@blockrun/clawrouter 0.12.278 → 0.12.279
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 +30 -30
- package/docs/9-free-ai-models-zero-cost-blockrun.md +5 -5
- package/docs/anthropic-cost-savings.md +1 -1
- package/docs/anthropic-third-party-harness-changes.md +3 -3
- package/docs/clawrouter-cuts-llm-api-costs-500x.md +2 -2
- package/docs/clawrouter-vs-openrouter-llm-routing-comparison.md +3 -3
- package/package.json +4 -8
- package/skills/clawrouter/SKILL.md +3 -3
package/README.md
CHANGED
|
@@ -9,11 +9,11 @@ Agents can only sign transactions.<br><br>
|
|
|
9
9
|
<strong>ClawRouter is the only LLM router that lets agents operate independently.</strong><br><br>
|
|
10
10
|
<em>Pay however you like: <strong>credit card</strong> — sign up at <a href="https://user.blockrun.ai"><strong>user.blockrun.ai</strong></a>, top up, mint an API key<br>
|
|
11
11
|
or <strong>USDC</strong> on Solana or Base (x402 wallet, no account at all).<br>
|
|
12
|
-
Or neither — <!-- br:models.free -->
|
|
12
|
+
Or neither — <!-- br:models.free -->6<!-- /br:models.free --> models are free, with no signup, no key and no wallet.</em></p>
|
|
13
13
|
|
|
14
14
|
<br>
|
|
15
15
|
|
|
16
|
-
<img src="https://img.shields.io/badge/🆓
|
|
16
|
+
<img src="https://img.shields.io/badge/🆓_6_Free_Models-success?style=for-the-badge" alt="6 free models">
|
|
17
17
|
<img src="https://img.shields.io/badge/🤖_Agent--Native-black?style=for-the-badge" alt="Agent native">
|
|
18
18
|
<img src="https://img.shields.io/badge/💳_Card_or_USDC-blue?style=for-the-badge" alt="Card or USDC">
|
|
19
19
|
<img src="https://img.shields.io/badge/⚡_Local_Routing-yellow?style=for-the-badge" alt="Local routing">
|
|
@@ -36,7 +36,7 @@ Or neither — <!-- br:models.free -->7<!-- /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 -->
|
|
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.
|
|
40
40
|
|
|
41
41
|
---
|
|
42
42
|
|
|
@@ -48,8 +48,8 @@ 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 -->
|
|
52
|
-
| **Every tool** | <!-- br:models.image -->
|
|
51
|
+
| **Every LLM** | <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> chat models across 9 providers, behind one endpoint and one balance |
|
|
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 |
|
|
55
55
|
|
|
@@ -65,7 +65,7 @@ Every other LLM router was built for **human developers** — create an account,
|
|
|
65
65
|
|
|
66
66
|
ClawRouter is built for the agent-first world:
|
|
67
67
|
|
|
68
|
-
- **Starts at $0** — <!-- br:models.free -->
|
|
68
|
+
- **Starts at $0** — <!-- br:models.free -->6<!-- /br:models.free --> open-weight models are free forever (incl. a 1M-context reasoner and two sub-second coders). Image turns route to paid models — see the free-tier note below.
|
|
69
69
|
- **No accounts needed** — a wallet is generated locally, no signup
|
|
70
70
|
- **No API keys needed** — your wallet signature IS authentication
|
|
71
71
|
- **No model selection** — <!-- br:clawrouter.dimensions -->15<!-- /br:clawrouter.dimensions -->-dimension scoring + constraint-first ranking ([router-core](https://github.com/BlockRunAI/router-core)) picks the right model automatically
|
|
@@ -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 -->
|
|
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.
