Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions docs/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ description: BlockRun is the routing and payment layer for AI agents — one end

**Agents that pay, spend, and trade.**

BlockRun is economic infrastructure for the agent era. AI agents discover services, pay in USDC over the [x402 protocol](x402/how-it-works.md), and execute autonomously — **no API keys, no subscriptions, no credit card.** One funded wallet unlocks 96 LLMs, media generation, real-time data, and on-chain execution.
BlockRun is economic infrastructure for the agent era. AI agents discover services, pay in USDC over the [x402 protocol](x402/how-it-works.md), and execute autonomously — **no API keys, no subscriptions, no credit card.** One funded wallet unlocks 97 LLMs, media generation, real-time data, and on-chain execution.

:::tip{title="In a hurry?"}
Jump to the [5-Minute Quickstart](getting-started/quickstart.md) and make your first paid call.
Expand Down Expand Up @@ -38,7 +38,7 @@ Pick the path that matches how you work.
::::cards

:::card{title="I want an autonomous agent" href="products/franklin.md" icon="Rocket"}
Franklin — the AI agent with a wallet. Writes code and spends USDC across 96 models and paid APIs. Free to start.
Franklin — the AI agent with a wallet. Writes code and spends USDC across 97 models and paid APIs. Free to start.
:::

:::card{title="I use Claude Code / Cursor" href="getting-started/quickstart.md" icon="Terminal"}
Expand All @@ -62,7 +62,7 @@ Four product families, one payment layer.
::::cards

:::card{title="Intelligence" href="products/intelligence/overview.md" icon="Brain"}
96 LLMs (GPT, Claude, Gemini, DeepSeek, Grok, Kimi, Qwen) through one OpenAI-compatible API. Pay per request.
97 LLMs (GPT, Claude, Gemini, DeepSeek, Grok, Kimi, Qwen) through one OpenAI-compatible API. Pay per request.
:::

:::card{title="Routing" href="products/routing/clawrouter.md" icon="Route"}
Expand Down
4 changes: 2 additions & 2 deletions docs/api-reference/chat-completions.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
title: Chat Completions
description: OpenAI-compatible Chat Completions endpoint for 96 LLMs, paid per request in USDC over x402 — no API keys, no subscriptions.
description: OpenAI-compatible Chat Completions endpoint for 97 LLMs, paid per request in USDC over x402 — no API keys, no subscriptions.
---

# Chat Completions
Expand Down Expand Up @@ -379,7 +379,7 @@ console.log(result.choices[0].message.content);
::::cards

:::card{title="Browse all models" href="models.md" icon="Brain"}
96 chat models with live pricing — pick the right model and ID for your call.
97 chat models with live pricing — pick the right model and ID for your call.
:::

:::card{title="Error handling" href="errors.md" icon="Code"}
Expand Down
2 changes: 1 addition & 1 deletion docs/api-reference/exa-search.md
Original file line number Diff line number Diff line change
Expand Up @@ -393,7 +393,7 @@ Real-time web and news search via Grok Live Search.
:::

:::card{title="Chat Completions" href="chat-completions.md" icon="Brain"}
Feed grounded search results into any of 96 LLMs for synthesis.
Feed grounded search results into any of 97 LLMs for synthesis.
:::

:::card{title="Error handling" href="errors.md" icon="Code"}
Expand Down
3 changes: 2 additions & 1 deletion docs/api-reference/models.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
title: Models
description: List and price 124 models — chat, image, video, music and speech — from one BlockRun API — provider rates, no margin on chat tokens, $0.001 per call.
description: List and price 125 models — chat, image, video, music and speech — from one BlockRun API — provider rates, no margin on chat tokens, $0.001 per call.
---

# Models
Expand Down Expand Up @@ -181,6 +181,7 @@ These models reject all sampling parameters (`temperature`, `top_p`, `top_k`); t

| Model ID | Name | Input Price | Output Price | Context |
|----------|------|-------------|--------------|---------|
| `google/gemini-4-neon` | Gemini 4 Neon | $3.00/M | $15.00/M | 1M |
| `google/gemini-4-carbon` | Gemini 4 Carbon | $2.00/M | $10.00/M | 1M |
| `google/gemini-4-argon` | Gemini 4 Argon | $2.00/M | $10.00/M | 1M |
| `google/gemini-4-hydrogen` | Gemini 4 Hydrogen | $1.50/M | $7.50/M | 1M |
Expand Down
4 changes: 2 additions & 2 deletions docs/frameworks/agentkit.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
title: AgentKit Integration
description: Pair Coinbase AgentKit with BlockRun so your agents both hold on-chain assets and pay per request for 124 AI models.
description: Pair Coinbase AgentKit with BlockRun so your agents both hold on-chain assets and pay per request for 125 AI models.
---

