OpenRouter

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

Configure your default workspace here: openrouter.ai/workspaces/def…

Cost management tip💡 Stack multiple inference budgets on a workspace, with different resets:

@jjacky Persistent customization on every site you visit powered by openrouter SDK

Cost simulator lab: x.com/OpenRouter/sta…

Fusion: a compound model agent that achieves Fable-level performance at half the cost. x.com/OpenRouter/sta…

This month is, unsurprisingly, Cost Reduction Month. In our data from the last 3 yrs, we commonly see major cost crunches right after the latest breakthrough. We'll ship major features to help you cut inference costs at least once a week, starting with today. Running list 👇

Try it out here: openrouter.ai/labs/simulate-…

New lab: Cost Simulator A simple tool for looking at your real-world traffic and estimating cost savings with different models, using median endpoint pricing

The first export control on a live AI model came 3 days after this post. New tutorial on how to make your agents robust to model removals and deprecations: openrouter.ai/blog/tutorials…

Read more about it from ZAI: x.com/Zai_org/status…

Use it now: openrouter.ai/z-ai/glm-5.2

GLM-5.2 from @Zai_org is live on OpenRouter! Z.ai's flagship for long-horizon tasks, now with a 1M-token context window capable of being reliable across long, messy coding-agent work.

This is an insane release from OpenRouter, and not just because it's perfect timing. It shows that frontier models alone do not own all the points on the cost-accuracy Pareto curve for knowledge work tasks; in fact they may not be on the Pareto curve at all. The Pareto curve may be defined by a mixture of models, which any independent third-party (e.g. an AI startup) has access to but the model labs do not. It's also surprising because this feature seems extremely horizontal and is not even well-tuned for a specific task. You can prompt the Fusion API with anything. This just means that for any given workflow subset, there's even greater alpha to exploit, by hillclimbing a task-specific benchmark. The more specific the workflow, the more hillclimbing you can do. This should be pretty obvious with a practical example - if you're trying to automate invoice reconciliation at scale, you can be orders of magnitude cheaper and more reliable than "raw" Claude by tuning an agentic workflow with a mixture of models for document extraction, line-item validation, and contract matching. That alpha is what's exploitable by any company out there that's not a frontier lab.

@keeran ❤️

Not seeing a lot / enough about this Fusion implementation on @OpenRouter . Really sounds like the future, or a significant part of it. I’ve done spark -> gpt vs opus -> execplan for gpt loops plenty of times. All the time. It should be automatic.

New Free capacity on OpenRouter, served by @eigenlabs's Darkbloom: gpt-oss-20b and Gemma 4 26B Start using the models today ↓

Sneak peak of the new multimodal Rankings page 👀 Google's Veo 3.1 climbing the video leaderboard

@shashankgoyal95 🐈

Le chaton fat is now #1 on OpenRouter! Need to urgently fix our axes!

If you're a researcher looking to: → conduct rigorous studies on how multiple models can outperform the frontier → leverage data from the largest LLM marketplace (150+ trillion tokens processed per month) ... DM me with your work! We have an exciting role coming in the future, but might fill it opportunistically.

@dtj0108 @opencode Yes! anywhere that supports OpenRouter, which includes OpenCode

@OpenRouter Can you use this with something like Open Code? @opencode @OpenRouter

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

Note: we have only evaluated one deep research benchmark so far, which did not include long-horizon tasks. Fable's long-horizon abilities were extremely impressive, and it calls for future work to benchmark both on long-horizon tasks.

Fusion is neurodiversity, but for models. Try it now! 💬 Chatroom: openrouter.ai/fusion (pick a preset or build a custom panel) ⚙️ API: docs at openrouter.ai/docs/guides/fe… ℹ️ More info on the blog post: openrouter.ai/blog/announcem…