|
|
80
80
|
|
|
81
81
|
| You are | Pay with | Setup |
|
|
82
82
|
| ------------------- | --------------------------------------- | ------------------------------------------------------------------------------------------- |
|
|
@@ -92,8 +92,8 @@ 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 -->
|
|
96
|
-
| **Free tier** | Rate-limited | BYO keys | No | No | **<!-- br:models.free -->
|
|
95
|
+
| **Models** | 200+ | 100+ | Smart routing | Gateway | **<!-- br:models.chatVisible -->78<!-- /br:models.chatVisible -->** |
|
|
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** |
|
|
99
99
|
| **Payment** | Credit card | BYO keys | Credit card | $49-499/mo | **USDC per-request _or_ card credit** |
|
|
@@ -109,7 +109,7 @@ Full walkthrough: [Paying with a credit card](#paying-with-a-credit-card-api-key
|
|
|
109
109
|
|
|
110
110
|
## Quick Start
|
|
111
111
|
|
|
112
|
-
> **No wallet? <!-- br:models.free -->
|
|
112
|
+
> **No wallet? <!-- br:models.free -->6<!-- /br:models.free --> models work free out of the box.** Install, run, and pin `free/nemotron-3.5-lightning` (or any of the <!-- br:models.free -->6<!-- /br:models.free -->) — no crypto, no signup, no balance required. Add a credit card or USDC later when you want paid models.
|
|
113
113
|
|
|
114
114
|
**Two ways to pay for the paid ones — pick one, the rest of ClawRouter is identical:**
|
|
115
115
|
|
|
@@ -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 -->
|
|
130
|
+
> one key covers all <!-- br:models.chatVisible -->78<!-- /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 -->
|
|
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.
|
|
175
175
|
|
|
176
176
|
No OpenClaw required. ClawRouter runs as a local proxy on port 8402.
|
|
177
177
|
|
|
@@ -182,7 +182,7 @@ npx @blockrun/clawrouter
|
|
|
182
182
|
```
|
|
183
183
|
|
|
184
184
|
**2. Fund your wallet** — optional, skip for free tier
|
|
185
|
-
Your wallet address is printed on first run. For paid models, send a few USDC on Solana (the default chain) or Base — $5 covers thousands of requests. Prefer a card? [Sign up at user.blockrun.ai](https://user.blockrun.ai) and run `clawrouter login brk_live_…` instead. To stay at $0, pin any of the <!-- br:models.free -->
|
|
185
|
+
Your wallet address is printed on first run. For paid models, send a few USDC on Solana (the default chain) or Base — $5 covers thousands of requests. Prefer a card? [Sign up at user.blockrun.ai](https://user.blockrun.ai) and run `clawrouter login brk_live_…` instead. To stay at $0, pin any of the <!-- br:models.free -->6<!-- /br:models.free --> free models (e.g. `free/nemotron-3.5-lightning`) or use `/model free` inside OpenClaw.
|
|
186
186
|
|
|
187
187
|
**3. Point your client at `http://localhost:8402`**
|
|
188
188
|
|
|
@@ -482,7 +482,7 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
|
|
|
482
482
|
|
|
483
483
|
## Models & Pricing
|
|
484
484
|
|
|
485
|
-
<!-- br:models.chatVisible -->
|
|
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.**
|
|
486
486
|
|
|
487
487
|
> **💡 "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
488
|
|
|
@@ -575,7 +575,7 @@ No Surf account, no API key — settles directly to Surf's Base treasury in USDC
|
|
|
575
575
|
| openai/gpt-5.4-pro | $30.00 | $180.00 | $0.1050 | 400K | reasoning, tools |
|
|
576
576
|
| openai/gpt-5.5-pro | $30.00 | $180.00 | $0.1050 | 1M | reasoning, vision, tools |
|
|
577
577
|
|
|
578
|
-
> **Free tier:** <!-- br:models.free -->
|
|
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).
|
|
579
579
|
>
|
|
580
580
|
> **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
581
|
> **Best value:** `gpt-5-nano` and `gemini-2.5-flash-lite` deliver strong results at ~$0.0003/request.
|
|
@@ -718,7 +718,7 @@ chains, the response cache and the local spend controls.
|
|
|
718
718
|
- **Balance lives server-side.** There is no local balance to check: a call that
|
|
719
719
|
outruns your credit comes back as HTTP `402 insufficient_quota`, naming the
|
|
720
720
|
top-up page. Free models stay free and need no credit at all — all
|
|
721
|
-
<!-- br:models.free -->
|
|
721
|
+
<!-- br:models.free -->6<!-- /br:models.free --> are served on the API-key gateway too.
