@blockrun/clawrouter 0.12.228 → 0.12.229

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 (7) hide show
  1. package/README.md +49 -48
  2. package/dist/cli.js +30 -8
  3. package/dist/index.js +30 -8
  4. package/package.json +1 -1
  5. package/skills/clawrouter/SKILL.md +2 -2
  6. package/skills/imagegen/SKILL.md +9 -9
  7. package/src/top-models.json +1 -1
package/README.md CHANGED
@@ -207,12 +207,12 @@ Choose your routing strategy with `/model <profile>`:
207
207
  Request → Weighted Scorer (15 dimensions) → Tier → Best Model → Response
208
208
  ```
209
209
 
210
- | Tier | ECO Model | AUTO Model | PREMIUM Model |
211
- | --------- | ------------------------------------- | ------------------------------------- | ---------------------------- |
212
- | SIMPLE | free/mistral-large-3-675b (**FREE**) | gemini-2.5-flash ($0.30/$2.50) | kimi-k2.7 ($0.95/$4.00) |
213
- | MEDIUM | gemini-3.1-flash-lite ($0.25/$1.50) | kimi-k2.7 ($0.95/$4.00) | gpt-5.3-codex ($1.75/$14.00) |
214
- | COMPLEX | gemini-3.1-flash-lite ($0.25/$1.50) | gemini-3.1-pro ($2/$12) | claude-opus-4.8 ($5/$25) |
215
- | REASONING | deepseek-reasoner ($0.20/$0.40) | deepseek-reasoner ($0.20/$0.40) | claude-sonnet-4.6 ($3/$15) |
210
+ | Tier | ECO Model | AUTO Model | PREMIUM Model |
211
+ | --------- | ------------------------------------ | ------------------------------- | ---------------------------- |
212
+ | SIMPLE | free/mistral-large-3-675b (**FREE**) | gemini-2.5-flash ($0.30/$2.50) | kimi-k2.7 ($0.95/$4.00) |
213
+ | MEDIUM | gemini-3.1-flash-lite ($0.25/$1.50) | kimi-k2.7 ($0.95/$4.00) | gpt-5.3-codex ($1.75/$14.00) |
214
+ | COMPLEX | gemini-3.1-flash-lite ($0.25/$1.50) | gemini-3.1-pro ($2/$12) | claude-opus-4.8 ($5/$25) |
215
+ | REASONING | deepseek-reasoner ($0.20/$0.40) | deepseek-reasoner ($0.20/$0.40) | claude-sonnet-4.6 ($3/$15) |
216
216
 
217
217
  **Blended average: $2.05/M** vs $25/M for Claude Opus = **92% savings**
218
218
 
@@ -230,16 +230,16 @@ Generate images directly from chat with `/cr-imagegen`:
230
230
 
231
231
  > The slash command is `/cr-imagegen` to avoid colliding with Telegram channel commands. Typing `/imagegen` in chat still works for backward compatibility.
