@blockrun/clawrouter 0.12.280 → 0.12.281
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 +82 -71
- package/dist/cli.js +1727 -1405
- package/dist/index.js +1711 -1389
- package/docs/features.md +3 -3
- package/docs/image-generation.md +43 -37
- package/docs/routing-profiles.md +3 -3
- package/package.json +1 -1
- package/skills/clawrouter/SKILL.md +3 -3
- package/skills/imagegen/SKILL.md +20 -16
- package/src/top-models.json +9 -1
package/docs/features.md
CHANGED
|
@@ -178,17 +178,17 @@ Use short aliases instead of full model paths:
|
|
|
178
178
|
```bash
|
|
179
179
|
/model free # free/nemotron-3.5-lightning (FREE!)
|
|
180
180
|
/model br-sonnet # anthropic/claude-sonnet-4.6
|
|
181
|
-
/model opus # anthropic/claude-opus-5
|
|
181
|
+
/model opus # anthropic/claude-opus-5; /model opus-5.5 for Opus 5.5 ($4/$20)
|
|
182
182
|
/model haiku # anthropic/claude-haiku-4.5
|
|
183
183
|
/model gpt # openai/gpt-4o
|
|
184
|
-
/model gpt5 # openai/gpt-5.6-terra
|
|
184
|
+
/model gpt5 # openai/gpt-5.6-terra; /model gpt-6-astra, gpt-6-sol, gpt-6-luna for GPT-6
|
|
185
185
|
/model deepseek # deepseek/deepseek-chat
|
|
186
186
|
/model reasoner # deepseek/deepseek-reasoner
|
|
187
187
|
/model kimi # moonshot/kimi-k2.7; /model kimi-k3 for the 1M-ctx flagship
|
|
188
188
|
/model glm # zai/glm-5.3
|
|
189
189
|
/model gemini # google/gemini-2.5-pro
|
|
190
190
|
/model flash # google/gemini-2.5-flash
|
|
191
|
-
/model grok # xai/grok-4.5
|
|
191
|
+
/model grok # xai/grok-4.5; /model grok-4.7 or grok-4.6 for the newer pins
|
|
192
192
|
/model grok-fast # xai/grok-4-fast-reasoning
|
|
193
193
|
```
|
|
194
194
|
|
package/docs/image-generation.md
CHANGED
|
@@ -51,17 +51,20 @@ The returned URL is a publicly hosted image, ready to use in Telegram, Discord,
|
|
|
51
51
|
|
|
52
52
|
## Models & Pricing
|
|
53
53
|
|
|
54
|
-
| Model ID
|
|
55
|
-
|
|
|
56
|
-
| `google/nano-banana`
|
|
57
|
-
| `google/nano-banana-2`
|
|
58
|
-
| `google/nano-banana-pro`
|
|
59
|
-
| `openai/gpt-image-1`
|
|
60
|
-
| `openai/gpt-image-2`
|
|
61
|
-
| `
|
|
62
|
-
| `
|
|
63
|
-
| `
|
|
64
|
-
| `
|
|
54
|
+
| Model ID | Shorthand | Price | Sizes | Provider |
|
|
55
|
+
| ------------------------------- | ------------------ | ------------------ | ------------------------------------------------------------------------------------- | ----------------------------- |
|
|
56
|
+
| `google/nano-banana` | `nano-banana` | $0.05/image | 1024×1024 | Google Gemini Flash |
|
|
57
|
+
| `google/nano-banana-2` | `banana-2` | $0.09/image | 1024×1024 | Google Nano Banana 2 |
|
|
58
|
+
| `google/nano-banana-pro` | `banana-pro` | $0.10–$0.15/image | 1024×1024, 2048×2048, 4096×4096 | Google Gemini Pro |
|
|
59
|
+
| `openai/gpt-image-1` | `gpt-image` | $0.02–$0.04/image | 1024×1024, 1536×1024, 1024×1536 | OpenAI GPT Image 1 |
|
|
60
|
+
| `openai/gpt-image-2` | `gpt-image-2` | $0.06–$0.12/image | 1024×1024, 1536×1024, 1024×1536 | OpenAI GPT Image 2 |
|
|
61
|
+
| `openai/gpt-image-2.5-flare` | `flare` | $0.28–$0.56/image | 1024×1024, 1536×1024, 1024×1536 | OpenAI GPT Image 2.5 Flare |
|
|
62
|
+
