
| Model | Provider | Needs proxy? | Vision | Setup guide |
|
|
24
24
|
| --------------------------- | --------- | ---------------------- | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
|
|
25
|
+
| **Kimi K3** | Moonshot | **Yes** | ✅ | [Manual setup](docs/models/kimi.md) |
|
|
25
26
|
| **MiMo V2.5** | Xiaomi | Optional (recommended) | ✅ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) ★ / [Manual setup](docs/models/mimo.md) |
|
|
26
27
|
| **MiMo V2.5 Pro** | Xiaomi | Optional (recommended) | ❌ | [Extension](https://marketplace.visualstudio.com/items?itemName=sdmapvstool.xiaomimimo-for-copilot) ★ / [Manual setup](docs/models/mimo.md) |
|
|
27
28
|
| **Kimi K2.7 Code / K2.6** | Moonshot | **Yes** | ✅ | [Manual setup](docs/models/kimi.md) |
|
|
@@ -117,7 +118,6 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
|
|
|
117
118
|
| **MiMo V2.5 Pro** | Xiaomi | **~$0.0072** | **42.2** | ~$0.30 | ❌ | 1M |
|
|
118
119
|
| **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | ~$0.36 | ✅ | 1M |
|
|
119
120
|
| **MiniMax M3 Priority**⁴ | MiniMax | **~$0.0092** | **44.4** | ~$0.41 | ✅ | 1M |
|
|
120
|
-
| **Gemini 3 Flash** | Google | **~$0.020** | **27.0** ³ | ~$0.55 | ✅ | 173K |
|
|
121
121
|
| **Kimi K2.6** | Moonshot | **~$0.021** | **42.8** | ~$0.88 | ✅ | 262K |
|
|
122
122
|
| **Kimi K2.7 Code** | Moonshot | **~$0.021** | **42.0** | ~$0.88 | ✅ | 262K |
|
|
123
123
|
| **GPT-5.4 mini** | OpenAI | **~$0.021** | **40.0** | ~$0.83 | ❌ | 400K |
|
|
@@ -129,6 +129,7 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
|
|
|
129
129
|
| **Qwen 3.7 Max** | DashScope | **~$0.043** | **46.0** | ~$2.00 | ❌ | 1M |
|
|
130
130
|
| **Gemini 3.1 Pro** | Google | **~$0.047** | **46.5** | ~$2.20 | ✅ | 1M |
|
|
131
131
|
| **GPT-5.6 Terra** | OpenAI | **~$0.050** | **55.0** | ~$2.75 | ✅ | 1M |
|
|
132
|
+
| **Kimi K3** ⁶ | Moonshot | **~$0.053** | **57.0** | ~$3.00 | ✅ | 1M |
|
|
132
133
|
| **GPT-5.4** | OpenAI | **~$0.054** | **51.4** | ~$2.75 | ✅ | 1M |
|
|
133
134
|
| **Claude Sonnet 5** ⁵ | Anthropic | **~$0.057** | **53.0** | ~$3.00 | ✅ | 1M |
|
|
134
135
|
| **Claude Sonnet 4.6** | Anthropic | **~$0.064** | **47.2** | ~$3.00 | ✅ | 1M |
|
|
@@ -153,6 +154,8 @@ All prices are **USD per 1M tokens** (non-cached). 1 AI credit = $0.01. To conve
|
|
|
153
154
|
|
|
154
155
|
⁶ **GPT-5.6** launched July 9, 2026. Sol, Terra, and Luna cost $5/$30, $2.50/$15, and $1/$6 per 1M input/output tokens respectively; all support image input and 1M context. Benchmark details and cache-write pricing are maintained in [docs/pricing.md](docs/pricing.md).
|
|
155
156
|
|
|
157
|
+
⁷ **Kimi K3** launched July 16, 2026. 2.8T params (open-source weights by July 27, 2026). Always-thinking reasoning model — uses `reasoning_effort` (not the K2.x `thinking` parameter). AA Intelligence Index score of **57.0** confirmed by [Artificial Analysis](https://artificialanalysis.ai/models/kimi-k3). Priced at $3.00 / $15.00 per MTok input/output. Requires the local Kimi proxy. See [docs/models/kimi.md](docs/models/kimi.md).
|
|
158
|
+
|
|
156
159
|
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).