|
|
722
722
|
- **One key covers nearly everything.** Verified live against `api.blockrun.ai`
|
|
723
723
|
on 2026-09-05: chat completions (`/v1/chat/completions`), the Anthropic-shaped
|
|
724
724
|
`/v1/messages`, `/v1/models`, image generation, speech, video, and the partner
|
|
@@ -871,7 +871,7 @@ npm test
|
|
|
871
871
|
|
|
872
872
|
**The LLM router built for autonomous agents**
|
|
873
873
|
|
|
874
|
-
You're here. <!-- br:models.chatVisible -->
|
|
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.
|
|
875
875
|
|
|
876
876
|
`curl -fsSL https://blockrun.ai/ClawRouter-update | bash`
|
|
877
877
|
|
|
@@ -882,7 +882,7 @@ You're here. <!-- br:models.chatVisible -->76<!-- /br:models.chatVisible --> mod
|
|
|
882
882
|
|
|
883
883
|
**BlockRun for Claude Code**
|
|
884
884
|
|
|
885
|
-
Run Claude Code with <!-- br:models.chatVisible -->
|
|
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.
|
|
886
886
|
|
|
887
887
|
`curl -fsSL https://blockrun.ai/brcc-install | bash`
|
|
888
888
|
|
|
@@ -895,7 +895,7 @@ Run Claude Code with <!-- br:models.chatVisible -->76<!-- /br:models.chatVisible
|
|
|
895
895
|
|
|
896
896
|
**ClawRouter for NousResearch Hermes**
|
|
897
897
|
|
|
898
|
-
Python plugin that wraps the ClawRouter proxy for `hermes-agent`. Same <!-- br:models.chatVisible -->
|
|
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.
|
|
899
899
|
|
|
900
900
|
`pip install hermes-plugin-clawrouter`
|
|
901
901
|
|
|
@@ -912,15 +912,15 @@ Python plugin that wraps the ClawRouter proxy for `hermes-agent`. Same <!-- br:m
|
|
|
912
912
|
|
|
913
913
|
## More Resources
|
|
914
914
|
|
|
915
|
-
| Resource | Description
|
|
916
|
-
| ------------------------------------------------------ |
|
|
917
|
-
| [Documentation](https://blockrun.ai/docs) | Full docs
|
|
918
|
-
| [Model Pricing](https://blockrun.ai/models) | All models & prices
|
|
919
|
-
| [Image Generation & Editing](docs/image-generation.md) | API examples, <!-- br:models.image -->
|
|
920
|
-
| [Routing Profiles](docs/routing-profiles.md) | ECO/AUTO/PREMIUM/AGENTIC tiers, fallback chains, ranking weights
|
|
921
|
-
| [Architecture](docs/architecture.md) | Technical deep dive
|
|
922
|
-
| [Configuration](docs/configuration.md) | Environment variables
|
|
923
|
-
| [Troubleshooting](docs/troubleshooting.md) | Common issues
|
|
915
|
+
| Resource | Description |
|
|
916
|
+
| ------------------------------------------------------ | ------------------------------------------------------------------------ |
|
|
917
|
+
| [Documentation](https://blockrun.ai/docs) | Full docs |
|
|
918
|
+
| [Model Pricing](https://blockrun.ai/models) | All models & prices |
|
|
919
|
+
| [Image Generation & Editing](docs/image-generation.md) | API examples, <!-- br:models.image -->12<!-- /br:models.image --> models |
|
|
920
|
+
| [Routing Profiles](docs/routing-profiles.md) | ECO/AUTO/PREMIUM/AGENTIC tiers, fallback chains, ranking weights |
|
|
921
|
+
| [Architecture](docs/architecture.md) | Technical deep dive |
|
|
922
|
+
| [Configuration](docs/configuration.md) | Environment variables |
|
|
923
|
+
| [Troubleshooting](docs/troubleshooting.md) | Common issues |
|
|
924
924
|
|
|
925
925
|
### Blog
|
|
926
926
|
|
|
@@ -939,7 +939,7 @@ Python plugin that wraps the ClawRouter proxy for `hermes-agent`. Same <!-- br:m
|
|
|
939
939
|
|
|
940
940
|
### What is BlockRun?
|
|
941
941
|
|
|
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 -->
|
|
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.
