@blockrun/clawrouter 0.12.279 → 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.
Files changed (19) hide show
  1. package/README.md +96 -86
  2. package/dist/cli.js +7479 -3049
  3. package/dist/index.d.ts +2 -2
  4. package/dist/index.js +7453 -3023
  5. package/dist/router/index.js +9 -10
  6. package/docs/9-free-ai-models-zero-cost-blockrun.md +5 -13
  7. package/docs/anthropic-cost-savings.md +1 -1
  8. package/docs/anthropic-third-party-harness-changes.md +2 -2
  9. package/docs/clawrouter-cuts-llm-api-costs-500x.md +2 -2
  10. package/docs/clawrouter-vs-openrouter-llm-routing-comparison.md +4 -4
  11. package/docs/features.md +3 -3
  12. package/docs/image-generation.md +43 -37
  13. package/docs/routing-profiles.md +12 -12
  14. package/openclaw.plugin.json +1 -1
  15. package/package.json +8 -5
  16. package/scripts/reinstall.sh +0 -1
  17. package/skills/clawrouter/SKILL.md +5 -5
  18. package/skills/imagegen/SKILL.md +20 -16
  19. package/src/top-models.json +9 -2
package/README.md CHANGED
@@ -36,7 +36,7 @@ Or neither — <!-- br:models.free -->6<!-- /br:models.free --> models are free,
36
36
 
37
37
  </div>
38
38
 
39
- > **ClawRouter** is an open-source smart LLM router that reduces AI API costs by up to <!-- br:savings.autoVsBaselinePct -->84<!-- /br:savings.autoVsBaselinePct -->%. It analyzes each request across <!-- br:clawrouter.dimensions -->15<!-- /br:clawrouter.dimensions --> dimensions and routes to the cheapest capable model in under 1ms, entirely locally. It is the only LLM router that an autonomous agent can pay for by itself — a wallet signature is the account, and USDC micropayments over the x402 protocol are the billing — and it takes an ordinary credit card too: sign up at [user.blockrun.ai](https://user.blockrun.ai), top up, and run the same router on an API key. <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models from OpenAI, Anthropic, Google, xAI, DeepSeek, and more. MIT licensed.
39
+ > **ClawRouter** is an open-source smart LLM router that reduces AI API costs by up to <!-- br:savings.autoVsBaselinePct -->84<!-- /br:savings.autoVsBaselinePct -->%. It analyzes each request across <!-- br:clawrouter.dimensions -->15<!-- /br:clawrouter.dimensions --> dimensions and routes to the cheapest capable model in under 1ms, entirely locally. It is the only LLM router that an autonomous agent can pay for by itself — a wallet signature is the account, and USDC micropayments over the x402 protocol are the billing — and it takes an ordinary credit card too: sign up at [user.blockrun.ai](https://user.blockrun.ai), top up, and run the same router on an API key. <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models from OpenAI, Anthropic, Google, xAI, DeepSeek, and more. MIT licensed.
40
40
 
41
41
  ---
42
42
 
@@ -48,7 +48,7 @@ Not a seat, not a subscription, not a monthly minimum you keep paying while the
48
48
 
49
49
  | | |
50
50
  | ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
51
- | **Every LLM** | <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> chat models across 9 providers, behind one endpoint and one balance |
51
+ | **Every LLM** | <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> chat models across 9 providers, behind one endpoint and one balance |
52
52
  | **Every tool** | <!-- br:models.image -->12<!-- /br:models.image --> image models, <!-- br:models.video -->8<!-- /br:models.video --> video models, music, <!-- br:models.speech -->5<!-- /br:models.speech --> voices, img2img editing, and outbound phone calls that come back as transcripts |
53
53
  | **Every data source** | web, news and neural search; prediction markets; live crypto and equity quotes; on-chain SQL over 100M+ labeled wallets; DEX routing; RPC across <!-- br:chains.rpc -->40<!-- /br:chains.rpc --> chains |
54
54
  | **Best value per dollar** | <!-- br:clawrouter.dimensions -->15<!-- /br:clawrouter.dimensions -->-dimension local routing sends each request to the cheapest model that can actually do it — <!-- br:savings.autoVsBaselinePct -->84<!-- /br:savings.autoVsBaselinePct -->% below pinning Claude Opus 5 on the same traffic, computed from a published workload mix rather than estimated |
@@ -76,7 +76,7 @@ This is the stack that lets agents operate autonomously: **x402 + USDC + local r
76
76
 
