The largest LLM marketplace. 500 models (incl. 50 free), the best prices, explorable data, private chat, & a unified API. openrouter.ai/discord
Joined July 2023
- Tweets 4,951
- Following 378
- Followers 106,369
- Likes 5,521
958 Photos and videos
Pinned Tweet
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
342
875
7,937
1,751,704
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
342
875
7,937
1,751,704
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…
5
12
354
45,576
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.
6
1
135
26,737
You can create your own mythos using fusion
OpenRouter has created a way to take all your favorite models and fuse them into one super smart model
If you're feeling sad after losing Fable, go ahead and give this a shot
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
14
8
110
22,473
Jun 8
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 👇
Jun 8
New server tool: Advisor
Let smaller models consult a higher-intelligence "advisor" model.
Helps them escape doom loops, and helps you migrate to cheaper models! 🧵
8
20
304
49,037
Jun 13
Subagent server tool, allowing powerful models to orchestrate cheaper and faster workers automatically for you. x.com/OpenRouter/status/2065…
Jun 13
New server tool: Subagent 🤖
Your model can now delegate focused sub-tasks to a smaller, cheaper, faster model mid-generation.
The big model orchestrates, the subagent executes. The subagent can use any model on OpenRouter.
2
2
9
6,336
Fusion: a compound model agent that achieves Fable-level performance at half the cost.
x.com/OpenRouter/status/2065…
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
6
2,823
OpenRouter retweeted
We just announced our Fusion API:
- Fable-level performance on deep research tasks, at half the cost
- Better-than-SOTA performance using panels
The future of AI is neurodiversity, not single-model takeovers.
Introducing the Fusion API, the smartest compound model in the market.
Fusion achieves Fable-level intelligence at half the price.
How it works 👇
76
61
781
88,672
Jun 13
New server tool: Subagent 🤖
Your model can now delegate focused sub-tasks to a smaller, cheaper, faster model mid-generation.
The big model orchestrates, the subagent executes. The subagent can use any model on OpenRouter.
12
39
543
34,567
Jun 13
Workers can even run as agents with their own server tools, like web_search, so a delegated task can ground itself in fresh sources before reporting back.
One tool definition, but with zero client-side plumbing. Docs: openrouter.ai/docs/guides/fe…
1
24
3,741
Jun 12
WSJ: OpenRouter provides a bundle of strategies that you can use to reduce inference costs, which our customers use every week. wsj.com/tech/ai/the-ai-price…
Read about what shipped this week in our Cost Reduction Month thread: x.com/OpenRouter/status/2064…
Jun 8
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 👇
4
8
76
10,073
Jun 11
Finally a way to see your top humans & top agents at a glance.
Includes an API to query all your data over time 📊
Jun 10
Today we're launching the new Activity explorer on OpenRouter.
It's the best way to see how much and your team are spending on every model, along with tokens, cache hit rate, agents, & trends. All updated in real time.
See how our team is using Fable and other models 👇
5
3
77
7,580