232
232
 
233
- | Model | Provider | Price | Max Size |
234
- | ---------------------------- | --------------------- | ------------ | --------- |
235
- | `nano-banana` | Google Gemini Flash | $0.05/image | 1024x1024 |
236
- | `banana-pro` | Google Gemini Pro | $0.10/image | 4096x4096 |
237
- | `gpt-image` | OpenAI GPT Image 1 | $0.02/image | 1536x1024 |
238
- | `gpt-image-2` | OpenAI GPT Image 2 | $0.06/image | 1536x1024 |
239
- | `seedream` | ByteDance Seedream 5 | $0.045/image | 2848x1600 |
240
- | `xai/grok-imagine-image` | xAI Grok Imagine | $0.02/image | 1024x1024 |
241
- | `xai/grok-imagine-image-pro` | xAI Grok Imagine Pro | $0.07/image | 1024x1024 |
242
- | `zai/cogview-4` | Zhipu CogView-4 | $0.015/image | 1440x1440 |
233
+ | Model | Provider | Price | Max Size |
234
+ | ---------------------------- | -------------------- | ------------ | --------- |
235
+ | `nano-banana` | Google Gemini Flash | $0.05/image | 1024x1024 |
236
+ | `banana-pro` | Google Gemini Pro | $0.10/image | 4096x4096 |
237
+ | `gpt-image` | OpenAI GPT Image 1 | $0.02/image | 1536x1024 |
238
+ | `gpt-image-2` | OpenAI GPT Image 2 | $0.06/image | 1536x1024 |
239
+ | `seedream` | ByteDance Seedream 5 | $0.045/image | 2848x1600 |
240
+ | `xai/grok-imagine-image` | xAI Grok Imagine | $0.02/image | 1024x1024 |
241
+ | `xai/grok-imagine-image-pro` | xAI Grok Imagine Pro | $0.07/image | 1024x1024 |
242
+ | `zai/cogview-4` | Zhipu CogView-4 | $0.015/image | 1440x1440 |
243
243
 
244
244
  ## Video Generation
245
245
 
@@ -388,38 +388,39 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
388
388
 
389
389
  ### Budget Models (under $0.001/request)
390
390
 
391
- | Model | Input $/M | Output $/M | ~$/request | Context | Features |
392
- | --------------------------------------------- | --------: | ---------: | ---------: | ------- | -------------------------------------------- |
393
- | free/mistral-large-3-675b | **FREE** | **FREE** | **$0** | 131K | 675B general flagship, default free model |
394
- | free/deepseek-v4-flash | **FREE** | **FREE** | **$0** | 1M | reasoning + coding, huge context |
395
- | free/seed-oss-36b | **FREE** | **FREE** | **$0** | 131K | coding |
396
- | free/nemotron-3-nano-omni-30b-a3b-reasoning | **FREE** | **FREE** | **$0** | 256K | reasoning, **vision** (text+img+video+audio) |
397
- | free/mistral-nemotron | **FREE** | **FREE** | **$0** | 131K | instruction following |
398
- | free/step-3.7-flash | **FREE** | **FREE** | **$0** | 131K | reasoning |
399
- | free/nemotron-nano-9b-v2 | **FREE** | **FREE** | **$0** | 131K | fast lightweight generalist |
400
- | free/nemotron-nano-12b-v2-vl | **FREE** | **FREE** | **$0** | 131K | vision (text + image) |
401
- | openai/gpt-5-nano | $0.05 | $0.40 | $0.0002 | 128K | tools |
402
- | openai/gpt-4.1-nano | $0.10 | $0.40 | $0.0003 | 128K | tools |
403
- | google/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.0003 | 1M | tools |
404
- | openai/gpt-4o-mini | $0.15 | $0.60 | $0.0004 | 128K | tools |
405
- | xai/grok-4-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
406
- | xai/grok-4-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools |
407
- | xai/grok-4-1-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
408
- | openai/gpt-5-mini | $0.25 | $2.00 | $0.0011 | 200K | tools |
409
- | deepseek/deepseek-chat | $0.20 | $0.40 | $0.0003 | 1M | tools (V4 Flash chat) |
410
- | deepseek/deepseek-reasoner | $0.20 | $0.40 | $0.0003 | 1M | reasoning, tools (V4 Flash thinking) |
411
- | deepseek/deepseek-v4-pro | $0.435 | $0.87 | $0.0007 | 1M | reasoning, agentic, tools (V4 flagship) |
412
- | zai/glm-5 | $0.60 | $1.92 | $0.0013 | 200K | tools |
413