77
77
  ### …and if you are a human, not an agent
78
78
 
79
- Every "no X needed" above is a capability, not a restriction. **ClawRouter takes a credit card too.** Sign up at **[user.blockrun.ai](https://user.blockrun.ai)**, top up, mint an API key, and run `clawrouter login brk_live_…`. Same router, same <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models, same local routing — calls go to `api.blockrun.ai` on a bearer token and bill your account credit. No crypto, no gas, no seed phrase.
79
+ Every "no X needed" above is a capability, not a restriction. **ClawRouter takes a credit card too.** Sign up at **[user.blockrun.ai](https://user.blockrun.ai)**, top up, mint an API key, and run `clawrouter login brk_live_…`. Same router, same <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models, same local routing — calls go to `api.blockrun.ai` on a bearer token and bill your account credit. No crypto, no gas, no seed phrase.
80
80
 
81
81
  | You are | Pay with | Setup |
82
82
  | ------------------- | --------------------------------------- | ------------------------------------------------------------------------------------------- |
@@ -92,7 +92,7 @@ Full walkthrough: [Paying with a credit card](#paying-with-a-credit-card-api-key
92
92
 
93
93
  | | OpenRouter | LiteLLM | Martian | Portkey | **ClawRouter** |
94
94
  | ---------------- | ----------------- | ---------------- | ----------------- | ----------------- | ---------------------------------------------------------------------- |
95
- | **Models** | 200+ | 100+ | Smart routing | Gateway | **<!-- br:models.chatVisible -->78<!-- /br:models.chatVisible -->** |
95
+ | **Models** | 200+ | 100+ | Smart routing | Gateway | **<!-- br:models.chatVisible -->82<!-- /br:models.chatVisible -->** |
96
96
  | **Free tier** | Rate-limited | BYO keys | No | No | **<!-- br:models.free -->6<!-- /br:models.free --> models, no signup** |
97
97
  | **Routing** | Manual selection | Manual selection | Smart (closed) | Observability | **Smart (open source)** |
98
98
  | **Auth** | Account + API key | Your API keys | Account + API key | Account + API key | **Wallet signature _or_ API key** |
@@ -127,7 +127,7 @@ is all it takes to switch and `clawrouter logout` is all it takes to switch back
127
127
 
128
128
  > **Where do I sign up?** [**user.blockrun.ai**](https://user.blockrun.ai) — sign in with
129
129
  > Google, add credit with a card under **Credits**, mint a key under **API Keys**. That
130
- > one key covers all <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> chat models
130
+ > one key covers all <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> chat models
131
131
  > plus images, video, speech and the live-data APIs. No wallet, no crypto, no seed phrase.
132
132
 
133
133
  ### Desktop control plane (macOS)
@@ -171,7 +171,7 @@ openclaw gateway restart
171
171
 
172
172
  > **Using Claude Code?** Check out [BRCC](https://github.com/BlockRunAI/brcc) — it's purpose-built for Claude Code with the same smart routing and x402 payments.
173
173
  >
174
- > **Using NousResearch Hermes?** See [ClawRouter-Hermes](https://github.com/BlockRunAI/ClawRouter-Hermes) — a Python plugin that wires Hermes into the ClawRouter proxy. Same wallet, same <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models, same x402 USDC settlement on Solana & Base.
174
+ > **Using NousResearch Hermes?** See [ClawRouter-Hermes](https://github.com/BlockRunAI/ClawRouter-Hermes) — a Python plugin that wires Hermes into the ClawRouter proxy. Same wallet, same <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models, same x402 USDC settlement on Solana & Base.
175
175
 
176
176
  No OpenClaw required. ClawRouter runs as a local proxy on port 8402.
177
177
 
@@ -285,8 +285,8 @@ Request → 15-dimension scorer → tier + task shape
285
285
  | --------- | --------------------------------- | ------------------------------- | ---------------------------- | ------------------------- |
286
286
  | SIMPLE | nemotron-3.5-lightning (**FREE**) | gemini-2.5-flash ($0.30/$2.50) | gemini-3.5-flash ($1.50/$9) | gpt-4o-mini ($0.15/$0.60) |
287
287
  | MEDIUM | glm-5.3-flash ($0.15/$0.50) | gemini-3.5-flash ($1.50/$9) | gpt-5.3-codex ($1.75/$14.00) | gpt-5-mini ($0.25/$2) |
288
- | COMPLEX | glm-5.3-flash ($0.15/$0.50) | gemini-3.1-pro ($2/$12) | claude-fable-5 ($10/$50) | claude-sonnet-5 ($3/$15) |
289
- | REASONING | deepseek-reasoner ($0.14/$0.28) | deepseek-reasoner ($0.14/$0.28) | claude-sonnet-5 ($3/$15) | claude-sonnet-5 ($3/$15) |
288
+ | COMPLEX | glm-5.3-flash ($0.15/$0.50) | gemini-3.1-pro ($2/$12) | claude-fable-5 ($10/$50) | claude-sonnet-5 ($2/$10) |
289
+ | REASONING | deepseek-reasoner ($0.14/$0.28) | deepseek-reasoner ($0.14/$0.28) | claude-sonnet-5 ($2/$10) | claude-sonnet-5 ($2/$10) |
290
290
 