|
|
943
943
|
|
|
944
944
|
### What is ClawRouter?
|
|
945
945
|
|
|
@@ -967,7 +967,7 @@ No. A wallet is the default because it is what lets an _agent_ pay for itself,
|
|
|
967
967
|
but you can sign up at **[user.blockrun.ai](https://user.blockrun.ai)**, top up
|
|
968
968
|
with a credit card, mint an API key and run `clawrouter login brk_live_…`. Calls
|
|
969
969
|
then go to `api.blockrun.ai` on a bearer token and bill your account credit — no
|
|
970
|
-
crypto, no gas, no seed phrase. And the <!-- br:models.free -->
|
|
970
|
+
crypto, no gas, no seed phrase. And the <!-- br:models.free -->6<!-- /br:models.free --> free models need neither: no
|
|
971
971
|
wallet, no key, no signup. See [Paying with a credit card](#paying-with-a-credit-card-api-key).
|
|
972
972
|
|
|
973
973
|
### Is ClawRouter free?
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
# 9 Free AI Models, Zero Cost: How BlockRun Gives Developers Top-Tier LLMs for Nothing
|
|
2
2
|
|
|
3
3
|
> **The count in this title is a snapshot, and so is every model name below.**
|
|
4
|
-
> It was 9 when this was written; the published free tier is <!-- br:models.free -->
|
|
4
|
+
> It was 9 when this was written; the published free tier is <!-- br:models.free -->6<!-- /br:models.free --> today, and _none_ of the
|
|
5
5
|
> nine originals is still in it. Free hosting is volatile — NVIDIA retired four
|
|
6
6
|
> of the five visible free models in a single sweep on 2026-08-30 — so the tier
|
|
7
7
|
> gets rebuilt rather than topped up. The URL keeps its original slug so existing
|
|
@@ -23,7 +23,7 @@ BlockRun's answer: just take them.
|
|
|
23
23
|
|
|
24
24
|
---
|
|
25
25
|
|
|
26
|
-
## The Lineup: <!-- br:models.free -->
|
|
26
|
+
## The Lineup: <!-- br:models.free -->6<!-- /br:models.free --> Models, $0.00
|
|
27
27
|
|
|
28
28
|
Through [ClawRouter](https://github.com/BlockRunAI/ClawRouter) — BlockRun's local AI routing proxy — you get zero-cost access to the following (verified live 2026-08-30):
|
|
29
29
|
|
|
@@ -244,13 +244,13 @@ Look at the cost trajectory over the past three years:
|
|
|
244
244
|
- **2023:** GPT-4 dominates alone at $30/$60 per M tokens
|
|
245
245
|
- **2024:** Open-source models surge, prices halve repeatedly
|
|
246
246
|
- **2025:** DeepSeek, Qwen push top-tier inference below $1/M
|
|
247
|
-
- **2026:** BlockRun offers <!-- br:models.free -->
|
|
247
|
+
- **2026:** BlockRun offers <!-- br:models.free -->6<!-- /br:models.free --> free models through a single API
|
|
248
248
|
|
|
249
249
|
**A free tier that gets rebuilt rather than retired isn't just a product feature — it's a signal.** Baseline AI capability is becoming infrastructure. Like internet bandwidth before it, the cost of "good enough" AI inference is converging toward zero.
|
|
250
250
|
|
|
251
251
|
BlockRun and ClawRouter exist to be the **routing layer** in this transition: not locked to any single provider, not bound to any single model, always giving developers the lowest-cost path to the right capability.
|
|
252
252
|
|
|
253
|
-
Today it's <!-- br:models.free -->
|
|
253
|
+
Today it's <!-- br:models.free -->6<!-- /br:models.free --> free models, and they are not the same seven as last month. Tomorrow it could be 50. Prices will only drop. Capabilities will only improve. The names will keep churning.