# AgentKit Integration
Expand All @@ -21,7 +21,7 @@ AgentKit provides:
- Framework extensions (`coinbase-agentkit-langchain`, …)

BlockRun adds:
- 96 chat models (121 in the full catalog)
- 97 chat models (121 in the full catalog)
- Pay-per-request intelligence
- No API key management

Expand Down
6 changes: 3 additions & 3 deletions docs/frameworks/elizaos.md
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
---
title: ElizaOS Integration
description: Add the BlockRun plugin to ElizaOS so your agents reach 96 chat models via x402 micropayments — no per-provider API keys.
description: Add the BlockRun plugin to ElizaOS so your agents reach 97 chat models via x402 micropayments — no per-provider API keys.
---

# ElizaOS Integration

Use BlockRun as an LLM provider in ElizaOS agents — one plugin unlocks 96 models paid per request over x402.
Use BlockRun as an LLM provider in ElizaOS agents — one plugin unlocks 97 models paid per request over x402.

:::note{title="Community integration"}
BlockRun's primary paths are [Franklin](../products/franklin.md), the [BlockRun MCP](../mcp/blockrun-mcp.md), and the [SDKs](../sdks/python.md). Framework integrations like this one are community-maintained.
:::

[ElizaOS](https://github.com/elizaOS/eliza) is an open-source agent framework. The BlockRun plugin gives your ElizaOS agents access to 96 chat models via x402 micropayments.
[ElizaOS](https://github.com/elizaOS/eliza) is an open-source agent framework. The BlockRun plugin gives your ElizaOS agents access to 97 chat models via x402 micropayments.

## Setup

Expand Down
6 changes: 3 additions & 3 deletions docs/frameworks/goat.md
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
---
title: GOAT SDK Integration
description: Combine GOAT SDK's cross-chain execution with BlockRun's 124 AI models, paid per request over x402 — until the official plugin ships.
description: Combine GOAT SDK's cross-chain execution with BlockRun's 125 AI models, paid per request over x402 — until the official plugin ships.
---

# GOAT SDK Integration

Use BlockRun with [GOAT SDK](https://github.com/crossmint/goat) (Great Onchain Agent Toolkit) for cross-chain AI agents. GOAT handles blockchain interactions, BlockRun provides AI intelligence via 96 models with x402 micropayments.
Use BlockRun with [GOAT SDK](https://github.com/crossmint/goat) (Great Onchain Agent Toolkit) for cross-chain AI agents. GOAT handles blockchain interactions, BlockRun provides AI intelligence via 97 models with x402 micropayments.

:::note{title="Community integration — pre-release"}
No official `@goat-sdk/plugin-blockrun` yet; use BlockRun alongside GOAT via the [TypeScript SDK](../sdks/typescript.md) as shown below. BlockRun's primary paths are [Franklin](../products/franklin.md), the [MCP](../mcp/blockrun-mcp.md), and the SDKs.
Expand Down Expand Up @@ -129,7 +129,7 @@ const { text } = await generateText({
| GOAT Provides | BlockRun Adds |
|---------------|---------------|
| Cross-chain execution | AI decision making |
| Protocol integrations | 96 chat models (121 total) |
| Protocol integrations | 97 chat models (121 total) |
| Wallet management | Pay-per-request AI |
| Transaction building | No API key hassle |

Expand Down
2 changes: 1 addition & 1 deletion docs/frameworks/langchain.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
title: LangChain Integration
description: Wrap BlockRun in a custom LangChain LLM class that handles x402 payments automatically — chains, agents, and RAG over 96 models.
description: Wrap BlockRun in a custom LangChain LLM class that handles x402 payments automatically — chains, agents, and RAG over 97 models.
---

# LangChain Integration
Expand Down
4 changes: 2 additions & 2 deletions docs/getting-started/agent-developers.md
Original file line number Diff line number Diff line change
@@ -1,13 +1,13 @@
---
title: Agent Developers
description: Build AI agents that pay for their own intelligence — 96 models via x402 micropayments. Use Franklin, the SDKs or the MCP, or the framework you already use.
description: Build AI agents that pay for their own intelligence — 97 models via x402 micropayments. Use Franklin, the SDKs or the MCP, or the framework you already use.
---

# Agent Developers

Build AI agents that pay for their own intelligence.