- | zai/glm-5-turbo | $1.20 | $4.00 | $0.0026 | 200K | tools |
414
- | minimax/minimax-m3 | $0.30 | $1.20 | $0.0008 | 1M | reasoning, agentic, tools |
415
- | minimax/minimax-m2.7 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
416
- | minimax/minimax-m2.5 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
417
- | google/gemini-2.5-flash | $0.30 | $2.50 | $0.0014 | 1M | vision, tools |
418
- | openai/gpt-4.1-mini | $0.40 | $1.60 | $0.0010 | 128K | tools |
419
- | google/gemini-3.5-flash | $0.50 | $3.00 | $0.0018 | 1M | reasoning, vision, tools (thinking built-in) |
420
- | google/gemini-3-flash-preview | $0.50 | $3.00 | $0.0018 | 1M | vision |
421
- | moonshot/kimi-k2.5 | $0.60 | $3.00 | $0.0018 | 262K | reasoning, vision, agentic, tools |
422
- | moonshot/kimi-k2.7 | $0.95 | $4.00 | $0.0025 | 262K | reasoning, vision, agentic, tools |
391
+ | Model | Input $/M | Output $/M | ~$/request | Context | Features |
392
+ | ------------------------------------------- | --------: | ---------: | ---------: | ------- | -------------------------------------------- |
393
+ | free/mistral-large-3-675b | **FREE** | **FREE** | **$0** | 131K | 675B general flagship, default free model |
394
+ | free/deepseek-v4-flash | **FREE** | **FREE** | **$0** | 1M | reasoning + coding, huge context |
395
+ | free/seed-oss-36b | **FREE** | **FREE** | **$0** | 131K | coding |
396
+ | free/nemotron-3-nano-omni-30b-a3b-reasoning | **FREE** | **FREE** | **$0** | 256K | reasoning, **vision** (text+img+video+audio) |
397
+ | free/mistral-nemotron | **FREE** | **FREE** | **$0** | 131K | instruction following |
398
+ | free/step-3.7-flash | **FREE** | **FREE** | **$0** | 131K | reasoning |
399
+ | free/nemotron-nano-9b-v2 | **FREE** | **FREE** | **$0** | 131K | fast lightweight generalist |
400
+ | free/nemotron-nano-12b-v2-vl | **FREE** | **FREE** | **$0** | 131K | vision (text + image) |
401
+ | openai/gpt-5-nano | $0.05 | $0.40 | $0.0002 | 128K | tools |
402
+ | openai/gpt-4.1-nano | $0.10 | $0.40 | $0.0003 | 128K | tools |
403
+ | google/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.0003 | 1M | tools |
404
+ | openai/gpt-4o-mini | $0.15 | $0.60 | $0.0004 | 128K | tools |
405
+ | xai/grok-4-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
406
+ | xai/grok-4-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools |
407
+ | xai/grok-4-1-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
408
+ | openai/gpt-5-mini | $0.25 | $2.00 | $0.0011 | 200K | tools |
409
+ | deepseek/deepseek-chat | $0.20 | $0.40 | $0.0003 | 1M | tools (V4 Flash chat) |
410
+ | deepseek/deepseek-reasoner | $0.20 | $0.40 | $0.0003 | 1M | reasoning, tools (V4 Flash thinking) |
411
+ | deepseek/deepseek-v4-pro | $0.435 | $0.87 | $0.0007 | 1M | reasoning, agentic, tools (V4 flagship) |
412
+ | zai/glm-5 | $0.60 | $1.92 | $0.0013 | 200K | tools |
413
+ | zai/glm-5-turbo | $1.20 | $4.00 | $0.0026 | 200K | tools |
414
+ | minimax/minimax-m3 | $0.30 | $1.20 | $0.0008 | 1M | reasoning, agentic, tools |
415
+ | minimax/minimax-m2.7 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
416
+ | minimax/minimax-m2.5 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
417
+ | google/gemini-2.5-flash | $0.30 | $2.50 | $0.0014 | 1M | vision, tools |
418
+ | openai/gpt-4.1-mini | $0.40 | $1.60 | $0.0010 | 128K | tools |
419
+ | google/gemini-3.5-flash | $0.50 | $3.00 | $0.0018 | 1M | reasoning, vision, tools (thinking built-in) |
420
+ | google/gemini-3-flash-preview | $0.50 | $3.00 | $0.0018 | 1M | vision |
421
+ | moonshot/kimi-k2.5 | $0.60 | $3.00 | $0.0018 | 262K | reasoning, vision, agentic, tools |
422
+ | moonshot/kimi-k2.7 | $0.95 | $4.00 | $0.0025 | 262K | reasoning, vision, agentic, tools |