|
|
157
160
|
|
|
158
161
|
> **👤 Personal picks** —
|
|
@@ -164,11 +167,10 @@ For footnotes, sources, and detailed notes (cache behavior, tiered pricing, free
|
|
|
164
167
|
> - No local proxy required — works direct
|
|
165
168
|
> **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.
|
|
166
169
|
>
|
|
167
|
-
> For **plan mode / architecture & design thinking**, **GLM 5.2**
|
|
170
|
+
> For **plan mode / architecture & design thinking**, **Kimi K3** and **GLM 5.2** are worth the premium:
|
|
168
171
|
>
|
|
169
|
-
> - Highest intelligence score
|
|
170
|
-
> - 1M lossless context, ideal for whole-codebase planning and large spec review
|
|
171
|
-
> - ~$1.14/session is ~4× MiniMax M3, so **not a daily driver for agent mode** — reserve it for planning, then hand implementation off to a cheaper model.
|
|
172
|
+
> - **Kimi K3** — new flagship. Highest intelligence score among custom-endpoint models (**57.0**, #3 overall). Best for complex reasoning, long-horizon planning, and architecture decisions. 1M context with vision. ~$3.00/session is ~11× MiniMax M3, so **not a daily driver** — reserve it for hard problems.
|
|
173
|
+
> - **GLM 5.2** — scores **51.0**, reasoning-heavy planning at a lower price. 1M lossless context, ideal for whole-codebase planning and large spec review. ~$1.14/session is ~4× MiniMax M3, so **not a daily driver for agent mode** — reserve it for planning, then hand implementation off to a cheaper model.
|
|
172
174
|
>
|
|
173
175
|
> Cheaper alternatives for simpler tasks:
|
|
174
176
|
>
|
package/docs/example-config.md
CHANGED
|
@@ -40,6 +40,20 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
|
|
|
40
40
|
"apiKey": "",
|
|
41
41
|
"apiType": "chat-completions",
|
|
42
42
|
"models": [
|
|
43
|
+
{
|
|
44
|
+
"id": "kimi-k3",
|
|
45
|
+
"name": "Kimi K3 (vision)",
|
|
46
|
+
"url": "http://127.0.0.1:3457/v1/chat/completions",
|
|
47
|
+
"requestBody": {
|
|
48
|
+
"temperature": 1,
|
|
49
|
+
"max_tokens": 8192
|
|
50
|
+
},
|
|
51
|
+
"toolCalling": true,
|
|
52
|
+
"vision": true,
|
|
53
|
+
"streaming": true,
|
|
54
|
+
"maxInputTokens": 1000000,
|
|
55
|
+
"maxOutputTokens": 131072
|
|
56
|
+
},
|
|
43
57
|
{
|
|
44
58
|
"id": "kimi-k2.6",
|
|
45
59
|
"name": "Kimi K2.6 (vision)",
|
|
@@ -189,7 +203,7 @@ Here's a complete, real-world `chatLanguageModels.json` that combines **the `cus
|
|
|
189
203
|
|
|
190
204
|
If you only need one provider, jump straight to its setup guide:
|
|
191
205
|
|
|
192
|
-
- [Kimi K2.6 / K2.7 Code](kimi.md)
|
|
206
|
+
- [Kimi K3 / K2.6 / K2.7 Code](kimi.md)
|
|
193
207
|
- [Qwen 3.7 Plus / 3.7 Max](qwen.md)
|
|
194
208
|
- [Xiaomi MiMo (V2.5 / V2.5 Pro)](mimo.md)
|
|
195
209
|
- [MiniMax M3 (Standard)](minimax.md) and [MiniMax M3 (Priority)](minimax.md#5-m3-priority-tier-optional)
|
package/docs/models/kimi.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
|
1
1
|
# Kimi (Moonshot) — VS Code Custom Endpoint Setup Guide
|
|
2
2
|
|
|
3
|
-
> **TL;DR:** Kimi models require the local proxy. The K2 family locks `temperature: 1` and `top_p: 0.95`. K2.6 needs `thinking: { type: "disabled" }` on tool turns; **K2.7 Code is always-thinking and rejects `thinking: disabled
|
|
3
|
+
> **TL;DR:** Kimi models require the local proxy. The K2/K3 family locks `temperature: 1` and `top_p: 0.95`. K2.6 needs `thinking: { type: "disabled" }` on tool turns; **K2.7 Code is always-thinking and rejects `thinking: disabled`**. **K3 is always-thinking and uses `reasoning_effort` (not the `thinking` parameter)** — the proxy detects `kimi-k3` and skips the thinking-disable rewrite while keeping sampling enforcement. Direct VS Code → Moonshot is not viable.