This guide is for agent developers. The primary paths are **[Franklin](../products/franklin.md)** (our autonomous agent), the **[SDKs](../sdks/python.md)**, and the **[BlockRun MCP](../mcp/blockrun-mcp.md)** — all on one wallet, 96 models via x402 micropayments. Already using a framework (ElizaOS, AgentKit, GOAT, LangChain)? See [Community integrations](../frameworks/elizaos.md).
This guide is for agent developers. The primary paths are **[Franklin](../products/franklin.md)** (our autonomous agent), the **[SDKs](../sdks/python.md)**, and the **[BlockRun MCP](../mcp/blockrun-mcp.md)** — all on one wallet, 97 models via x402 micropayments. Already using a framework (ElizaOS, AgentKit, GOAT, LangChain)? See [Community integrations](../frameworks/elizaos.md).

:::tip{title="Fastest path: Franklin"}
Want an agent that already spends autonomously? [Franklin](../products/franklin.md) is one install (`npm install -g @blockrun/franklin`) and runs free out of the box — fund a wallet to unlock everything.
Expand Down
4 changes: 2 additions & 2 deletions docs/getting-started/claude-code.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
title: Claude Code Users
description: Install BlockRun MCP in Claude Code, fund a wallet with USDC on Base or Solana, and give your agent 96 models, images, and live data.
description: Install BlockRun MCP in Claude Code, fund a wallet with USDC on Base or Solana, and give your agent 97 models, images, and live data.
---

# Claude Code Users
Expand Down Expand Up @@ -272,7 +272,7 @@ Create images via micropayments with `blockrun_image`.
:::

:::card{title="Explore all models" href="../products/intelligence/overview.md" icon="Brain"}
96 LLMs with live pricing, plus smart routing to cut costs automatically.
97 LLMs with live pricing, plus smart routing to cut costs automatically.
:::

::::
2 changes: 1 addition & 1 deletion docs/getting-started/quickstart.md
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,7 @@ The full list of 19 `blockrun_*` tools — chat, image, video, search, markets,
:::

:::card{title="Explore the models" href="../products/intelligence/overview.md" icon="Brain"}
96 LLMs with live pricing, plus smart routing to cut costs automatically.
97 LLMs with live pricing, plus smart routing to cut costs automatically.
:::

:::card{title="How payment works" href="../x402/how-it-works.md" icon="Zap"}
Expand Down
4 changes: 2 additions & 2 deletions docs/mcp/blockrun-mcp.md
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
---
title: BlockRun MCP
description: A Model Context Protocol server that gives Claude Code 96 models, crypto data, voice calls, media generation, and prediction markets with zero API keys.
description: A Model Context Protocol server that gives Claude Code 97 models, crypto data, voice calls, media generation, and prediction markets with zero API keys.
---

# BlockRun MCP

Give Claude Code access to 124 AI models, crypto and DeFi data, voice calls, image/video/music generation, prediction markets (read *and* trade), multi-chain RPC, and a sandbox runtime — all with zero API keys.
Give Claude Code access to 125 AI models, crypto and DeFi data, voice calls, image/video/music generation, prediction markets (read *and* trade), multi-chain RPC, and a sandbox runtime — all with zero API keys.

BlockRun MCP is a Model Context Protocol server that connects Claude Code to BlockRun's intelligence, trading, and creation capabilities.

Expand Down
4 changes: 2 additions & 2 deletions docs/products/franklin.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
title: Franklin Agent
description: Franklin is the AI agent with a wallet. It writes code and spends USDC autonomously across 96 models and paid APIs, settling per outcome over x402. No API keys.
description: Franklin is the AI agent with a wallet. It writes code and spends USDC autonomously across 97 models and paid APIs, settling per outcome over x402. No API keys.
---

# Franklin Agent
Expand Down Expand Up @@ -116,7 +116,7 @@ Inside a session: `/model`, `/plan` / `/execute`, `/ultrathink`, `/compact`, `/c

Franklin is the autonomous agent on top of the BlockRun stack — it uses the same pieces you can use directly:

- **Models & routing** — picks the best model per task via [ClawRouter](routing/clawrouter.md)'s scoring, across 96 chat models. Four profiles: `auto`, `eco`, `premium`, `free`.
- **Models & routing** — picks the best model per task via [ClawRouter](routing/clawrouter.md)'s scoring, across 97 chat models. Four profiles: `auto`, `eco`, `premium`, `free`.
- **Paid APIs** — search, market data, media, RPC, prediction markets and more, paid per call over [x402](../x402/how-it-works.md).
- **One wallet** — the wallet is the identity; fund it on Solana or Base ([Wallet Setup](../getting-started/wallet-setup.md)).