291
291
  † Withheld from `/v1/models` — since Router Core V3.5 no chain names such a model: every primary and every fallback rung above is a model you can find on the public pricing page. [savings-mix.json](https://github.com/BlockRunAI/blockrun/blob/main/src/brand/savings-mix.json) prices the published savings claim on the same visible models.
292
292
  ‡ Auto-selected in any profile when the turn actually needs its attached tools; prefers models that keep going instead of stopping to ask.
@@ -318,17 +318,20 @@ Generate images directly from chat with `/cr-imagegen`:
318
318
 
319
319
  > The slash command is `/cr-imagegen` to avoid colliding with Telegram channel commands. Typing `/imagegen` in chat still works for backward compatibility.
320
320
 
321
- | Model | Provider | Price | Max Size |
322
- | ---------------------------- | -------------------- | ------------ | --------- |
323
- | `nano-banana` | Google Gemini Flash | $0.05/image | 1024x1024 |
324
- | `banana-2` | Google Nano Banana 2 | $0.09/image | 1024x1024 |
325
- | `banana-pro` | Google Gemini Pro | $0.10/image | 4096x4096 |
326
- | `gpt-image` | OpenAI GPT Image 1 | $0.02/image | 1536x1024 |
327
- | `gpt-image-2` | OpenAI GPT Image 2 | $0.06/image | 1536x1024 |
328
- | `seedream` | ByteDance Seedream 5 | $0.045/image | 2848x1600 |
329
- | `xai/grok-imagine-image` | xAI Grok Imagine | $0.02/image | 1024x1024 |
330
- | `xai/grok-imagine-image-pro` | xAI Grok Imagine Pro | $0.07/image | 1024x1024 |
331
- | `zai/cogview-4` | Zhipu CogView-4 | $0.015/image | 1440x1440 |
321
+ | Model | Provider | Price | Max Size |
322
+ | ---------------------------- | ----------------------------- | ------------ | --------- |
323
+ | `nano-banana` | Google Gemini Flash | $0.05/image | 1024x1024 |
324
+ | `banana-2` | Google Nano Banana 2 | $0.09/image | 1024x1024 |
325
+ | `banana-pro` | Google Gemini Pro | $0.10/image | 4096x4096 |
326
+ | `gpt-image` | OpenAI GPT Image 1 | $0.02/image | 1536x1024 |
327
+ | `gpt-image-2` | OpenAI GPT Image 2 | $0.06/image | 1536x1024 |
328
+ | `flare` | OpenAI GPT Image 2.5 Flare | $0.28/image | 1536x1024 |
329
+ | `sunburst` | OpenAI GPT Image 2.5 Sunburst | $0.28/image | 1536x1024 |
330
+ | `seedream` | ByteDance Seedream 5 | $0.045/image | 2848x1600 |
331
+ | `xai/grok-imagine-image` | xAI Grok Imagine | $0.02/image | 1024x1024 |
332
+ | `grok-imagine-2` | xAI Grok Imagine 2.0 | $0.04/image | 1024x1024 |
333
+ | `xai/grok-imagine-image-pro` | xAI Grok Imagine Pro | $0.07/image | 1024x1024 |
334
+ | `zai/cogview-4` | Zhipu CogView-4 | $0.015/image | 1440x1440 |
332
335
 