|
|
4
|
+
>
|
|
5
|
+
> **🆕 Kimi K3** (released July 16, 2026) is Kimi's flagship — 2.8T parameters, 1M context, AA Intelligence Index **57.0** (#3 overall, between GPT-5.6 Sol and Claude Opus 4.8). Open-source weights coming by July 27, 2026.
|
|
4
6
|
>
|
|
5
7
|
> **🆕 Alternative:** On the **Kimi Coding tier** (`kimi.com/code/console`), the [**Moonshot LM Provider**](https://marketplace.visualstudio.com/items?itemName=DenizhanDaklr.kimi-lm-provider) extension offers zero-proxy setup with reasoning visibility. **Not compatible with Pay-as-You-Go** keys from `platform.kimi.ai`. See [the extension comparison](../research/kimi-vscode-extension.md).
|
|
6
8
|
|
|
@@ -20,12 +22,13 @@
|
|
|
20
22
|
|
|
21
23
|
### Models
|
|
22
24
|
|
|
23
|
-
| Model | Vision | Context | Max output | Notes
|
|
24
|
-
| ---------------- | ------ | ------- | ---------- |
|
|
25
|
-
| `kimi-
|
|
26
|
-
| `kimi-k2.
|
|
25
|
+
| Model | Vision | Context | Max output | Notes |
|
|
26
|
+
| ---------------- | ------ | ------- | ---------- | -------------------------------------------------------------------------------------------------------- |
|
|
27
|
+
| `kimi-k3` | ✅ Yes | 1M | 131072 | **Flagship.** Always-thinking, uses `reasoning_effort` (not `thinking`). 2.8T params. AA Index **57.0**. |
|
|
28
|
+
| `kimi-k2.6` | ✅ Yes | 262K | 32768 | Proxy forces `thinking: { type: "disabled" }` on tool turns |
|
|
29
|
+
| `kimi-k2.7-code` | ✅ Yes | 262K | 4096 | Always-thinking; rejects `thinking: disabled`. Keep `maxOutputTokens` low (4096). |
|
|
27
30
|
|
|
28
|
-
> Deprecated K2 ids (`kimi-k2-0905-preview`, `kimi-k2-turbo-preview`, `kimi-k2-thinking`, etc.) were discontinued May 25, 2026 — use K2.6
|
|
31
|
+
> Deprecated K2 ids (`kimi-k2-0905-preview`, `kimi-k2-turbo-preview`, `kimi-k2-thinking`, etc.) were discontinued May 25, 2026 — use K2.6, K2.7, or K3.
|
|
29
32
|
|
|
30
33
|
## Quick Start
|
|
31
34
|
|
|
@@ -33,7 +36,7 @@
|
|
|
33
36
|
2. **Edit `chatLanguageModels.json`** — add the Kimi block below.
|
|
34
37
|
3. **Set your Moonshot API key** via Command Palette → **Chat: Manage Language Models**.
|
|
35
38
|
4. **Configure the Utility Small Model** — Open Settings → search **"Chat: Utility Small Model"** → pick your fastest model (e.g., DeepSeek V4 Flash or MiMo V2.5). [Why?](../../README.md#4-configure-the-utility-small-model)
|
|
36
|
-
5. **Restart VS Code** and pick "Kimi K2.6" or "Kimi K2.7 Code".
|
|
39
|
+
5. **Restart VS Code** and pick "Kimi K3", "Kimi K2.6", or "Kimi K2.7 Code".
|
|
37
40
|
|
|
38
41
|
## Setup
|
|
39
42
|
|
|
@@ -52,6 +55,17 @@
|
|
|
52
55
|
"apiKey": "",
|
|
53
56
|
"apiType": "chat-completions",
|
|
54
57
|
"models": [
|
|
58
|
+
{
|
|
59
|
+
"id": "kimi-k3",
|
|
60
|
+
"name": "Kimi K3 (vision)",
|
|
61
|
+
"url": "http://127.0.0.1:3457/v1/chat/completions",
|
|
62
|
+
"requestBody": { "temperature": 1, "max_tokens": 8192 },
|
|
63
|
+
"toolCalling": true,
|
|
64
|
+
"vision": true,
|
|
65
|
+
"streaming": true,
|
|
66
|
+
"maxInputTokens": 1000000,
|
|
67
|
+
"maxOutputTokens": 131072
|
|
68
|
+
},
|
|
55
69
|
{
|
|
56
70
|
"id": "kimi-k2.6",
|
|
57
71
|
"name": "Kimi K2.6 (vision)",
|
|
@@ -78,6 +92,8 @@
|
|
|
78
92
|
}
|
|
79
93
|
```
|
|
80
94
|
|
|
95
|
+
> **K3 note:** `max_tokens` is set to **8192** as a safe starting point. K3 is always-thinking and very verbose (130M tokens generated on the AA Intelligence Index evaluation). The API default for `max_completion_tokens` is 131072 and can go up to 1048576, but reasoning tokens inflate response size — monitor your usage and adjust upward if needed. Unlike K2.7, K3 uses `reasoning_effort` (not `thinking`); the proxy handles this automatically.