| `openai/gpt-image-2.5-sunburst` | `sunburst` | $0.28–$0.56/image | 1024×1024, 1536×1024, 1024×1536 | OpenAI GPT Image 2.5 Sunburst |
|
|
63
|
+
| `bytedance/seedream-5-pro` | `seedream` | $0.045–$0.09/image | 1024×1024, 1280×720, 2048×1024, 2048×2048, 2304×1728, 1728×2304, 2848×1600, 1600×2848 | ByteDance Seedream 5 |
|
|
64
|
+
| `xai/grok-imagine-image` | `grok-imagine` | $0.02/image | 1024×1024 | xAI Grok Imagine |
|
|
65
|
+
| `xai/grok-imagine-image-2.0` | `grok-imagine-2` | $0.04/image | 1024×1024 | xAI Grok Imagine 2.0 |
|
|
66
|
+
| `xai/grok-imagine-image-pro` | `grok-imagine-pro` | $0.07/image | 1024×1024 | xAI Grok Imagine Pro |
|
|
67
|
+
| `zai/cogview-4` | `cogview` | $0.015–$0.02/image | 512×512, 768×768, 1024×1024, 768×1344, 1344×768, 1440×1440 | Zhipu CogView-4 |
|
|
65
68
|
|
|
66
69
|
Default model: `google/nano-banana`.
|
|
67
70
|
|
|
@@ -102,13 +105,13 @@ Edit an existing image using AI. Route via ClawRouter proxy (`http://localhost:8
|
|
|
102
105
|
|
|
103
106
|
**Request body:**
|
|
104
107
|
|
|
105
|
-
| Field | Type | Required | Description
|
|
106
|
-
| -------- | -------- | -------- |
|
|
107
|
-
| `model` | `string` | No | Model ID (default: `openai/gpt-image-1`)
|
|
108
|
-
| `prompt` | `string` | Yes | Text description of the edit to apply
|
|
109
|
-
| `image` | `string` | Yes | Source image — see **Image input formats** below
|
|
110
|
-
| `mask` | `string` | No | Mask image (white = area to edit) — same formats as `image`
|
|
111
|
-
| `size` | `string` | No | Output dimensions, e.g. `"1024x1024"` (default)
|
|
108
|
+
| Field | Type | Required | Description |
|
|
109
|
+
| -------- | -------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
110
|
+
| `model` | `string` | No | Model ID (default: `openai/gpt-image-1`). Also `openai/gpt-image-2`, `openai/gpt-image-2.5-sunburst`, `google/nano-banana`, `google/nano-banana-2`, `google/nano-banana-pro` |
|
|
111
|
+
| `prompt` | `string` | Yes | Text description of the edit to apply |
|
|
112
|
+
| `image` | `string` | Yes | Source image — see **Image input formats** below |
|
|
113
|
+
| `mask` | `string` | No | Mask image (white = area to edit) — same formats as `image` |
|
|
114
|
+
| `size` | `string` | No | Output dimensions, e.g. `"1024x1024"` (default) |
|
|
112
115
|
|
|
113
116
|
**Image input formats** — the `image` and `mask` fields accept any of:
|
|
114
117
|
|
|
@@ -360,27 +363,30 @@ When using ClawRouter with OpenClaw, generate and edit images directly from any
|
|
|
360
363
|
/img2img --image /tmp/portrait.png --size 1536x1024 add a hat
|
|
361
364
|
```
|
|
362
365
|
|
|
363
|
-
| Flag | Default | Description
|
|
364
|
-
| --------- | ------------- |
|
|
365
|
-
| `--image` | _(required)_ | Local image file path (supports `~/`)
|
|
366
|
-
| `--mask` | _(none)_ | Mask image (white = area to edit)
|
|
367
|
-
| `--model` | `gpt-image-1` |
|
|
368
|
-
| `--size` | `1024x1024` | Output size
|
|
366
|
+
| Flag | Default | Description |
|
|
367
|
+
| --------- | ------------- | --------------------------------------------------------------------------------- |
|
|
368
|
+
| `--image` | _(required)_ | Local image file path (supports `~/`) |