333
336
  ## Video Generation
334
337
 
@@ -377,12 +380,12 @@ Edit existing images with `/img2img`:
377
380
  /img2img --image ./cat.jpg --mask ./mask.png remove the background
378
381
  ```
379
382
 
380
- | Option | Required | Description |
381
- | ----------------- | -------- | ------------------------------------- |
382
- | `--image <path>` | Yes | Local image file path (supports `~/`) |
383
- | `--mask <path>` | No | Mask image (white = area to edit) |
384
- | `--model <model>` | No | Model to use (default: `gpt-image-1`) |
385
- | `--size <WxH>` | No | Output size (default: `1024x1024`) |
383
+ | Option | Required | Description |
384
+ | ----------------- | -------- | --------------------------------------------------------------------------------------------------------------------- |
385
+ | `--image <path>` | Yes | Local image file path (supports `~/`) |
386
+ | `--mask <path>` | No | Mask image (white = area to edit) |
387
+ | `--model <model>` | No | `gpt-image-1` (default), `gpt-image-2`, `sunburst`, `nano-banana`, `banana-2`, `banana-pro` — `--mask` is OpenAI-only |
388
+ | `--size <WxH>` | No | Output size (default: `1024x1024`) |
386
389
 
387
390
  **API endpoint:** `POST http://localhost:8402/v1/images/image2image` — see [full docs](docs/image-generation.md#post-v1imagesimage2image).
388
391
 
@@ -482,48 +485,46 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
482
485
 
483
486
  ## Models & Pricing
484
487
 
485
- <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models across 9 providers, one wallet. **<!-- br:models.free -->6<!-- /br:models.free --> models are $0 — paid models start at fractions of a cent.**
488
+ <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models across 9 providers, one wallet. **<!-- br:models.free -->6<!-- /br:models.free --> models are $0 — paid models start at fractions of a cent.**
486
489
 
487
490
  > **💡 "Cost per request"** = estimated cost for a typical chat message (~500 input + 500 output tokens). Paid requests also carry a flat **$0.001/tx settlement fee** (covers on-chain gas; already included in the price the gateway quotes). Free models never pay it.
488
491
 
489
492
  ### Budget Models (under $0.001/request)
490
493
 
491
- | Model | Input $/M | Output $/M | ~$/request | Context | Features |
492
- | ------------------------------------------- | --------: | ---------: | ---------: | ------- | -------------------------------------------- |
493
- | free/nemotron-3.5-lightning | **FREE** | **FREE** | **$0** | 1M | reasoning (thinking mode) — the free default |
494
- | free/nemotron-3-nano-30b | **FREE** | **FREE** | **$0** | 131K | fastest free model (~121 tok/s) |
495
- | free/laguna-xs-2.1 | **FREE** | **FREE** | **$0** | 131K | coding (Poolside, ~161 tok/s) |
496
- | free/north-mini-code | **FREE** | **FREE** | **$0** | 256K | coding (Cohere, sub-second) |
497
- | free/nemotron-3-nano-omni-30b-a3b-reasoning | **FREE** | **FREE** | **$0** | 256K | reasoning (text only — see note) |
498
- | free/nemotron-3-ultra-550b | **FREE** | **FREE** | **$0** | 1M | largest free model (550B/55B MoE) |
499
- | free/llama-3.2-11b-vision | **FREE** | **FREE** | **$0** | 128K | Meta Llama (text only — see note) |
500
- | qwen/qwen3.7-flash | $0.03 | $0.13 | $0.0001 | 1M | reasoning, tools (fastest Qwen tier) |
501
- | openai/gpt-5-nano | $0.05 | $0.40 | $0.0002 | 128K | tools |
502
- | openai/gpt-5.6-luna-pro | $0.10 | $0.60 | $0.0004 | 1M | reasoning, vision, agentic, tools |
503
- | openai/gpt-4.1-nano | $0.10 | $0.40 | $0.0003 | 128K | tools |
504
- | google/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.0003 | 1M | tools |
505
- | openai/gpt-4o-mini | $0.15 | $0.60 | $0.0004 | 128K | tools |
506
- | tencent/hy3 | $0.132 | $0.528 | $0.0003 | 262K | reasoning (Tencent Hy3) |
507
- | xai/grok-4-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
508
- | openai/gpt-5.6-luna | $0.20 | $1.20 | $0.0007 | 1M | vision, agentic, tools |
509
- | xai/grok-4-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools |
510
- | xai/grok-4-1-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
511
- | openai/gpt-5-mini | $0.25 | $2.00 | $0.0011 | 200K | tools |
512