|
|
96
|
+
>
|
|
81
97
|
> **K2.7 note:** `max_tokens` and `maxOutputTokens` are intentionally conservative at **4096**. K2.7 is always-thinking, so reasoning tokens inflate response size. Values above 24K triggered VS Code's "Response too long" error in agent mode.
|
|
82
98
|
|
|
83
99
|
### 2. API key
|
|
@@ -93,7 +109,7 @@ Kimi is **Pay-as-You-Go only** — no subscription. A single Open Platform API k
|
|
|
93
109
|
|
|
94
110
|
## Local Proxy
|
|
95
111
|
|
|
96
|
-
The `proxy/kimi-proxy.mjs` is **required** for Kimi — K2-family sampling constraints and tool-turn thinking behaviour cannot be satisfied by VS Code's direct path. See [Quick Start](#quick-start) for the launch command.
|
|
112
|
+
The `proxy/kimi-proxy.mjs` is **required** for Kimi — K2/K3-family sampling constraints and tool-turn thinking behaviour cannot be satisfied by VS Code's direct path. See [Quick Start](#quick-start) for the launch command.
|
|
97
113
|
|
|
98
114
|
| Setting | Value |
|
|
99
115
|
| ------------ | ----------------------------------------------------- |
|
|
@@ -123,33 +139,38 @@ Set in `.env` at the repo root (the proxy `import 'dotenv/config'` automatically
|
|
|
123
139
|
- Rewrites plain-chat requests to `temperature: 1`, `top_p: 0.95`.
|
|
124
140
|
- For **K2.5 / K2.6**: rewrites tool-enabled requests to `thinking: { type: "disabled" }`, `temperature: 0.6`, `top_p: 0.95`.
|
|
125
141
|
- For **K2.7 Code**: keeps thinking enabled (K2.7 rejects `thinking: disabled` with HTTP 400); rewrites to `temperature: 1`, `top_p: 0.95`.
|
|
142
|
+
- For **K3**: keeps thinking enabled (K3 is always-thinking and uses `reasoning_effort`, not `thinking`); rewrites to `temperature: 1`, `top_p: 0.95`. Does **not** inject a `thinking` block — K3 rejects it.
|
|
126
143
|
- Preserves streaming responses (SSE).
|
|
127
144
|
- Writes redacted request summaries to `debug_log/kimi-proxy.ndjson`.
|
|
128
145
|
|
|
129
146
|
## Notes
|
|
130
147
|
|
|
148
|
+
- **Kimi K3** (released July 16, 2026) is Kimi's new flagship. 2.8T params, 1M context, always-thinking. Uses `reasoning_effort` (currently only `max`) — do **not** send the K2.x `thinking` parameter. `tool_choice` supports `auto`, `required`, and named tools. `max_completion_tokens` defaults to 131072 and can go up to 1048576. Fixed sampling: `temperature=1`, `top_p=0.95`. Vision supports text + image + video (via `ms://<file-id>` URLs). See the [K3 quickstart](https://platform.kimi.ai/docs/guide/kimi-k3-quickstart).
|
|
131
149
|
- **K2.7 Code** is always-thinking. `max_tokens` and `maxOutputTokens` are intentionally conservative at **4096** — reasoning tokens inflate response size and values above 24K triggered VS Code's "Response too long" error in agent mode.
|
|
132
150
|
- **K2 platform rebranding:** the Kimi Platform (formerly Moonshot) rebranded to `platform.kimi.ai` in 2026 — `api.moonshot.ai` still resolves and the proxy targets it unchanged.
|
|
133
|
-
- **`tool_choice` only supports `auto`** — don't override it (VS Code's default is `auto`).