423
+ | moonshot/kimi-k3 | $3.00 | $15.00 | $0.0110 | 1M | reasoning, vision, agentic, tools |
423
424
 
424
425
  ### Mid-Range Models ($0.001–$0.01/request)
425
426
 
package/dist/cli.js CHANGED
@@ -34295,7 +34295,7 @@ var init_top_models = __esm({
34295
34295
  "zai/glm-5",
34296
34296
  "minimax/minimax-m3",
34297
34297
  "minimax/minimax-m2.7",
34298
- "moonshot/kimi-k2.7",
34298
+ "moonshot/kimi-k3",
34299
34299
  "deepseek/deepseek-v4-pro",
34300
34300
  "deepseek/deepseek-chat",
34301
34301
  "deepseek/deepseek-reasoner",
@@ -34507,13 +34507,16 @@ var init_models = __esm({
34507
34507
  deepseek: "deepseek/deepseek-chat",
34508
34508
  "deepseek-chat": "deepseek/deepseek-chat",
34509
34509
  reasoner: "deepseek/deepseek-reasoner",
34510
- // Kimi / Moonshot — K2.7 is the featured flagship on BlockRun (added 2026-06-13,
34511
- // commit cd3d79b; K2.6 marked hidden/superseded, K2.5 hidden). Bare aliases now
34512
- // resolve to K2.7 (same $0.95/$4.00 price as K2.6 — AT-COST, zero margin). Explicit
34510
+ // Kimi / Moonshot — K3 is the featured flagship on BlockRun (added 2026-07-17; K2.7
34511
+ // hidden/superseded, K2.6 hidden, K2.5 hidden). K3 is ~5x K2.7's price ($3/$15 vs
34512
+ // $0.95/$4.00), so the BARE aliases deliberately STAY on K2.7 — repointing them to K3
34513
+ // would silently ~5x every generic-`kimi` quote and break per-call-cap wallets (mirrors
34514
+ // blockrun's own alias decision). Address the flagship explicitly via "kimi-k3". Explicit
34513
34515
  // pins for "kimi-k2.6" / "kimi-k2.5" still resolve to those exact models (K2.5 is a
34514
34516
  // cost-stability opt-in at $0.60/$3.00). NVIDIA-hosted K2.5 was retired 2026-04-21.
34515
34517
  kimi: "moonshot/kimi-k2.7",
34516
34518
  moonshot: "moonshot/kimi-k2.7",
34519
+ "kimi-k3": "moonshot/kimi-k3",
34517
34520
  "kimi-k2": "moonshot/kimi-k2.7",
34518
34521
  "kimi-k2.7": "moonshot/kimi-k2.7",
34519
34522
  "kimi-k2.6": "moonshot/kimi-k2.6",
@@ -35292,10 +35295,29 @@ var init_models = __esm({
35292
35295
  agentic: true,
35293
35296
  toolCalling: true
35294
35297
  },
35295
- // Kimi K2.7 — Moonshot's flagship (added 2026-06-13). 256K context, multi-modal
35296
- // (image + VIDEO input), returns reasoning_content. Served via BlockRun's OpenRouter
35297
- // credit pool (slug moonshotai/kimi-k2.7-code) failing over to direct Moonshot.
35298
- // AT-COST pricing ($0.95/$4.00 = OpenRouter COGS, zero margin) — same as K2.6.
35298
+ // Kimi K3 — Moonshot's flagship (blockrun added 2026-07-17, live-probed same day).
35299
+ // 2.8T-param open MoE, 1M context, image + text input, returns reasoning_content.
35300
+ // Priced at COGS + BlockRun's 5% margin: users pay ~$3.15/$15.75 per 1M; the fields
35301
+ // here store the raw $3.00/$15.00 COST (server applies margin at billing). ~5x K2.7,
35302
+ // so the generic `kimi` alias deliberately stays on K2.7 — address k3 explicitly.
35303
+ {
35304
+ id: "moonshot/kimi-k3",
35305
+ name: "Kimi K3",
35306
+ version: "k3",
35307
+ inputPrice: 3,
35308
+ outputPrice: 15,
35309
+ contextWindow: 1048576,
35310
+ maxOutput: 65536,
35311
+ reasoning: true,
35312
+ vision: true,
35313
+ agentic: true,
35314
+ toolCalling: true
35315
+ },
35316
+ // Kimi K2.7 — previous-gen flagship (added 2026-06-13); superseded by K3 + hidden on
35317
+ // BlockRun 2026-07-17 but kept routable. 256K context, multi-modal (image + VIDEO
35318
+ // input), returns reasoning_content. Served via BlockRun's OpenRouter credit pool
35319
+ // (slug moonshotai/kimi-k2.7-code) failing over to direct Moonshot. AT-COST pricing
35320
+ // ($0.95/$4.00 = OpenRouter COGS, zero margin) — same as K2.6.