- | qwen/qwen3.7-plus | $0.32 | $1.28 | $0.0008 | 1M | reasoning, agentic, tools (balanced Qwen) |
513
- | deepseek/deepseek-chat | $0.14 | $0.28 | $0.0002 | 1M | tools (V4 Flash chat) |
514
- | deepseek/deepseek-reasoner | $0.14 | $0.28 | $0.0002 | 1M | reasoning, tools (V4 Flash thinking) |
515
- | deepseek/deepseek-v4-pro | $0.435 | $0.87 | $0.0007 | 1M | reasoning, agentic, tools (V4 flagship) |
516
- | xiaomi/mimo-v2.5-pro | $0.435 | $0.87 | $0.0007 | 1M | reasoning (Xiaomi MiMo-V2.5 Pro) |
517
- | zai/glm-5-turbo | $1.20 | $4.00 | $0.0026 | 200K | tools |
518
- | minimax/minimax-m3 | $0.30 | $1.20 | $0.0008 | 1M | reasoning, agentic, tools |
519
- | minimax/minimax-m2.7 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
520
- | minimax/minimax-m2.5 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
521
- | google/gemini-2.5-flash | $0.30 | $2.50 | $0.0014 | 1M | vision, tools |
522
- | google/gemini-3.5-flash-lite | $0.30 | $2.50 | $0.0014 | 1M | reasoning, tools (thinking built-in) |
523
- | openai/gpt-4.1-mini | $0.40 | $1.60 | $0.0010 | 128K | tools |
524
- | google/gemini-3-flash-preview | $0.50 | $3.00 | $0.0018 | 1M | vision |
525
- | moonshot/kimi-k2.5 | $0.60 | $3.00 | $0.0018 | 262K | reasoning, vision, agentic, tools |
526
- | moonshot/kimi-k2.7 | $0.95 | $4.00 | $0.0025 | 262K | reasoning, vision, agentic, tools |
494
+ | Model | Input $/M | Output $/M | ~$/request | Context | Features |
495
+ | ------------------------------------------- | --------: | ---------: | ---------: | ------- | --------------------------------------------------- |
496
+ | free/nemotron-3.5-lightning | **FREE** | **FREE** | **$0** | 1M | reasoning (thinking mode) — the free default |
497
+ | free/laguna-xs-2.1 | **FREE** | **FREE** | **$0** | 131K | coding (Poolside, ~161 tok/s) |
498
+ | free/north-mini-code | **FREE** | **FREE** | **$0** | 256K | coding (Cohere, sub-second) |
499
+ | free/nemotron-3-nano-omni-30b-a3b-reasoning | **FREE** | **FREE** | **$0** | 256K | reasoning (text only — see note) |
500
+ | free/nemotron-3-ultra-550b | **FREE** | **FREE** | **$0** | 1M | largest free model (550B/55B MoE) |
501
+ | free/llama-3.2-11b-vision | **FREE** | **FREE** | **$0** | 128K | Meta Llama (text only — see note) |
502
+ | qwen/qwen3.7-flash | $0.03 | $0.13 | $0.0001 | 1M | reasoning, tools (fastest Qwen tier) |
503
+ | openai/gpt-5-nano | $0.05 | $0.40 | $0.0002 | 128K | tools |
504
+ | openai/gpt-5.6-luna-pro | $0.20 | $1.20 | $0.0007 | 1M | reasoning, vision, agentic, tools |
505
+ | openai/gpt-4.1-nano | $0.10 | $0.40 | $0.0003 | 128K | tools |
506
+ | google/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.0003 | 1M | tools |
507
+ | openai/gpt-4o-mini | $0.15 | $0.60 | $0.0004 | 128K | tools |
508
+ | openai/gpt-6-luna | $0.10 | $0.50 | $0.0003 | 1M | reasoning, vision, agentic, tools (GPT-6 fast tier) |
509
+ | xai/grok-4-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
510
+ | openai/gpt-5.6-luna | $0.20 | $1.20 | $0.0007 | 1M | vision, agentic, tools |
511
+ | xai/grok-4-fast-reasoning | $0.20 | $0.50 | $0.0004 | 131K | reasoning, tools |
512
+ | xai/grok-4-1-fast | $0.20 | $0.50 | $0.0004 | 131K | tools |
513
+ | openai/gpt-5-mini | $0.25 | $2.00 | $0.0011 | 200K | tools |
514
+ | qwen/qwen3.7-plus | $0.32 | $1.28 | $0.0008 | 1M | reasoning, agentic, tools (balanced Qwen) |
515
+ | deepseek/deepseek-chat | $0.14 | $0.28 | $0.0002 | 1M | tools (V4 Flash chat) |
516
+ | deepseek/deepseek-reasoner | $0.14 | $0.28 | $0.0002 | 1M | reasoning, tools (V4 Flash thinking) |
517
+ | xiaomi/mimo-v2.5-pro | $0.435 | $0.87 | $0.0007 | 1M | reasoning (Xiaomi MiMo-V2.5 Pro) |
518
+ | zai/glm-5-turbo | $1.20 | $4.00 | $0.0026 | 200K | tools |
519
+ | minimax/minimax-m3 | $0.30 | $1.20 | $0.0008 | 1M | reasoning, agentic, tools |
520
+ | minimax/minimax-m2.7 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
521
+ | minimax/minimax-m2.5 | $0.30 | $1.20 | $0.0008 | 205K | reasoning, agentic, tools |
522
+ | google/gemini-2.5-flash | $0.30 | $2.50 | $0.0014 | 1M | vision, tools |
523
+ | google/gemini-3.5-flash-lite | $0.30 | $2.50 | $0.0014 | 1M | reasoning, tools (thinking built-in) |
524
+ | openai/gpt-4.1-mini | $0.40 | $1.60 | $0.0010 | 128K | tools |
525