|
|
151
|
+
- **`tool_choice` for K2.x only supports `auto`** — don't override it (VS Code's default is `auto`). K3 also supports `required` and named tools.
|
|
152
|
+
- **K3 `reasoning_effort` vs K2.x `thinking`:** K3 uses `reasoning_effort` (currently only `max` level) at the top level of the request body. Do not mix this with the K2.x `thinking` parameter — K3 rejects it. The proxy preserves whatever `reasoning_effort` VS Code sends and only enforces temperature/top_p.
|
|
134
153
|
|
|
135
154
|
## Troubleshooting
|
|
136
155
|
|
|
137
|
-
| Symptom | Likely cause
|
|
138
|
-
| ------------------------------------------------------ |
|
|
139
|
-
| "Connection refused" on chat | Proxy not running
|
|
140
|
-
| `invalid temperature: only 1 is allowed` | Direct path without proxy
|
|
141
|
-
| `invalid top_p: only 0.95 is allowed` | Direct path without proxy
|
|
142
|
-
| `thinking is enabled but reasoning_content is missing` | Tool turn with thinking on
|
|
143
|
-
|
|
|
144
|
-
|
|
|
156
|
+
| Symptom | Likely cause | Fix |
|
|
157
|
+
| ------------------------------------------------------ | ---------------------------- | ------------------------------------------------- |
|
|
158
|
+
| "Connection refused" on chat | Proxy not running | `npm run proxy:kimi` |
|
|
159
|
+
| `invalid temperature: only 1 is allowed` | Direct path without proxy | Use the proxy |
|
|
160
|
+
| `invalid top_p: only 0.95 is allowed` | Direct path without proxy | Use the proxy |
|
|
161
|
+
| `thinking is enabled but reasoning_content is missing` | Tool turn with thinking on | Verify `KIMI_PROXY_DISABLE_THINKING_WITH_TOOLS=1` |
|
|
162
|
+
| `unsupported parameter: thinking` with K3 | K3 doesn't accept `thinking` | Use `reasoning_effort` instead; proxy detects K3 |
|
|
163
|
+
| Model not in VS Code picker | Config not reloaded | Restart VS Code |
|
|
164
|
+
| `tool_choice=required` rejected (K2.x) | Model limitation | Use `auto` only for K2.x; K3 supports `required` |
|
|
145
165
|
|
|
146
166
|
## Pricing
|
|
147
167
|
|
|
148
168
|
For the cross-provider comparison, see [docs/pricing.md](../pricing.md). Moonshot direct platform rates:
|
|
149
169
|
|
|
150
|
-
| Model | Input (cache miss) | Cached input | Output
|
|
151
|
-
| ---------------- | ------------------ | ------------ |
|
|
152
|
-
| `kimi-
|
|
153
|
-
| `kimi-k2.
|
|
170
|
+
| Model | Input (cache miss) | Cached input | Output |
|
|
171
|
+
| ---------------- | ------------------ | ------------ | ----------- |
|
|
172
|
+
| `kimi-k3` | $3.00 / 1M | $0.30 / 1M | $15.00 / 1M |
|
|
173
|
+
| `kimi-k2.6` | $0.95 / 1M | $0.16 / 1M | $4.00 / 1M |
|
|
174
|
+
| `kimi-k2.7-code` | $0.95 / 1M | $0.19 / 1M | $4.00 / 1M |
|
|
154
175
|
|
|
155
|
-
> K2.7 has no non-thinking mode. Via DashScope, K2.6 is also available at $0.89 / 1M input and $3.71 / 1M output.
|
|
176
|
+
> K3 pricing is flat (no tiering by context length). K2.7 has no non-thinking mode. Via DashScope, K2.6 is also available at $0.89 / 1M input and $3.71 / 1M output.
|
package/docs/pricing.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Pricing
|
|
2
2
|
|
|
3
|
-
> **Updated:** July
|
|
3
|
+
> **Updated:** July 17, 2026 — Kimi K3 added (released July 16, 2026). AA Intelligence Index **57.0**, pricing $3.00 / $15.00 per MTok input/output.