35299
35321
  {
35300
35322
  id: "moonshot/kimi-k2.7",
35301
35323
  name: "Kimi K2.7",
package/dist/index.js CHANGED
@@ -85,7 +85,7 @@ var init_top_models = __esm({
85
85
  "zai/glm-5",
86
86
  "minimax/minimax-m3",
87
87
  "minimax/minimax-m2.7",
88
- "moonshot/kimi-k2.7",
88
+ "moonshot/kimi-k3",
89
89
  "deepseek/deepseek-v4-pro",
90
90
  "deepseek/deepseek-chat",
91
91
  "deepseek/deepseek-reasoner",
@@ -297,13 +297,16 @@ var init_models = __esm({
297
297
  deepseek: "deepseek/deepseek-chat",
298
298
  "deepseek-chat": "deepseek/deepseek-chat",
299
299
  reasoner: "deepseek/deepseek-reasoner",
300
- // Kimi / Moonshot — K2.7 is the featured flagship on BlockRun (added 2026-06-13,
301
- // commit cd3d79b; K2.6 marked hidden/superseded, K2.5 hidden). Bare aliases now
302
- // resolve to K2.7 (same $0.95/$4.00 price as K2.6 — AT-COST, zero margin). Explicit
300
+ // Kimi / Moonshot — K3 is the featured flagship on BlockRun (added 2026-07-17; K2.7
301
+ // hidden/superseded, K2.6 hidden, K2.5 hidden). K3 is ~5x K2.7's price ($3/$15 vs
302
+ // $0.95/$4.00), so the BARE aliases deliberately STAY on K2.7 — repointing them to K3
303
+ // would silently ~5x every generic-`kimi` quote and break per-call-cap wallets (mirrors
304
+ // blockrun's own alias decision). Address the flagship explicitly via "kimi-k3". Explicit
303
305
  // pins for "kimi-k2.6" / "kimi-k2.5" still resolve to those exact models (K2.5 is a
304
306
  // cost-stability opt-in at $0.60/$3.00). NVIDIA-hosted K2.5 was retired 2026-04-21.
305
307
  kimi: "moonshot/kimi-k2.7",
306
308
  moonshot: "moonshot/kimi-k2.7",
309
+ "kimi-k3": "moonshot/kimi-k3",
307
310
  "kimi-k2": "moonshot/kimi-k2.7",
308
311
  "kimi-k2.7": "moonshot/kimi-k2.7",
309
312
  "kimi-k2.6": "moonshot/kimi-k2.6",
@@ -1082,10 +1085,29 @@ var init_models = __esm({
1082
1085
  agentic: true,
1083
1086
  toolCalling: true
1084
1087
  },
1085
- // Kimi K2.7 — Moonshot's flagship (added 2026-06-13). 256K context, multi-modal
1086
- // (image + VIDEO input), returns reasoning_content. Served via BlockRun's OpenRouter
1087
- // credit pool (slug moonshotai/kimi-k2.7-code) failing over to direct Moonshot.
1088
- // AT-COST pricing ($0.95/$4.00 = OpenRouter COGS, zero margin) — same as K2.6.
1088
+ // Kimi K3 — Moonshot's flagship (blockrun added 2026-07-17, live-probed same day).
1089
+ // 2.8T-param open MoE, 1M context, image + text input, returns reasoning_content.
1090
+ // Priced at COGS + BlockRun's 5% margin: users pay ~$3.15/$15.75 per 1M; the fields
1091
+ // here store the raw $3.00/$15.00 COST (server applies margin at billing). ~5x K2.7,
1092
+ // so the generic `kimi` alias deliberately stays on K2.7 — address k3 explicitly.