|
|
254
254
|
|
|
255
255
|
**The one constant: your code doesn't need to change.**
|
|
256
256
|
|
|
@@ -265,7 +265,7 @@ clawrouter start
|
|
|
265
265
|
|
|
266
266
|
Point your `base_url` to `http://localhost:8402/v1`. That's the whole setup.
|
|
267
267
|
|
|
268
|
-
<!-- br:models.free -->
|
|
268
|
+
<!-- br:models.free -->6<!-- /br:models.free --> free models. Up to 1M context. Unlimited calls. Zero cost.
|
|
269
269
|
|
|
270
270
|
Go build something.
|
|
271
271
|
|
|
@@ -50,7 +50,7 @@ This is where you're paying for real value:
|
|
|
50
50
|
|
|
51
51
|
## The Solution: ClawRouter
|
|
52
52
|
|
|
53
|
-
[ClawRouter](https://github.com/BlockRunAI/ClawRouter) is an open-source local proxy that sits between your app and <!-- br:models.chatVisible -->
|
|
53
|
+
[ClawRouter](https://github.com/BlockRunAI/ClawRouter) is an open-source local proxy that sits between your app and <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> AI models. It saves you money in three ways: **smart routing**, **token optimization**, and **response caching**.
|
|
54
54
|
|
|
55
55
|
```
|
|
56
56
|
┌─────────────┐ ┌──────────────────────────────┐ ┌──────────────────┐
|
|
@@ -31,7 +31,7 @@ This is exactly the problem [ClawRouter](https://github.com/BlockRunAI/ClawRoute
|
|
|
31
31
|
|
|
32
32
|
## ClawRouter: Smart Routing for Agents
|
|
33
33
|
|
|
34
|
-
ClawRouter is an open-source local proxy that sits between your agent and <!-- br:models.chatVisible -->
|
|
34
|
+
ClawRouter is an open-source local proxy that sits between your agent and <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> LLM models across 9 providers. It analyzes every request across 15 dimensions and routes it to the cheapest model that can handle it — in under 1ms, entirely locally.
|
|
35
35
|
|
|
36
36
|
```
|
|
37
37
|
Your Agent → ClawRouter (localhost:8402) → Best model for the job
|
|
@@ -74,12 +74,12 @@ Then point your agent at `http://localhost:8402/v1/` with any OpenAI-compatible
|
|
|
74
74
|
|
|
75
75
|
- **No API keys to manage** — wallet-based cryptographic auth
|
|
76
76
|
- **No subscriptions** — pay per request in USDC (Base or Solana)
|
|
77
|
-
- **No vendor lock-in** — <!-- br:models.chatVisible -->
|
|
77
|
+
- **No vendor lock-in** — <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models, switch anytime
|
|
78
78
|
- **You control your wallet** — non-custodial, funds never held by a third party
|
|
79
79
|
- **Budget caps** — set a max spend per session, ClawRouter gracefully downgrades when budget runs low
|
|
80
80
|
- **Token compression** — 7-layer pipeline reduces token costs by 7–40% before they hit any provider
|
|
81
81
|
- **Response caching** — identical requests within 10 minutes cost $0
|
|
82
|
-
- **<!-- br:models.free -->
|
|
82
|
+
- **<!-- br:models.free -->6<!-- /br:models.free --> free models** — for tasks that don't need a paid model at all
|
|
83
83
|
|
|
84
84
|
### Routing Profiles
|
|
85
85
|
|
|
@@ -135,7 +135,7 @@ Less context repeated = fewer tokens = lower cost. Agents that need to recall ea
|
|
|
135
135
|
|
|
136
136
|
### 7. x402 Micropayments — Wallet-Based Budget Control
|
|
137
137
|
|
|
138
|
-
<p align="center"><img src="assets/blockrun-clawrouter-x402-usdc-micropayment-wallet-budget-control.png" alt="Budget limits enforced by physical construction — wallet loaded via Base/Solana, pay per call across <!-- br:models.chatVisible -->
|
|
138
|
+
<p align="center"><img src="assets/blockrun-clawrouter-x402-usdc-micropayment-wallet-budget-control.png" alt="Budget limits enforced by physical construction — wallet loaded via Base/Solana, pay per call across <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models, balance hits zero and the valve shuts cleanly" width="720"></p>
|
|
139
139
|
|
|
140
140
|
ClawRouter pays for inference via [x402](https://x402.org/) USDC micropayments (Base or Solana). You load a wallet. Each inference call costs exactly what it costs. When the wallet runs low, requests stop cleanly.