|
|
4
4
|
|
|
5
5
|
> **⏰ June 1, 2026 — GitHub Copilot switched to usage-based billing (AI Credits) today.**
|
|
6
6
|
>
|
|
@@ -31,7 +31,6 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
31
31
|
| **MiMo V2.5 Pro** | Xiaomi | **~$0.0072** | **42.2** | $0.435 | $0.0036 | $0.87 | ~$0.30 | 1M |
|
|
32
32
|
| **Qwen 3.7 Plus** | DashScope | **~$0.0092** | **39.0** | $0.40 (≤256K) / $1.20 (>256K) | — | $1.60 (≤256K) / $4.80 (>256K) | ~$0.36 | 1M |
|
|
33
33
|
| **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 |
|
|
34
|
-
| **Gemini 3 Flash** | Google | **~$0.020** | **27.0** ³ | $0.50 | $0.05 | $3.00 | ~$0.55 | 173K |
|
|
35
34
|
| **Kimi K2.6** | Moonshot | **~$0.021** | **42.8** | $0.95 | $0.16 | $4.00 | ~$0.88 | 256K |
|
|
36
35
|
| **Kimi K2.7 Code** | Moonshot | **~$0.021** | **42.0** | $0.95 | $0.19 | $4.00 | ~$0.88 | 262K |
|
|
37
36
|
| **GPT-5.4 mini** | OpenAI | **~$0.021** | **40.0** | $0.75 | $0.075 | $4.50 | ~$0.83 | 400K |
|
|
@@ -42,8 +41,9 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
42
41
|
| **Gemini 3.5 Flash** | Google | **~$0.033** | **50.2** | $1.50 | $0.15 | $9.00 | ~$1.65 | 1M |
|
|
43
42
|
| **Qwen 3.7 Max** | DashScope | **~$0.043** | **46.0** | $2.50 (≤1M) | — | $7.50 (≤1M) | ~$2.00 | 1M |
|
|
44
43
|
| **Gemini 3.1 Pro** | Google | **~$0.047** | **46.5** | $2.00¹ | $0.20 | $12.00¹ | ~$2.20 | 1M |
|
|
45
|
-
| **GPT-5.3-Codex** | OpenAI | **~$0.052** | **44.0** ³ | $1.75 | $0.175 | $14.00 | ~$2.28 | 400K |
|
|
46
44
|
| **GPT-5.6 Terra** | OpenAI | **~$0.050** | **55.0** | $2.50 | $0.25 | $15.00 | ~$2.75 | 1M |
|
|
45
|
+
| **GPT-5.3-Codex** | OpenAI | **~$0.052** | **44.0** ³ | $1.75 | $0.175 | $14.00 | ~$2.28 | 400K |
|
|
46
|
+
| **Kimi K3** ⁷ | Moonshot | **~$0.053** | **57.0** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
|
|
47
47
|
| **GPT-5.4** | OpenAI | **~$0.054** | **51.4** | $2.50 | $0.25 | $15.00 | ~$2.75 | 1M |
|
|
48
48
|
| **Claude Sonnet 5** ⁶ | Anthropic | **~$0.057** | **53.0** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
|
|
49
49
|
| **Claude Sonnet 4.6** | Anthropic | **~$0.064** | **47.2** | $3.00 | $0.30 | $15.00 | ~$3.00 | 1M |
|
|
@@ -67,7 +67,9 @@ All models are listed together below, sorted by Cost per intelligence ascending
|
|
|
67
67
|
|
|
68
68
|
⁶ **Claude Sonnet 5** has introductory pricing of **$2.00 / $0.20 / $10.00** (input / cached / output) through **August 31, 2026**, after which the standard pricing of $3.00 / $0.30 / $15.00 shown above takes effect. See [Anthropic's pricing page](https://claude.com/pricing) for the latest.
|
|
69
69
|
|
|
70
|
-
⁷ **
|
|
70
|
+
⁷ **Kimi K3** was released on **July 16, 2026**. 2.8T parameters (open-source, weights by July 27, 2026). 1M context window. Always-thinking reasoning model — uses `reasoning_effort` (not the K2.x `thinking` parameter). Fixed sampling: `temperature=1`, `top_p=0.95`. Pricing is flat (no tiering by context length). See [Kimi K3 pricing](https://platform.kimi.ai/docs/pricing/chat-k3) and the [Artificial Analysis model page](https://artificialanalysis.ai/models/kimi-k3).