1093
+ {
1094
+ id: "moonshot/kimi-k3",
1095
+ name: "Kimi K3",
1096
+ version: "k3",
1097
+ inputPrice: 3,
1098
+ outputPrice: 15,
1099
+ contextWindow: 1048576,
1100
+ maxOutput: 65536,
1101
+ reasoning: true,
1102
+ vision: true,
1103
+ agentic: true,
1104
+ toolCalling: true
1105
+ },
1106
+ // Kimi K2.7 — previous-gen flagship (added 2026-06-13); superseded by K3 + hidden on
1107
+ // BlockRun 2026-07-17 but kept routable. 256K context, multi-modal (image + VIDEO
1108
+ // input), returns reasoning_content. Served via BlockRun's OpenRouter credit pool
1109
+ // (slug moonshotai/kimi-k2.7-code) failing over to direct Moonshot. AT-COST pricing
1110
+ // ($0.95/$4.00 = OpenRouter COGS, zero margin) — same as K2.6.
1089
1111
  {
1090
1112
  id: "moonshot/kimi-k2.7",
1091
1113
  name: "Kimi K2.7",
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@blockrun/clawrouter",
3
- "version": "0.12.228",
3
+ "version": "0.12.229",
4
4
  "description": "Smart LLM router — save 85% on inference costs. 55+ models (8 free), one wallet, x402 micropayments.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
package/skills/clawrouter/SKILL.md CHANGED
@@ -135,7 +135,7 @@ Rules handle ~~80% of requests in <1ms. Only ambiguous queries hit the LLM class
135
135
 
136
136
  ## Available Models
137
137
 
138
- 55+ models including: gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.5, gpt-5.4, gpt-4o, o3, claude-fable-5, claude-opus-4.8, claude-opus-4.7, claude-opus-4.5, claude-sonnet-5, claude-sonnet-4.6, gemini-3.1-pro, gemini-2.5-flash, deepseek-v4-pro, deepseek-chat, grok-4.5, grok-4.3, grok-build-0.1, kimi-k2.7, and 8 free NVIDIA models (mistral-large-3-675b [default, 675B flagship], deepseek-v4-flash [1M context], seed-oss-36b [coding], nemotron-3-nano-omni-30b-a3b-reasoning [vision], mistral-nemotron, step-3.7-flash, nemotron-nano-9b-v2, nemotron-nano-12b-v2-vl [vision]).
138
+ 55+ models including: gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.5, gpt-5.4, gpt-4o, o3, claude-fable-5, claude-opus-4.8, claude-opus-4.7, claude-opus-4.5, claude-sonnet-5, claude-sonnet-4.6, gemini-3.1-pro, gemini-2.5-flash, deepseek-v4-pro, deepseek-chat, grok-4.5, grok-4.3, grok-build-0.1, kimi-k3 [1M ctx flagship], kimi-k2.7, and 8 free NVIDIA models (mistral-large-3-675b [default, 675B flagship], deepseek-v4-flash [1M context], seed-oss-36b [coding], nemotron-3-nano-omni-30b-a3b-reasoning [vision], mistral-nemotron, step-3.7-flash, nemotron-nano-9b-v2, nemotron-nano-12b-v2-vl [vision]).