|
|
369
|
+
| `--mask` | _(none)_ | Mask image (white = area to edit) |
|
|
370
|
+
| `--model` | `gpt-image-1` | `gpt-image-1`, `gpt-image-2`, `sunburst`, `nano-banana`, `banana-2`, `banana-pro` |
|
|
371
|
+
| `--size` | `1024x1024` | Output size |
|
|
369
372
|
|
|
370
373
|
### Model shorthands
|
|
371
374
|
|
|
372
|
-
| Shorthand | Full ID
|
|
373
|
-
| -------------------------------------- |
|
|
374
|
-
| `nano-banana`, `banana` | `google/nano-banana`
|
|
375
|
-
| `banana-2`, `nano-banana-2` | `google/nano-banana-2`
|
|
376
|
-
| `banana-pro`, `nano-banana-pro` | `google/nano-banana-pro`
|
|
377
|
-
| `gpt-image`, `gpt-image-1` | `openai/gpt-image-1`
|
|
378
|
-
| `gpt-image-2` | `openai/gpt-image-2`
|
|
379
|
-
| `
|
|
380
|
-
| `
|
|
381
|
-
| `
|
|
382
|
-
| `
|
|
383
|
-
| `
|
|
375
|
+
| Shorthand | Full ID |
|
|
376
|
+
| -------------------------------------- | ------------------------------- |
|
|
377
|
+
| `nano-banana`, `banana` | `google/nano-banana` |
|
|
378
|
+
| `banana-2`, `nano-banana-2` | `google/nano-banana-2` |
|
|
379
|
+
| `banana-pro`, `nano-banana-pro` | `google/nano-banana-pro` |
|
|
380
|
+
| `gpt-image`, `gpt-image-1` | `openai/gpt-image-1` |
|
|
381
|
+
| `gpt-image-2` | `openai/gpt-image-2` |
|
|
382
|
+
| `flare`, `gpt-image-2.5-flare` | `openai/gpt-image-2.5-flare` |
|
|
383
|
+
| `sunburst`, `gpt-image-2.5-sunburst` | `openai/gpt-image-2.5-sunburst` |
|
|
384
|
+
| `seedream` | `bytedance/seedream-5-pro` |
|
|
385
|
+
| `grok-imagine` | `xai/grok-imagine-image` |
|
|
386
|
+
| `grok-imagine-2`, `grok-imagine-2.0` | `xai/grok-imagine-image-2.0` |
|
|
387
|
+
| `grok-imagine-pro` | `xai/grok-imagine-image-pro` |
|
|
388
|
+
| `cogview` | `zai/cogview-4` |
|
|
389
|
+
| `dall-e-3`, `dalle3`, `dalle` (legacy) | `openai/gpt-image-2` |
|
|
384
390
|
|
|
385
391
|
---
|
|
386
392
|
|
|
@@ -390,4 +396,4 @@ When using ClawRouter with OpenClaw, generate and edit images directly from any
|
|
|
390
396
|
- **Payment** — Each image costs the listed price in USDC, deducted from your wallet via x402. Make sure your wallet is funded before generating or editing.
|
|
391
397
|
- **Content policy** — OpenAI image models (GPT Image 1/2) apply OpenAI's content policy. Use `nano-banana` or `grok-imagine` for more flexibility with generation.
|
|
392
398
|
- **Size limits** — The gateway validates `size` per model before payment; a size outside the model's list returns an error and costs nothing. Check the table above before setting `--size`.
|
|
393
|
-
- **Image editing** — The `/v1/images/image2image` endpoint
|
|
399
|
+
- **Image editing** — The `/v1/images/image2image` endpoint supports `openai/gpt-image-1` (default), `openai/gpt-image-2`, `openai/gpt-image-2.5-sunburst` and the three `google/nano-banana*` models. `mask` is OpenAI-only (Nano Banana edits by prompt); `openai/gpt-image-2.5-flare` is generation-only. The `image` and `mask` fields accept local file paths (`~/photo.png`, `/abs/path.png`), HTTP/HTTPS URLs, or base64 data URIs. ClawRouter handles file reading and URL downloading automatically. Supported formats: PNG, JPG/JPEG, WebP.
