LiteLLM vs OpenRouter

Auto Router: 45% Lower Cost on 25 SWE-bench Tasks

We solved 23 of 25 SWE-bench Verified tasks with LiteLLM's experimental capability router for $11.15, compared with $20.27 using Opus 5.

Introducing LiteLLM Fusion: 56% More Tasks Solved Than Fable 5

LiteLLM Auto Router Fusion ran three models on the same task and synthesized their work, solving 14 of 21 Terminal-Bench tasks against 9 for Claude Fable-5 alone. Total spend rose 36%, cost per solved task fell 12%, and turn latency went up 5x.

Configure LiteLLM as Codex Model Provider

A developer guide demonstrating how to route Codex to use LiteLLM as a custom model provider. The post explains exposing a LiteLLM API key as an OS environment variable, updating Codex's .codex/config.toml to set model_provider to 'litellm' and add provider-specific fields (base_url, env_key, wire_api, streaming options), setting optional custom HTTP headers, and noting that session models are fixed at session creation. The author also advises verifying usage via LiteLLM dashboard logs and links to LiteLLM and Codex documentation for reference.

• Author Julia Shevchenko published a how-to on dev.to on 2026-08-28 about configuring LiteLLM as a gateway for Codex.
• LiteLLM exposes an OpenAI-compatible interface and can act as a gateway for LLMs.
• Required steps include setting LITELLM_API_KEY as an OS environment variable and updating .codex/config.toml to set model_provider = "litellm" and provider-specific settings (base_url, env_key, wire_api, streaming options).

Open-weight AI models gain production traction

The article discusses the shift in the AI industry from closed to open-weight models, citing that in August 2026, open models processed 56% of tokens on Vercel's AI Gateway, up from 7% in December 2025, and about 60% of US-originating token consumption on OpenRouter. While closed models still lead at the frontier, open weights are becoming part of production infrastructure. The piece introduces the concept of 'open escape velocity', where open AI develops independent sources of demand and infrastructure, reducing dependence on any single model company. However, the content is largely paywalled, and the full analysis and data are not accessible.

• Open-weight models processed 56% of all tokens on Vercel's AI Gateway in August 2026, up from 7% in December 2025.
• OpenRouter reported open models accounting for roughly 60% of US-originating token consumption in the same period.
• DeepSeek demonstrated that open-weight models can compete on cost, capability, and deployability.

Stripe on Agentic Commerce: Can AI Agents Buy From You?

The article discusses a conversation between the author and Emily Sands, Stripe's Head of Data & AI, about the challenges of agentic commerce. It highlights a case where Cursor faced issues with AI agents abusing free trials, which Stripe's fraud detection (Radar) couldn't handle. The discussion explores how fraud rules are distribution decisions, the role of spending limits, and why Stripe acquired OpenRouter to better understand task costs. The article also touches on pricing strategies for AI agents and introduces a library MCP for subscribers.

• Stripe's Emily Sands discussed agentic commerce challenges with the author.
• Cursor complained that Stripe's Radar fraud detection couldn't handle AI agents abusing free trials.
• Stripe acquired OpenRouter to connect task costs to earnings.

Moonshot AI targets $2B annualized revenue after K3 success

Chinese AI lab Moonshot AI, maker of the Kimi assistant, is targeting $2 billion in annualized revenue by the end of 2026, doubling its August run rate. The goal reflects the strong performance of its open-weight K3 model, which generates up to 300 billion tokens daily on OpenRouter. However, Moonshot faces allegations from Anthropic of running a model distillation campaign, using Kimi to route requests to Claude Opus and collecting over 23 million responses for training. Despite controversy, Moonshot's projections show the commercial viability of open-weight models, though margins remain lower than closed-weight rivals like OpenAI and Anthropic, whose annualized revenues are reported at $40 billion and $65 billion respectively.

• Moonshot AI targets $2 billion annualized revenue by end of 2026, double its August run rate.
• K3 model generates up to 300 billion tokens daily on OpenRouter.
• Anthropic accuses Moonshot of running a model distillation campaign, collecting over 23 million responses.