|
|
141
141
|
|
|
@@ -144,7 +144,7 @@ There is no monthly invoice. There is no 3am email. There is a wallet balance, a
|
|
|
144
144
|
**`maxCostPerRun`** — a per-session cost ceiling that stops or downgrades requests once a session exceeds a configured threshold (e.g., `$0.50`). This closes the remaining gap ([#3181](https://github.com/openclaw/openclaw/issues/3181)) where a wallet with sufficient funds can still accumulate within a single run. Two modes: `graceful` (downgrade to cheaper models) and `strict` (hard 429 once the cap is hit).
|
|
145
145
|
|
|
146
146
|
```
|
|
147
|
-
<!-- br:models.chatVisible@live -->
|
|
147
|
+
<!-- br:models.chatVisible@live -->78<!-- /br:models.chatVisible@live --> models. One wallet. Pay per call.
|
|
148
148
|
```
|
|
149
149
|
|
|
150
150
|
---
|
|
@@ -222,7 +222,7 @@ OpenRouter doesn't always pass through provider-specific features correctly. Ima
|
|
|
222
222
|
|
|
223
223
|
**Direct provider routing.** ClawRouter routes through BlockRun's API directly to providers — not through a second aggregator. One hop, not two. Provider-specific features work because there's no middleman translating them.
|
|
224
224
|
|
|
225
|
-
|
|
226
226
|
|
|
227
227
|
---
|
|
228
228
|
|
|
@@ -240,7 +240,7 @@ When new models launch, OpenRouter's catalog lags. Users configure a model that
|
|
|
240
240
|
|
|
241
241
|
### How ClawRouter Solves This
|
|
242
242
|
|
|
243
|
-
ClawRouter maintains a curated catalog of <!-- br:models.chatVisible -->
|
|
243
|
+
ClawRouter maintains a curated catalog of <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models across 9 providers (including <!-- br:models.free -->6<!-- /br:models.free --> free models), updated with each release. Delisted models have automatic redirect aliases:
|
|
244
244
|
|
|
245
245
|
```typescript
|
|
246
246
|
// Delisted models redirect automatically
|
|
@@ -268,7 +268,7 @@ No silent drops. No stale catalog. Models are benchmarked for speed, quality, an
|
|
|
268
268
|
| **Rate limits** | Per-key, shared | Per-wallet, independent |
|
|
269
269
|
| **Vision support** | Images sometimes dropped | Auto-detected, vision-only fallback |
|
|
270
270
|
| **Tool calling** | Silent failures with some models | Flag-based filtering, guaranteed support |
|
|
271
|
-
| **Model catalog** | Laggy, silent drops | Curated <!-- br:models.chatVisible -->
|
|
271
|
+
| **Model catalog** | Laggy, silent drops | Curated <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models, redirect aliases |
|
|
272
272
|
| **Budget control** | Monthly invoice | Per-session cap (`maxCostPerRun`) |
|
|
273
273
|
| **Setup** | Create account, paste key | Agent generates wallet, auto-configured |
|
|
274
274
|
| **Average cost** | $25/M tokens (Opus direct) | auto-routed = **<!-- br:savings.autoVsBaselinePct -->84<!-- /br:savings.autoVsBaselinePct -->% savings** |
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@blockrun/clawrouter",
|
|
3
|
-
"version": "0.12.
|
|
4
|
-
"description": "Smart LLM router — save 84% on inference costs.