|
|
71
|
+
|
|
72
|
+
⁸ **GPT-5.6** pricing is **$1.00 / $0.10 / $6.00** for Luna, **$2.50 / $0.25 / $15.00** for Terra, and **$5.00 / $0.50 / $30.00** for Sol (input / cached input / output per 1M tokens). OpenAI bills cache writes at 1.25x the uncached input rate for GPT-5.6 and later. All three tiers have a 1M-token context window and support text + image input. See [OpenAI's GPT-5.6 announcement](https://openai.com/index/gpt-5-6/) and the [Artificial Analysis model pages](https://artificialanalysis.ai/models/gpt-5-6-sol).
|
|
71
73
|
|
|
72
74
|
Cost per intelligence = estimated session cost ÷ Intelligence Index score. Session cost assumes ~10K input + ~2K output tokens per turn, 50 turns.
|
|
73
75
|
|
|
@@ -75,7 +77,6 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
|
|
|
75
77
|
>
|
|
76
78
|
> - **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).
|
|
77
79
|
> - **MiMo** input pricing shown is the **cache miss** price. Cache hits are essentially free for V2.5 Pro ($0.0036/M, ~120× cheaper) and V2.5 ($0.0028/M, ~50× cheaper). A Xiaomi price cut took effect on 2026-05-27.
|
|
78
|
-
> - **Gemini 3 Flash** is priced at $0.50/MTok input (text/image/video) and $1.00/MTok input for audio.
|
|
79
80
|
> - **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+, Sonnet 5, and Fable 5 use a new tokenizer that produces approximately 30% more tokens for the same text.
|
|
80
81
|
> - **OpenAI** models support cached input at 0.1× base input rate.
|
|
81
82
|
> - **Qwen** models use **tiered pricing** — determined by total input tokens per request. Prices above are for non-thinking mode.
|
|
@@ -91,7 +92,7 @@ Cost per intelligence = estimated session cost ÷ Intelligence Index score. Sess
|
|
|
91
92
|
|
|
92
93
|
> **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.)
|
|
93
94
|
|
|
94
|
-
> Prices last verified: July
|
|
95
|
+
> Prices last verified: July 17, 2026. Always check the official pages for the latest rates:
|
|
95
96
|
>
|
|
96
97
|
> - [GitHub Copilot models & pricing](https://docs.github.com/en/copilot/reference/copilot-billing/models-and-pricing)
|
|
97
98
|
> - [Microsoft MAI-Code-1-Flash model card](https://docs.github.com/en/copilot/reference/ai-models/model-comparison#task-general-purpose-coding-and-writing)
|
package/package.json
CHANGED
package/proxy/kimi-proxy.mjs
CHANGED
|
@@ -12,10 +12,15 @@ import { createProxy } from '../lib/create-proxy.mjs'
|
|
|
12
12
|
* always-thinking and rejects `thinking: { type: 'disabled' }`. The proxy
|
|
13
13
|
* detects K2.7 and skips the thinking-disable rewrite while keeping
|
|
14
14
|
* temperature/top_p enforcement.
|
|
15
|
+
* - Validated in this repo with `kimi-k3` (July 17, 2026). K3 is always-thinking
|
|
16
|
+
* and uses `reasoning_effort` (NOT the K2.x `thinking` parameter). The proxy
|
|
17
|
+
* detects K3 and skips the thinking-disable rewrite while keeping
|
|
18
|
+
* temperature/top_p enforcement. It does NOT inject a `thinking` block —
|
|
19
|
+
* K3 rejects it.
|
|
15
20
|
* - Not intended for `moonshot-v1` models or non-Kimi providers, because this
|
|
16
|
-
* proxy rewrites requests to K2-family-specific values:
|
|
21
|
+
* proxy rewrites requests to K2/K3-family-specific values:
|
|
17
22
|
* - thinking mode temperature = 1.0
|
|
18
|
-
* - non-thinking mode temperature = 0.6
|
|
23
|
+
* - non-thinking mode temperature = 0.6 (K2.5/K2.6 only)
|
|
19
24
|
* - top_p = 0.95
|
|
20
25
|
* - tool-enabled requests force `thinking: { type: 'disabled' }` (K2.5/K2.6 only)
|
|
21
26
|
*/
|
|
@@ -108,12 +113,16 @@ function rewriteKimi(payload) {
|
|
|
108
113
|
const incomingTemperature = payload.temperature
|
|
109
114
|
const incomingTopP = payload.top_p
|
|
110
115
|
const incomingThinkingType = payload?.thinking?.type
|
|
116
|
+
const incomingReasoningEffort = payload?.reasoning_effort
|
|
111
117
|
const model = payload.model ?? ''
|
|
112
118
|
|
|
113
|
-
// K2.7
|
|
114
|
-
//
|
|
115
|
-
//
|
|
119
|
+
// K2.7 and K3 are always-thinking and reject thinking: disabled.