Expand Down
5 changes: 3 additions & 2 deletions docs/products/intelligence/overview.md
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
---
title: Intelligence
description: BlockRun Intelligence gives your agent 96 LLMs through one OpenAI-compatible API, paid per request in USDC — no API keys, no subscriptions.
description: BlockRun Intelligence gives your agent 97 LLMs through one OpenAI-compatible API, paid per request in USDC — no API keys, no subscriptions.
---

# Intelligence

AI accesses any LLM. 96 models, pay-per-request.
AI accesses any LLM. 97 models, pay-per-request.

BlockRun's Intelligence product gives your AI agent access to models from OpenAI, Anthropic, Google, xAI, DeepSeek, Z.AI, Moonshot, MiniMax, and more — without managing API keys or subscriptions.

Expand Down Expand Up @@ -57,6 +57,7 @@ Provider rates per 1M tokens. Since 2026-08-07 these are also the BILLED rates
### Google
| Model | Input | Output |
|-------|-------|--------|
| Gemini 4 Neon | $3.00/M | $15.00/M |
| Gemini 4 Carbon | $2.00/M | $10.00/M |
| Gemini 4 Argon | $2.00/M | $10.00/M |
| Gemini 4 Hydrogen | $1.50/M | $7.50/M |
Expand Down
3 changes: 2 additions & 1 deletion docs/products/intelligence/pricing.md
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,7 @@ How the cached rate reaches an x402 payment depends on the scheme the client sig

| Model | Input (per 1M) | Output (per 1M) | Cached input (per 1M) |
|-------|----------------|-----------------|-----------------------|
| Gemini 4 Neon | $3.00 | $15.00 | $0.15 |
| Gemini 4 Carbon | $2.00 | $10.00 | $0.10 |
| Gemini 4 Argon | $2.00 | $10.00 | $0.10 |
| Gemini 4 Hydrogen | $1.50 | $7.50 | $0.075 |
Expand All @@ -119,7 +120,7 @@ How the cached rate reaches an x402 payment depends on the scheme the client sig
| Gemini 3.1 Flash Lite | $0.25 | $1.50 | $0.025 |
| Gemini 2.5 Flash Lite | $0.10 | $0.40 | $0.01 |

Gemini 4 Carbon and Argon move to $4.00 / $20.00 (cached $0.20) on 2026-12-01; Gemini 4 Hydrogen has no announced change. Gemini 3.1 Pro and 2.5 Pro double the input rate and add 50% to the output rate above 200K prompt tokens (the whole request reprices), mirroring Google's official long-context pricing — e.g. Gemini 2.5 Pro is $2.50 in · $15.00 out above the threshold. Flash tiers are flat.
Gemini 4 Carbon and Argon move to $4.00 / $20.00 (cached $0.20) on 2026-12-01; Gemini 4 Neon and Hydrogen have no announced change. Gemini 3.1 Pro and 2.5 Pro double the input rate and add 50% to the output rate above 200K prompt tokens (the whole request reprices), mirroring Google's official long-context pricing — e.g. Gemini 2.5 Pro is $2.50 in · $15.00 out above the threshold. Flash tiers are flat.

### xAI Grok

Expand Down
6 changes: 3 additions & 3 deletions docs/products/routing/clawrouter.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ description: ClawRouter is a smart LLM router for OpenClaw that picks the optima

**84% cheaper than pinning one flagship for every request — 98% on `eco`. Automatically.**

ClawRouter is a smart LLM router for OpenClaw that routes every request to the cheapest model that can handle it. One wallet, 96 models, zero API keys.
ClawRouter is a smart LLM router for OpenClaw that routes every request to the cheapest model that can handle it. One wallet, 97 models, zero API keys.