|
|
3
|
+
"version": "0.12.279",
|
|
4
|
+
"description": "Smart LLM router — save 84% on inference costs. 78 models (6 free). Pay by credit card (API key) or USDC (x402 wallet).",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
7
7
|
"types": "dist/index.d.ts",
|
|
@@ -129,19 +129,15 @@
|
|
|
129
129
|
"overrides": {
|
|
130
130
|
"axios": "$axios",
|
|
131
131
|
"undici": "$undici",
|
|
132
|
-
"basic-ftp": "^5.3.1",
|
|
133
132
|
"ws": "^8.21.2",
|
|
134
133
|
"postcss": "^8.5.25",
|
|
135
134
|
"esbuild": "^0.28.1",
|
|
136
135
|
"brace-expansion": "^5.0.9",
|
|
137
136
|
"fast-uri": "^3.1.5",
|
|
138
137
|
"tar": "^7.5.22",
|
|
139
|
-
"hono": "^4.13.
|
|
138
|
+
"hono": "^4.13.5",
|
|
140
139
|
"@hono/node-server": "^2.1.0",
|
|
141
|
-
"ip-address": "^10.4.0"
|
|
142
|
-
"jayson": {
|
|
143
|
-
"uuid": "^11.1.1"
|
|
144
|
-
}
|
|
140
|
+
"ip-address": "^10.4.0"
|
|
145
141
|
},
|
|
146
142
|
"engines": {
|
|
147
143
|
"node": ">=22"
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: clawrouter
|
|
3
|
-
description: Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across
|
|
3
|
+
description: Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 78 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data (global stocks, crypto, FX, commodities), Twitter/X intelligence, prediction-market data across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + UMA oracle resolution + wallet identity & clustering, phone-number intelligence (carrier + SIM-swap fraud detection) plus AI-powered outbound voice calls (Twilio + Bland.ai), AND the Surf unified crypto data API (84 endpoints — CEX/DEX, on-chain SQL over 80+ ClickHouse tables, 100M+ labeled wallets, prediction markets, social/CT mindshare, news, VC fund intel) as built-in agent tools. Not a local-inference tool — prompts are sent to the blockrun.ai gateway.
|
|
4
4
|
triggers:
|
|
5
5
|
- "clawrouter"
|
|
6
6
|
- "claw router"
|
|
@@ -53,7 +53,7 @@ metadata:
|
|
|
53
53
|
|
|
54
54
|
# ClawRouter
|
|
55
55
|
|
|
56
|
-
Hosted-gateway LLM router that saves <!-- br:savings.autoVsBaselinePct -->84<!-- /br:savings.autoVsBaselinePct -->% on inference costs by forwarding each request to the blockrun.ai gateway, which picks the cheapest model capable of handling it across <!-- br:models.chatVisible -->
|
|
56
|
+
Hosted-gateway LLM router that saves <!-- br:savings.autoVsBaselinePct -->84<!-- /br:savings.autoVsBaselinePct -->% on inference costs by forwarding each request to the blockrun.ai gateway, which picks the cheapest model capable of handling it across <!-- br:models.chatVisible -->78<!-- /br:models.chatVisible --> models from 9 providers (<!-- br:models.free -->6<!-- /br:models.free --> free open-weight models). All billing flows through one BlockRun credential — either a USDC wallet paying x402 per call, or a BlockRun API key drawing on card-funded account credit. Either way you do not hold provider API keys.
|
|
57
57
|
|
|
58
58
|
**This is not a local-inference tool.** ClawRouter is a thin local proxy. Your prompts are sent over HTTPS to the blockrun.ai gateway for model execution. If your workload requires inference that never leaves your machine, use a local runtime like Ollama — ClawRouter is not the right tool for that use case.
|
|
59
59
|
|
|
@@ -147,7 +147,7 @@ it against a baseline nobody wrote down. See
|
|
|
147
147
|
|
|
148
148
|
## Available Models
|
|
149
149
|
|
|
150
|
-
<!-- br:models.chatVisible -->
|
|
150
|
+
<!-- br:models.chatVisible -->78<!-- /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 [Anthropic flagship, 1M ctx], claude-opus-4.8, claude-opus-4.7, claude-opus-4.5, 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-4.5, 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, hy3 [Tencent], mimo [Xiaomi MiMo-V2.5 Pro, 1M ctx], and 7 free open-weight models (nemotron-3.5-lightning [1M ctx, thinking mode — the free default], nemotron-3-nano-30b [fastest, ~121 tok/s], 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
|
|