+ | google/gemini-3-flash-preview | $0.50 | $3.00 | $0.0018 | 1M | vision |
526
+ | moonshot/kimi-k2.5 | $0.60 | $3.00 | $0.0018 | 262K | reasoning, vision, agentic, tools |
527
+ | moonshot/kimi-k2.7 | $0.95 | $4.00 | $0.0025 | 262K | reasoning, vision, agentic, tools |
527
528
 
528
529
  ### Mid-Range Models ($0.001–$0.01/request)
529
530
 
@@ -531,51 +532,60 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
531
532
  | --------------------------- | --------: | ---------: | ---------: | ------- | ----------------------------------------- |
532
533
  | anthropic/claude-haiku-4.5 | $1.00 | $5.00 | $0.0030 | 200K | vision, agentic, tools |
533
534
  | zai/glm-5 | $1.00 | $3.20 | $0.0021 | 200K | reasoning, tools |
534
- | openai/gpt-5.6-terra-pro | $1.00 | $6.00 | $0.0035 | 1M | reasoning, vision, agentic, tools |
535
+ | openai/gpt-5.6-terra-pro | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, agentic, tools |
535
536
  | openai/o1-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools |
536
537
  | openai/o3-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools |
537
538
  | openai/o4-mini | $1.10 | $4.40 | $0.0028 | 128K | reasoning, tools |
538
539
  | google/gemini-2.5-pro | $1.25 | $10.00 | $0.0056 | 1M | reasoning, vision, tools |
539
540
  | zai/glm-5.2 | $1.40 | $4.40 | $0.0029 | 1M | reasoning, coding, tools (flagship) |
540
541
  | zai/glm-5.1 | $1.40 | $4.40 | $0.0029 | 200K | reasoning, tools (promo ended 2026-06-05) |
542
+ | deepseek/deepseek-v4-pro | $1.32 | $3.96 | $0.0026 | 1M | reasoning, agentic, tools (V4 flagship) |
541
543
  | qwen/qwen3.7-max | $1.475 | $4.425 | $0.0030 | 1M | reasoning, agentic, tools (Qwen flagship) |
542
544
  | xai/grok-4.3 | $1.25 | $2.50 | $0.0019 | 1M | reasoning, vision, agentic, tools |
543
545
  | google/gemini-3.8-flash | $0.75 | $3.75 | $0.0023 | 1M | reasoning, vision, tools (newest Flash) |
544
546
  | google/gemini-3.6-flash | $0.75 | $3.75 | $0.0023 | 1M | reasoning, vision, tools (thinking mode) |
545
547
  | google/gemini-3.5-flash | $1.50 | $9.00 | $0.0053 | 1M | reasoning, vision, tools (thinking) |
546
548
  | xai/grok-4.5 | $2.00 | $6.00 | $0.0040 | 500K | reasoning, vision, agentic, tools |
549
+ | xai/grok-4.7 | $2.00 | $6.00 | $0.0040 | 500K | reasoning, vision, agentic, tools |
550
+ | xai/grok-4.6 | $2.00 | $6.00 | $0.0040 | 500K | reasoning, vision, agentic, tools |
547
551
  | xai/grok-build-0.1 | $1.00 | $2.00 | $0.0015 | 256K | agentic coding, tools |
548
552
  | openai/gpt-5.2 | $1.75 | $14.00 | $0.0079 | 400K | reasoning, vision, agentic, tools |
549
553
  | openai/gpt-5.3 | $1.75 | $14.00 | $0.0079 | 128K | reasoning, vision, agentic, tools |
550
554
  | openai/gpt-5.3-codex | $1.75 | $14.00 | $0.0079 | 400K | agentic, tools |
555
+ | openai/gpt-5.1 | $1.25 | $10.00 | $0.0056 | 400K | reasoning, vision, agentic, tools |
551
556
  | openai/gpt-4.1 | $2.00 | $8.00 | $0.0050 | 128K | vision, tools |
552
557
  | openai/o3 | $2.00 | $8.00 | $0.0050 | 200K | reasoning, tools |
553
558
  | google/gemini-3-pro-preview | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, tools |
554
559
  | google/gemini-3.1-pro | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, tools |
555
560
  | xai/grok-2-vision | $2.00 | $10.00 | $0.0060 | 131K | vision, tools |
556
561
  | openai/gpt-4o | $2.50 | $10.00 | $0.0063 | 128K | vision, agentic, tools |
557
- | openai/gpt-5.4 | $2.50 | $15.00 | $0.0088 | 400K | reasoning, vision, agentic, tools |
562
+ | openai/gpt-5.4 | $2.50 | $15.00 | $0.0088 | 1M | reasoning, vision, agentic, tools |
558
563
  | openai/gpt-5.6-terra | $2.00 | $12.00 | $0.0070 | 1M | reasoning, vision, agentic, tools |
564
+ | openai/gpt-6-sol | $2.00 | $10.00 | $0.0060 | 1M | reasoning, vision, agentic, tools (GPT-6) |
565
+ | anthropic/claude-sonnet-5.5 | $2.00 | $10.00 | $0.0060 | 1M | reasoning, vision, agentic, tools |
566
+ | anthropic/claude-sonnet-5 | $2.00 | $10.00 | $0.0060 | 1M | reasoning, vision, agentic, tools |
559
567
 
560
568
  ### Premium Models ($0.01+/request)
561
569
 
562
- | Model | Input $/M | Output $/M | ~$/request | Context | Features |
563
- | --------------------------- | --------: | ---------: | ---------: | ------- | --------------------------------- |
564