|
package/docs/routing-profiles.md
CHANGED
|
@@ -52,7 +52,7 @@ Use `blockrun/premium` for maximum quality. Codex for complex coding, Gemini 3.5
|
|
|
52
52
|
| SIMPLE | google/gemini-3.5-flash | $1.50 | $9.00 | gemini-3.6-flash → claude-haiku-4.5 → glm-5.3 → gemini-2.5-flash → gemini-3.5-flash-lite → deepseek-chat |
|
|
53
53
|
| MEDIUM | openai/gpt-5.3-codex | $1.75 | $14.00 | claude-sonnet-5 → kimi-k3 → glm-5.3 → gemini-3.6-flash → gemini-3.5-flash → gemini-2.5-pro → grok-4.5 → claude-sonnet-4.6 → gpt-5.6-terra |
|
|
54
54
|
| COMPLEX | anthropic/claude-fable-5 | $10.00 | $50.00 | claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → claude-sonnet-5 → claude-sonnet-4.6 → grok-4.5 → kimi-k3 → gpt-5.6-terra → gpt-5.5 → gpt-5.4 → gpt-5.3-codex → glm-5.3 → deepseek-v4-pro → deepseek-chat → nemotron-3.5-lightning (free) |
|
|
55
|
-
| REASONING | anthropic/claude-sonnet-5 | $
|
|
55
|
+
| REASONING | anthropic/claude-sonnet-5 | $2.00 | $10.00 | claude-sonnet-4.6 → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → grok-4.5 → deepseek-v4-pro → grok-4.3 → o4-mini → o3 |
|
|
56
56
|
|
|
57
57
|
The premium COMPLEX chain is deliberately de-Gemini'd: Google's "high demand" 503s correlate with Anthropic outages (everyone falls back to Google at the same time), so the chain prefers the in-family Opus hot swaps, then xAI, Moonshot, OpenAI and Z.AI — providers on independent infrastructure.
|
|
58
58
|
|
|
@@ -66,8 +66,8 @@ Not a profile you pick — router-core switches to these tiers when the turn act
|
|
|
66
66
|
| --------- | ------------------------- | ----- | ------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
67
67
|
| SIMPLE | openai/gpt-4o-mini | $0.15 | $0.60 | gpt-5.6-luna → glm-5.3-flash → claude-haiku-4.5 → gemini-2.5-flash |
|
|
68
68
|
| MEDIUM | openai/gpt-5-mini | $0.25 | $2.00 | gemini-3.5-flash → glm-5.3-flash → gpt-5.6-terra → gpt-4o-mini → claude-haiku-4.5 → deepseek-chat → kimi-k3 |
|
|
69
|
-
| COMPLEX | anthropic/claude-sonnet-5 | $
|
|
70
|
-
| REASONING | anthropic/claude-sonnet-5 | $
|
|
69
|
+
| COMPLEX | anthropic/claude-sonnet-5 | $2.00 | $10.00 | claude-sonnet-4.6 → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → grok-4.5 → kimi-k3 → gpt-5.6-terra → gpt-5.5 → gpt-5.4 → gpt-5.3-codex → glm-5.3 → deepseek-v4-pro → deepseek-chat → nemotron-3.5-lightning (free) |
|
|
70
|
+
| REASONING | anthropic/claude-sonnet-5 | $2.00 | $10.00 | claude-sonnet-4.6 → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → grok-4.5 → deepseek-v4-pro → deepseek-reasoner |
|
|
71
71
|
|
|
72
72
|
Set `routing.overrides.agenticMode: false` to disable the agentic tier set, or `true` to force it.
|
|
73
73
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@blockrun/clawrouter",
|
|
3
|
-
"version": "0.12.