:::tip{title="In a hurry?"}
Install, fund a wallet, then run `/model blockrun/auto` in any OpenClaw conversation — that's it. Current release: **v0.12.314** (November 12, 2026).
Expand Down Expand Up @@ -233,7 +233,7 @@ Note the second row: the REASONING primary is DeepSeek Reasoner, but the portfol
- The routing decision runs locally: your prompt is not sent anywhere to choose a model
- The request itself then goes to the BlockRun gateway that serves the chosen model. blockrun.ai (Base) stores request and response content; sol.blockrun.ai (Solana) stores none. Free models run on third-party free tiers whose terms may let the host use prompts, so don't send sensitive data to a free model

### 96 Models
### 97 Models

Access all major providers through one wallet:

Expand Down Expand Up @@ -596,7 +596,7 @@ No. AI model access requires internet. But routing decisions are made locally.
::::cards

:::card{title="View all models" href="../intelligence/overview.md" icon="Brain"}
96 LLMs across OpenAI, Anthropic, Google, xAI, DeepSeek, Z.AI, Moonshot, MiniMax, and the free tier.
97 LLMs across OpenAI, Anthropic, Google, xAI, DeepSeek, Z.AI, Moonshot, MiniMax, and the free tier.
:::

:::card{title="Check pricing" href="../intelligence/pricing.md" icon="Zap"}
Expand Down
6 changes: 6 additions & 0 deletions docs/resources/changelog.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,12 @@ description: All notable changes to BlockRun — gateway endpoints, model lineup

All notable changes to BlockRun, newest first — gateway endpoints, model lineup, pricing, and SDK releases.

## [2026-11-19]

### Added — Gemini 4 Neon
- **`google/gemini-4-neon`** ($3.00/M in · $15.00/M out, cached input $0.15/M, 1M context, 65,536 max output, thinking, vision, tools) — Google's newest Gemini 4, released 2026-11-18, for agentic coding, knowledge work and long-context reasoning. No long-context tier and no announced price change. Multi-round tool calling works, with the thought signatures Gemini 4 requires handled by the gateway. Falls back to `google/gemini-3.1-pro` if its upstream fails and the caller allows fallback.
- Visible chat models are now **97**; total catalog **125**.

## [2026-11-18]

### Changed — A 5% platform fee on pay-per-call chat
Expand Down
2 changes: 1 addition & 1 deletion docs/resources/examples.md
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@ Run any GPT-Image-2 or Seedance prompt as a one-liner — `/headshot`, `/dance`,
:::

:::card{title="lobster.cash skill" href="https://github.com/BlockRunAI/lobstercash-blockrun-skill" icon="Zap"}
BlockRun skill for the lobster.cash OpenClaw plugin — 96 models paid with Solana USDC.
BlockRun skill for the lobster.cash OpenClaw plugin — 97 models paid with Solana USDC.
:::

:::card{title="blockrun-claude-plugin" href="https://github.com/BlockRunAI/blockrun-claude-plugin" icon="Wallet"}
Expand Down
4 changes: 2 additions & 2 deletions docs/resources/faq.md
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ Frequently asked questions about BlockRun — payments, products, models, wallet
BlockRun is economic infrastructure for AI agents. It provides:
- **Trading** — Franklin's built-in trading tools: live signals, paper trading, Polymarket bets, and a trade-plan gate for real money
- **Creation** — generate images, video, music, and speech, paid per output
- **Intelligence** — Access to 96 chat models via x402 micropayments
- **Intelligence** — Access to 97 chat models via x402 micropayments
- **Routing** — ClawRouter picks the cheapest capable model locally, in under 1ms

### What makes BlockRun different?
Expand Down Expand Up @@ -121,7 +121,7 @@ Yes — a flat $0.001 transaction fee on every paid call, which covers on-chain

### Which AI models are available?

96 models including:
97 models including:
- OpenAI (GPT-6 Astra, GPT-6 Sol, GPT-6 Luna, GPT-5.6 Sol, GPT-5.5, GPT-5.4, GPT-5.4 Pro, GPT-5.2)
- Anthropic (Claude Fable 5.2, Fable 5.1, Opus 5.5, Opus 5, Opus 4.8, Sonnet 5.5, Sonnet 5, Sonnet 4.6, Haiku 4.5)
- Google (Gemini 3.1 Pro, Gemini 3.5 Flash)
Expand Down
Loading
Loading