@blockrun/franklin 3.15.64 → 3.15.65

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.
@@ -192,7 +192,7 @@ You run on the BlockRun AI Gateway. When the user asks you to "test the BlockRun
192
192
  - \`GET /.well-known/x402\` — x402 resource list with prices
193
193
 
194
194
  **LLM (POST, x402-paid)**
195
- - \`POST /v1/chat/completions\` — OpenAI-compatible. Body: \`{ model, messages, stream?, tools?, max_tokens?, temperature? }\`. \`model\` MUST come from \`GET /v1/models\` (e.g. \`anthropic/claude-sonnet-4.6\`, \`openai/gpt-5.1\`, \`xai/grok-5\`). Wrong model name 400 with the valid list in the error body.
195
+ - \`POST /v1/chat/completions\` — OpenAI-compatible. Body: \`{ model, messages, stream?, tools?, max_tokens?, temperature? }\`. \`model\` MUST come from \`GET /v1/models\` (real frontier examples on the gateway as of 2026-05: \`anthropic/claude-sonnet-4.6\`, \`anthropic/claude-opus-4.7\`, \`deepseek/deepseek-v4-pro\`, \`zai/glm-5.1\`, \`nvidia/qwen3-coder-480b\`, \`openai/gpt-5-nano\`). Do NOT invent versions like \`openai/gpt-5.1\` or \`xai/grok-5\` those don't exist; the gateway 400s with the valid list in the error body, so when in doubt fetch \`GET /v1/models\` first.
196
196
  - \`POST /v1/messages\` — Anthropic-compatible. Body: \`{ model, messages, max_tokens, system?, tools? }\`.
197
197
 
198
198
  **Media (POST, x402-paid; GET to poll async jobs)**
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@blockrun/franklin",
3
- "version": "3.15.64",
3
+ "version": "3.15.65",
4
4
  "description": "Franklin — The AI agent with a wallet. Spends USDC autonomously to get real work done. Pay per action, no subscriptions.",
5
5
  "type": "module",
6
6
  "exports": {