- | anthropic/claude-sonnet-5 | $3.00 | $15.00 | $0.0090 | 1M | reasoning, vision, agentic, tools |
565
- | anthropic/claude-sonnet-4.6 | $3.00 | $15.00 | $0.0090 | 200K | reasoning, vision, agentic, tools |
566
- | anthropic/claude-opus-5 | $5.00 | $25.00 | $0.0150 | 1M | reasoning, vision, agentic, tools |
567
- | anthropic/claude-opus-4.8 | $5.00 | $25.00 | $0.0150 | 1M | reasoning, vision, agentic, tools |
568
- | openai/gpt-5.6-sol | $4.00 | $20.00 | $0.0120 | 1M | reasoning, vision, agentic, tools |
569
- | openai/gpt-5.6-sol-pro | $4.00 | $20.00 | $0.0120 | 1M | reasoning, vision, agentic, tools |
570
- | openai/gpt-5.5 | $5.00 | $30.00 | $0.0175 | 1M | reasoning, vision, agentic, tools |
571
- | moonshot/kimi-k3 | $3.00 | $15.00 | $0.0110 | 1M | reasoning, vision, agentic, tools |
572
- | openai/chat-latest | $5.00 | $30.00 | $0.0175 | 128K | vision, tools |
573
- | openai/o1 | $15.00 | $60.00 | $0.0375 | 200K | reasoning, tools |
574
- | openai/gpt-5.2-pro | $21.00 | $168.00 | $0.0945 | 400K | reasoning, tools |
575
- | openai/gpt-5.4-pro | $30.00 | $180.00 | $0.1050 | 400K | reasoning, tools |
576
- | openai/gpt-5.5-pro | $30.00 | $180.00 | $0.1050 | 1M | reasoning, vision, tools |
577
-
578
- > **Free tier:** <!-- br:models.free -->6<!-- /br:models.free --> open-weight models cost nothing — `/model free` pins the free default (`nemotron-3.5-lightning`, with the other six as fallbacks), `/model eco` opens on it, or pick one directly (e.g., `/model lightning` for 1M-context reasoning, `/model north-mini` or `/model laguna` for fast coding, `/model nano-30b` for the fastest).
570
+ | Model | Input $/M | Output $/M | ~$/request | Context | Features |
571
+ | --------------------------- | --------: | ---------: | ---------: | ------- | ------------------------------------------------------ |
572
+ | anthropic/claude-sonnet-4.6 | $3.00 | $15.00 | $0.0090 | 1M | reasoning, vision, agentic, tools |
573
+ | anthropic/claude-opus-5.5 | $4.00 | $20.00 | $0.0120 | 1M | reasoning, vision, agentic, tools |
574
+ | anthropic/claude-opus-5 | $5.00 | $25.00 | $0.0150 | 1M | reasoning, vision, agentic, tools |
575
+ | anthropic/claude-opus-4.8 | $5.00 | $25.00 | $0.0150 | 1M | reasoning, vision, agentic, tools |
576
+ | openai/gpt-5.6-sol | $4.00 | $20.00 | $0.0120 | 1M | reasoning, vision, agentic, tools |
577
+ | openai/gpt-5.6-sol-pro | $4.00 | $20.00 | $0.0120 | 1M | reasoning, vision, agentic, tools |
578
+ | openai/gpt-5.5 | $5.00 | $30.00 | $0.0175 | 1M | reasoning, vision, agentic, tools |
579
+ | openai/gpt-6-astra | $10.00 | $50.00 | $0.0300 | 1M | reasoning, vision, agentic, tools (GPT-6 flagship) |
580
+ | anthropic/claude-fable-5.1 | $10.00 | $50.00 | $0.0300 | 1M | reasoning, vision, agentic, tools (always-on thinking) |
581
+ | moonshot/kimi-k3 | $3.00 | $15.00 | $0.0110 | 1M | reasoning, vision, agentic, tools |
582
+ | openai/chat-latest | $5.00 | $30.00 | $0.0175 | 128K | vision, tools |
583
+ | openai/o1 | $15.00 | $60.00 | $0.0375 | 200K | reasoning, tools |
584
+ | openai/gpt-5.2-pro | $21.00 | $168.00 | $0.0945 | 400K | reasoning, tools |
585
+ | openai/gpt-5.4-pro | $30.00 | $180.00 | $0.1050 | 1M | reasoning, tools |
586
+ | openai/gpt-5.5-pro | $30.00 | $180.00 | $0.1050 | 1M | reasoning, vision, tools |
587
+
588
+ > **Free tier:** <!-- br:models.free -->6<!-- /br:models.free --> open-weight models cost nothing — `/model free` pins the free default (`nemotron-3.5-lightning`, with the other five as fallbacks), `/model eco` opens on it, or pick one directly (e.g., `/model lightning` for 1M-context reasoning, `/model north-mini` or `/model laguna` for fast coding).
579
589
  >
580
590
  > **No free vision.** Two free models are catalogued as vision-capable and neither reliably is: on a 64×64 solid-colour probe `nemotron-3-nano-omni` was right 1 of 4 times on Base and answered "white" for red on Solana, and `llama-3.2-11b-vision` replied "I'm unable to see the image" 3 of 3 while answering text fine. Both return HTTP 200, so a wrong answer arrives with no error to branch on. ClawRouter therefore does not flag them for vision, and requests carrying an `image_url` route to a paid vision model instead.
581
591