|
|
3
|
+
"version": "0.12.281",
|
|
4
4
|
"description": "Smart LLM router — save 84% on inference costs. 82 models (6 free). Pay by credit card (API key) or USDC (x402 wallet).",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
@@ -147,7 +147,7 @@ it against a baseline nobody wrote down. See
|
|
|
147
147
|
|
|
148
148
|
## Available Models
|
|
149
149
|
|
|
150
|
-
<!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models including: gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.6-sol/terra/luna-pro [pro reasoning tiers], gpt-5.5, gpt-5.5-pro [max compute], chat-latest [ChatGPT Instant], gpt-5.4, gpt-4o, o3, claude-fable-5, claude-opus-5 [
|
|
150
|
+
<!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models including: gpt-6-astra [GPT-6 flagship, 1M ctx], gpt-6-sol, gpt-6-luna [fast, $0.10/$0.50], gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.6-sol/terra/luna-pro [pro reasoning tiers], gpt-5.5, gpt-5.5-pro [max compute], chat-latest [ChatGPT Instant], gpt-5.4, gpt-5.1, gpt-4o, o3, claude-fable-5.1, claude-fable-5, claude-opus-5.5 [newest Opus, $4/$20], claude-opus-5 [1M ctx], claude-opus-4.8, claude-opus-4.7, claude-opus-4.5, claude-sonnet-5.5, claude-sonnet-5, claude-sonnet-4.6, gemini-3.1-pro, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-2.5-flash, deepseek-v4-pro, deepseek-chat, grok-4.7, grok-4.6, grok-4.5, grok-4.3, grok-build-0.1, glm-5.3 [Z.AI flagship, 1M ctx], glm-5.3-flash [natively multimodal, 1M ctx — $0.15/$0.50], glm-5.2, minimax-m3, kimi-k3 [1M ctx flagship], kimi-k2.7, qwen3.7-max [Qwen flagship, 1M ctx], qwen3.7-plus, qwen3.7-flash, mimo [Xiaomi MiMo-V2.5 Pro, 1M ctx], and <!-- br:models.free -->6<!-- /br:models.free --> free open-weight models (nemotron-3.5-lightning [1M ctx, thinking mode — the free default], nemotron-3-ultra-550b [550B/55B MoE, 1M ctx — the largest free model], nemotron-3-nano-omni-30b-a3b-reasoning [256K ctx], llama-3.2-11b-vision [Meta Llama], north-mini-code [Cohere, coding, sub-second], laguna-xs-2.1 [Poolside, coding, ~161 tok/s]). The free tier is text-only — image turns route to a paid vision model, because the two free models the catalogs advertise as vision-capable fail a solid-colour probe on both chains and do so with an HTTP 200.
|
|
151
151
|
|
|
152
152
|
## Built-in Agent Tools
|
|
153
153
|
|
|
@@ -170,8 +170,8 @@ Realtime prices and historical OHLC across every asset class. The agent should c
|
|
|
170
170
|
|
|
171
171
|
| Tool | Purpose | Price |
|
|
172
172
|
| --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------- |
|
|
173
|
-
| `blockrun_image_generation` |
|
|
174
|
-
| `blockrun_image_edit` | Edit / inpaint existing image (
|
|
173
|
+
| `blockrun_image_generation` | 12 image models — GPT Image 1/2/2.5 (Flare, Sunburst), Nano Banana / 2 / Pro, Seedream 5 Pro, Grok Imagine / 2.0 / Pro, CogView-4 | $0.015–$0.15 / image |
|
|
174
|
+
| `blockrun_image_edit` | Edit / inpaint existing image (GPT Image 1/2, 2.5 Sunburst, Nano Banana; `model` param) | $0.02–$0.04 / image |
|
|
175
175
|
| `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 |
|
|
176
176
|
|
|
177
177
|
### Phone & Voice (Twilio + Bland.ai)
|
package/skills/imagegen/SKILL.md
CHANGED
|
@@ -55,17 +55,20 @@ Display inline: ``
|
|
|
55
55
|
|
|
56
56
|
### Model Selection
|
|
57
57
|
|
|
58
|
-
| Alias | Full ID
|
|
59
|
-
| ------------------ |
|
|
60
|
-
| `nano-banana` | `google/nano-banana`
|
|
61
|
-
| `banana-2` | `google/nano-banana-2`
|
|
62
|
-
| `banana-pro` | `google/nano-banana-pro`
|
|
63
|
-
| `gpt-image` | `openai/gpt-image-1`
|
|
64
|
-
| `gpt-image-2` | `openai/gpt-image-2`
|
|
65
|
-
| `
|
|
66
|
-
| `
|
|
67
|
-
| `
|
|
68
|
-
| `
|
|
58
|
+
| Alias | Full ID | Price | Sizes | Best for |