|
|
120
|
+
// K2.7 uses `thinking` parameter; K3 uses `reasoning_effort` instead.
|
|
121
|
+
// Detect K2.7 variants (e.g. kimi-k2.7-code) and K3 variants (e.g. kimi-k3)
|
|
122
|
+
// and skip the thinking-disable rewrite while keeping temperature/top_p enforcement.
|
|
116
123
|
const isK27 = model.startsWith('kimi-k2.7')
|
|
124
|
+
const isK3 = model.startsWith('kimi-k3')
|
|
125
|
+
const isAlwaysThinking = isK27 || isK3
|
|
117
126
|
|
|
118
127
|
// Determine if a tool is actually being invoked:
|
|
119
128
|
// - tool_choice is set and not "none"
|
|
@@ -126,13 +135,15 @@ function rewriteKimi(payload) {
|
|
|
126
135
|
(toolChoice !== undefined && toolChoice !== 'none' && toolChoice !== null)
|
|
127
136
|
const hasTools = hasActiveToolCall
|
|
128
137
|
|
|
129
|
-
const useNonThinkingMode =
|
|
138
|
+
const useNonThinkingMode =
|
|
139
|
+
!isAlwaysThinking && disableThinkingWithTools && hasTools
|
|
130
140
|
const rewrittenTemperature = useNonThinkingMode
|
|
131
141
|
? forcedNonThinkingTemperature
|
|
132
142
|
: forcedTemperature
|
|
133
143
|
|
|
134
144
|
// Capture incoming state before mutation
|
|
135
145
|
payload.__incomingThinkingType = incomingThinkingType
|
|
146
|
+
payload.__incomingReasoningEffort = incomingReasoningEffort
|
|
136
147
|
|
|
137
148
|
// Apply rewrites
|
|
138
149
|
payload.temperature = rewrittenTemperature
|
|
@@ -142,26 +153,35 @@ function rewriteKimi(payload) {
|
|
|
142
153
|
payload.thinking = { type: 'disabled' }
|
|
143
154
|
}
|
|
144
155
|
|
|
156
|
+
// K3 does not accept `thinking` — delete it if present so it doesn't cause a 400
|
|
157
|
+
if (isK3 && payload.thinking) {
|
|
158
|
+
delete payload.thinking
|
|
159
|
+
}
|
|
160
|
+
|
|
145
161
|
const rewrittenThinkingType = payload.thinking?.type
|
|
146
162
|
const rewriteInfo = {
|
|
147
163
|
model,
|
|
148
164
|
isK27,
|
|
165
|
+
isK3,
|
|
149
166
|
incomingTemperature,
|
|
150
167
|
rewrittenTemperature,
|
|
151
168
|
incomingTopP,
|
|
152
169
|
rewrittenTopP: forcedTopP,
|
|
153
170
|
incomingThinkingType,
|
|
154
|
-
rewrittenThinkingType
|
|
171
|
+
rewrittenThinkingType,
|
|
172
|
+
incomingReasoningEffort
|
|
155
173
|
}
|
|
156
174
|
|
|
157
175
|
const summary = summarizePayload(payload, hasTools, rewriteInfo)
|
|
158
176
|
|
|
159
177
|
const modeTag = hasTools ? '[tools]' : '[chat]'
|
|
160
178
|
const k27Tag = isK27 ? '[k2.7]' : ''
|
|
161
|
-
const
|
|
179
|
+
const k3Tag = isK3 ? '[k3]' : ''
|
|
180
|
+
const consoleMsg = `${k27Tag}${k3Tag}${modeTag} temperature ${String(incomingTemperature)} -> ${String(rewrittenTemperature)}, top_p ${String(incomingTopP)} -> ${String(forcedTopP)}, thinking ${String(incomingThinkingType)} -> ${String(rewrittenThinkingType)}, reasoning_effort ${String(incomingReasoningEffort)}`
|
|
162
181
|
|
|
163
|
-
// Clean up internal
|
|
182
|
+
// Clean up internal keys before forwarding
|
|
164
183
|
delete payload.__incomingThinkingType
|
|
184
|
+
delete payload.__incomingReasoningEffort
|
|
165
185
|
|
|
166
186
|
return { summary, consoleMsg }
|
|
167
187
|
}
|