  > **Best value:** `gpt-5-nano` and `gemini-2.5-flash-lite` deliver strong results at ~$0.0003/request.
@@ -871,7 +881,7 @@ npm test
871
881
 
872
882
  **The LLM router built for autonomous agents**
873
883
 
874
- You're here. <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models, local smart routing, and two ways to pay — a credit-card-funded API key, or x402 USDC from a wallet, which is what lets an agent operate independently.
884
+ You're here. <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models, local smart routing, and two ways to pay — a credit-card-funded API key, or x402 USDC from a wallet, which is what lets an agent operate independently.
875
885
 
876
886
  `curl -fsSL https://blockrun.ai/ClawRouter-update | bash`
877
887
 
@@ -882,7 +892,7 @@ You're here. <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> mod
882
892
 
883
893
  **BlockRun for Claude Code**
884
894
 
885
- Run Claude Code with <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models, no rate limits, no Anthropic account, no phone verification. Pay per request with USDC — your wallet is your identity.
895
+ Run Claude Code with <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models, no rate limits, no Anthropic account, no phone verification. Pay per request with USDC — your wallet is your identity.
886
896
 
887
897
  `curl -fsSL https://blockrun.ai/brcc-install | bash`
888
898
 
@@ -895,7 +905,7 @@ Run Claude Code with <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible
895
905
 
896
906
  **ClawRouter for NousResearch Hermes**
897
907
 
898
- Python plugin that wraps the ClawRouter proxy for `hermes-agent`. Same <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models, same x402 USDC payments on Solana & Base, native Hermes ergonomics.
908
+ Python plugin that wraps the ClawRouter proxy for `hermes-agent`. Same <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> models, same x402 USDC payments on Solana & Base, native Hermes ergonomics.
899
909
 
900
910
  `pip install hermes-plugin-clawrouter`
901
911
 
@@ -939,7 +949,7 @@ Python plugin that wraps the ClawRouter proxy for `hermes-agent`. Same <!-- br:m
939
949
 
940
950
  ### What is BlockRun?
941
951
 
942
- BlockRun lets agents pay for the outcome — every LLM, tool and data source, best value per dollar. One endpoint and one balance covering <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> chat models plus image, video, music and speech generation, search, market data and multi-chain RPC, billed per call with USDC over [x402](https://x402.org) or a credit-card-funded API key — no seat, no subscription, no minimum. ClawRouter is the open-source local router agents use to reach it.
952
+ BlockRun lets agents pay for the outcome — every LLM, tool and data source, best value per dollar. One endpoint and one balance covering <!-- br:models.chatVisible -->82<!-- /br:models.chatVisible --> chat models plus image, video, music and speech generation, search, market data and multi-chain RPC, billed per call with USDC over [x402](https://x402.org) or a credit-card-funded API key — no seat, no subscription, no minimum. ClawRouter is the open-source local router agents use to reach it.
943
953
 
944
954
  ### What is ClawRouter?
945
955
 
@@ -972,7 +982,7 @@ wallet, no key, no signup. See [Paying with a credit card](#paying-with-a-credit
972
982
 
973
983
  ### Is ClawRouter free?
974
984
 
975
- ClawRouter itself is free and MIT licensed. You pay only for the LLM API calls routed through it — and several open-weight models (`nemotron-3.5-lightning`, `nemotron-3-nano-30b`, `laguna-xs-2.1`, `north-mini-code`, `nemotron-3-nano-omni-30b-a3b-reasoning`, `nemotron-3-ultra-550b`, `llama-3.2-11b-vision`) are completely free (text only). Use `/model free` to smart-route across them, or pick any by name.
985
+ ClawRouter itself is free and MIT licensed. You pay only for the LLM API calls routed through it — and several open-weight models (`nemotron-3.5-lightning`, `laguna-xs-2.1`, `north-mini-code`, `nemotron-3-nano-omni-30b-a3b-reasoning`, `nemotron-3-ultra-550b`, `llama-3.2-11b-vision`) are completely free (text only). Use `/model free` to smart-route across them, or pick any by name.
976
986
 
977
987
  ---
978
988