|
|
59
|
+
| ------------------ | ------------------------------- | ------------ | ------------------------------- | ------------------------------------------------------------------------------------------------------------------ |
|
|
60
|
+
| `nano-banana` | `google/nano-banana` | $0.05 | 1024×1024 | Default — fast, cheap, good quality |
|
|
61
|
+
| `banana-2` | `google/nano-banana-2` | $0.09 | 1024×1024 | Gemini 3.1 Flash imagegen — sharper than nano-banana at 1K |
|
|
62
|
+
| `banana-pro` | `google/nano-banana-pro` | $0.10–$0.15 | 1024×1024, 2048×2048, 4096×4096 | High-res, large format |
|
|
63
|
+
| `gpt-image` | `openai/gpt-image-1` | $0.02–$0.04 | 1024×1024, 1536×1024, 1024×1536 | Budget option; supports editing |
|
|
64
|
+
| `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 |
|
|
65
|
+
| `flare` | `openai/gpt-image-2.5-flare` | $0.28–$0.56 | 1024×1024, 1536×1024, 1024×1536 | GPT Image 2.5, fast — top OpenAI quality, caller can pick `quality` at a flat price |
|
|
66
|
+
| `sunburst` | `openai/gpt-image-2.5-sunburst` | $0.28–$0.56 | 1024×1024, 1536×1024, 1024×1536 | GPT Image 2.5, precision — best for high-fidelity edits |
|
|
67
|
+
| `seedream` | `bytedance/seedream-5-pro` | $0.045–$0.09 | up to 2848×1600 / 2304×1728 | Flagship quality, reference-image support |
|
|
68
|
+
| `grok-imagine` | `xai/grok-imagine-image` | $0.02 | 1024×1024 | xAI Grok image style |
|
|
69
|
+
| `grok-imagine-2` | `xai/grok-imagine-image-2.0` | $0.04 | 1024×1024 | Grok Imagine 2.0 — between grok-imagine and pro |
|
|
70
|
+
| `grok-imagine-pro` | `xai/grok-imagine-image-pro` | $0.07 | 1024×1024 | Grok high-quality |
|
|
71
|
+
| `cogview` | `zai/cogview-4` | $0.015–$0.02 | 512×512 to 1440×1440 | Cheapest — Zhipu CogView |
|
|
69
72
|
|
|
70
73
|
**Choosing a model:**
|
|
71
74
|
|
|
@@ -74,15 +77,16 @@ Display inline: ``
|
|
|
74
77
|
- "photorealistic" / complex scenes → `gpt-image-2`
|
|
75
78
|
- "flagship quality" / reference image → `seedream`
|
|
76
79
|
- "budget" / "cheap" → `cogview`
|
|
77
|
-
- "
|
|
80
|
+
- "top quality" / "best OpenAI" → `flare` (fast) or `sunburst` (precision)
|
|
81
|
+
- "editable" / "inpainting" → `gpt-image` (cheapest), `gpt-image-2`, or `sunburst` (most precise)
|
|
78
82
|
- "artistic" / flexible content → `grok-imagine`
|
|
79
83
|
- "grok style" → `grok-imagine` or `grok-imagine-pro`
|
|
80
84
|
|
|
81
85
|
**Choosing a size:**
|
|
82
86
|
|
|
83
87
|
- Default: `1024x1024` (the only size every model accepts)
|
|
84
|
-
- Portrait: `1024x1536` (gpt-image / gpt-image-2) or `1728x2304` (seedream)
|
|
85
|
-
- Landscape: `1536x1024` (gpt-image / gpt-image-2), `1344x768` (cogview), or `2048x1024` / `1280x720` (seedream)
|
|
88
|
+
- Portrait: `1024x1536` (gpt-image / gpt-image-2 / flare / sunburst) or `1728x2304` (seedream)
|
|
89
|
+
- Landscape: `1536x1024` (gpt-image / gpt-image-2 / flare / sunburst), `1344x768` (cogview), or `2048x1024` / `1280x720` (seedream)
|
|
86
90
|
- High-res: `2048x2048` / `4096x4096` with `banana-pro`; `2848x1600` with `seedream`
|
|
87
91
|
- The gateway validates size per model BEFORE payment and rejects unknown ones — do not invent sizes outside each model's list above
|
|
88
92
|
|
|
@@ -115,7 +119,7 @@ Response is identical to generation:
|
|
|
115
119
|
}
|
|
116
120
|
```
|
|
117
121
|
|
|
118
|
-
**Supported models for editing:** `openai/gpt-image-1`
|
|
122
|
+
**Supported models for editing:** `openai/gpt-image-1` (default, $0.02), `openai/gpt-image-2` ($0.06), `openai/gpt-image-2.5-sunburst` ($0.28), `google/nano-banana` ($0.05), `google/nano-banana-2` ($0.09), `google/nano-banana-pro` ($0.10). `mask` works with the OpenAI models only. `openai/gpt-image-2.5-flare` cannot edit.