139
139
 
140
140
  ## Built-in Agent Tools
141
141
 
@@ -158,7 +158,7 @@ Realtime prices and historical OHLC across every asset class. The agent should c
158
158
 
159
159
  | Tool | Purpose | Price |
160
160
  | --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------- |
161
- | `blockrun_image_generation` | 8 image models — GPT Image 1/2, Nano Banana / Pro, Seedream 5 Pro, Grok Imagine / Pro, CogView-4 | $0.015–$0.15 / image |
161
+ | `blockrun_image_generation` | 8 image models — GPT Image 1/2, Nano Banana / Pro, Seedream 5 Pro, Grok Imagine / Pro, CogView-4 | $0.015–$0.15 / image |
162
162
  | `blockrun_image_edit` | Edit / inpaint existing image (openai/gpt-image-1) | $0.02–$0.04 / image |
163
163
  | `blockrun_video_generation` | Grok Imagine + ByteDance Seedance (1.5-pro / 2.0-fast / 2.0) at 720p with synced audio (t2v default), 5–10s, + OpenAI Sora 2 via Azure (`azure/sora-2`, 4/8/12s, t2v + i2v, rejects human faces in reference images). Seedance is token-priced upstream (~20,256 tokens/sec at the 720p+audio default — 2× the prior 480p rate); `image_url` (image-to-video) costs the same as t2v since 2026-06-01. Seedance 2.0 variants accept optional `real_face_asset_id` (`ta_…`) for BytePlus RealFace character-consistency — mutually exclusive with `image_url`. | $0.05/s (Grok); $0.10/s (Sora 2); Seedance ~$0.46–$1.49 per 5s clip |
164
164
 
package/skills/imagegen/SKILL.md CHANGED
@@ -55,16 +55,16 @@ Display inline: `![generated image](http://localhost:8402/images/abc123.png)`
55
55
 
56
56
  ### Model Selection
57
57
 
58
- | Alias | Full ID | Price | Sizes | Best for |
59
- | ------------------ | ---------------------------- | ------------ | ------------------------------- | ---------------------------------------------------------------- |
60
- | `nano-banana` | `google/nano-banana` | $0.05 | 1024×1024, 1216×832, 1024×1792 | Default — fast, cheap, good quality |
61
- | `banana-pro` | `google/nano-banana-pro` | $0.10–$0.15 | up to 4096×4096 | High-res, large format |
62
- | `gpt-image` | `openai/gpt-image-1` | $0.02–$0.04 | 1024×1024, 1536×1024, 1024×1536 | Budget option; supports editing |
58
+ | Alias | Full ID | Price | Sizes | Best for |
59
+ | ------------------ | ---------------------------- | ------------ | ------------------------------- | ------------------------------------------------------------------------------------------------------------------ |
60
+ | `nano-banana` | `google/nano-banana` | $0.05 | 1024×1024, 1216×832, 1024×1792 | Default — fast, cheap, good quality |
61
+ | `banana-pro` | `google/nano-banana-pro` | $0.10–$0.15 | up to 4096×4096 | High-res, large format |
62
+ | `gpt-image` | `openai/gpt-image-1` | $0.02–$0.04 | 1024×1024, 1536×1024, 1024×1536 | Budget option; supports editing |
63
63
  | `gpt-image-2` | `openai/gpt-image-2` | $0.06–$0.12 | 1024×1024, 1536×1024, 1024×1536 | Photorealistic, reasoning-driven, text rendering (slow — proxy polls up to 5min); legacy `dalle` alias routes here |
64
- | `seedream` | `bytedance/seedream-5-pro` | $0.045–$0.09 | up to 2848×1600 / 2304×1728 | Flagship quality, reference-image support |
65
- | `grok-imagine` | `xai/grok-imagine-image` | $0.02 | 1024×1024 | xAI Grok image style |
66
- | `grok-imagine-pro` | `xai/grok-imagine-image-pro` | $0.07 | 1024×1024 | Grok high-quality |
67
- | `cogview` | `zai/cogview-4` | $0.015–$0.02 | 512×512 to 1440×1440 | Cheapest — Zhipu CogView |
64
+ | `seedream` | `bytedance/seedream-5-pro` | $0.045–$0.09 | up to 2848×1600 / 2304×1728 | Flagship quality, reference-image support |
65
+ | `grok-imagine` | `xai/grok-imagine-image` | $0.02 | 1024×1024 | xAI Grok image style |
66
+ | `grok-imagine-pro` | `xai/grok-imagine-image-pro` | $0.07 | 1024×1024 | Grok high-quality |
67
+ | `cogview` | `zai/cogview-4` | $0.015–$0.02 | 512×512 to 1440×1440 | Cheapest — Zhipu CogView |
68
68
 
69
69
  **Choosing a model:**
70
70
 
package/src/top-models.json CHANGED
@@ -31,7 +31,7 @@
31
31
  "zai/glm-5",
32
32
  "minimax/minimax-m3",
33
33
  "minimax/minimax-m2.7",
34
- "moonshot/kimi-k2.7",
34
+ "moonshot/kimi-k3",
35
35
  "deepseek/deepseek-v4-pro",
36
36
  "deepseek/deepseek-chat",
37
37
  "deepseek/deepseek-reasoner",