|
|
119
123
|
|
|
120
124
|
---
|
|
121
125
|
|
|
@@ -141,4 +145,4 @@ Response is identical to generation:
|
|
|
141
145
|
- If the call fails with a payment error, check `GET http://localhost:8402/health` and read `authMode` before telling the user how to fix it: `wallet` → fund the wallet at [blockrun.ai](https://blockrun.ai); `api-key` → top up account credit at [user.blockrun.ai/dashboard/credits](https://user.blockrun.ai/dashboard/credits). Naming the wrong one sends the user to a page that cannot fix their error.
|
|
142
146
|
- Google models may return base64 internally — ClawRouter uploads automatically and returns a hosted URL
|
|
143
147
|
- OpenAI image models enforce OpenAI content policy; use `nano-banana` or `grok-imagine` for more flexibility
|
|
144
|
-
- Image editing
|
|
148
|
+
- Image editing works with gpt-image-1/2, sunburst and the nano-banana models (not flare, seedream, grok or cogview); generation supports all listed models
|
package/src/top-models.json
CHANGED
|
@@ -3,13 +3,19 @@
|
|
|
3
3
|
"premium",
|
|
4
4
|
"eco",
|
|
5
5
|
"free",
|
|
6
|
+
"anthropic/claude-fable-5.1",
|
|
6
7
|
"anthropic/claude-fable-5",
|
|
8
|
+
"anthropic/claude-opus-5.5",
|
|
7
9
|
"anthropic/claude-opus-5",
|
|
8
10
|
"anthropic/claude-opus-4.8",
|
|
9
11
|
"anthropic/claude-opus-4.7",
|
|
12
|
+
"anthropic/claude-sonnet-5.5",
|
|
10
13
|
"anthropic/claude-sonnet-5",
|
|
11
14
|
"anthropic/claude-sonnet-4.6",
|
|
12
15
|
"anthropic/claude-haiku-4.5",
|
|
16
|
+
"openai/gpt-6-astra",
|
|
17
|
+
"openai/gpt-6-sol",
|
|
18
|
+
"openai/gpt-6-luna",
|
|
13
19
|
"openai/gpt-5.6-terra",
|
|
14
20
|
"openai/gpt-5.6-sol",
|
|
15
21
|
"openai/gpt-5.6-luna",
|
|
@@ -19,6 +25,7 @@
|
|
|
19
25
|
"openai/gpt-5.4",
|
|
20
26
|
"openai/gpt-5.4-mini",
|
|
21
27
|
"openai/gpt-5.4-nano",
|
|
28
|
+
"openai/gpt-5.1",
|
|
22
29
|
"openai/gpt-5.3-codex",
|
|
23
30
|
"google/gemini-3.1-pro",
|
|
24
31
|
"google/gemini-3.8-flash",
|
|
@@ -27,6 +34,8 @@
|
|
|
27
34
|
"google/gemini-3.5-flash-lite",
|
|
28
35
|
"google/gemini-3.1-flash-lite",
|
|
29
36
|
"google/gemini-3-flash-preview",
|
|
37
|
+
"xai/grok-4.7",
|
|
38
|
+
"xai/grok-4.6",
|
|
30
39
|
"xai/grok-4.5",
|
|
31
40
|
"xai/grok-4.3",
|
|
32
41
|
"xai/grok-build-0.1",
|
|
@@ -43,7 +52,6 @@
|
|
|
43
52
|
"moonshot/kimi-k3",
|
|
44
53
|
"qwen/qwen3.7-max",
|
|
45
54
|
"qwen/qwen3.8-flash",
|
|
46
|
-
"tencent/hy3",
|
|
47
55
|
"deepseek/deepseek-v4-flash-vision-exp",
|
|
48
56
|
"deepseek/deepseek-v4-pro",
|
|
49
57
|
"deepseek/deepseek-chat",
|