The largest LLM marketplace. 500+ models (incl. 50+ free), the best prices, explorable data, private chat, & a unified API. openrouter.ai/discord
- Tweets 5,021
- Following 381
- Followers 118,019
- Likes 5,608
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 👇
719
1,791
15,041
6,279,056
Tip: OpenRouter continuously runs GPQA and TAU-Bench on most open-weight models and publishes the results publicly.
This informs our AutoExacto meta-benchmark, used by default when routing tool calls.
Here, @Parasail_io and @Zai_org rank first: openrouter.ai/z-ai/glm-5.2#p…
16
23
322
36,984
Four open-weight models have crossed into territory where they are powering real agentic pipelines.
New post in our Insights blog about why companies are choosing them in June: openrouter.ai/blog/insights/…
45
186
1,676
167,401
OpenRouter retweeted
TIP 💡@Zai_org GLM-5.2 providers are working on faster and faster inference! Today's new endpoints include @wafer_ai and @FireworksAI_HQ fast variants.
Set your model to "z-ai/glm-5.2:nitro" to continuously get the fastest provider based on live traffic data.
23
34
599
65,387
OpenRouter retweeted
Building on the deepest inference market = automatically getting the best price and performance!
TIP 💡@Zai_org GLM-5.2 providers are working on faster and faster inference! Today's new endpoints include @wafer_ai and @FireworksAI_HQ fast variants.
Set your model to "z-ai/glm-5.2:nitro" to continuously get the fastest provider based on live traffic data.
4
4
56
14,940
In this OpenRouter MCP demo, your agent finds the best model at design:
1. Pulls the top design models from @DesignArena, live, through the MCP
2. Spins up three subagents - GLM-5.2, Opus 4.7, Kimi 2.6 - each designing a self-portrait as a webpage
3. Opens all three for you to compare side by side
4. You choose your favorite
diff models are good at diff things, but how many of us actually compare them?
you sign up for each provider separately, load creds, and run the same prompt over and over
it's tedious, so 99% of the time, people just go with what others say is best
there's a better way..
13
13
226
22,402
More info about the new MCP:
Introducing the OpenRouter MCP, live model intelligence right inside your agent
Your agent builds and ships, but when it comes to choosing the right model for the right job, it guesses from 6 month old training data
Watch it pick, price, and test the right model:
2
10
5,287
Example of how to use the OpenRouter MCP to build a model council.
Tuned for your codebase and usecase!
6
4
130
18,848
xAI + Zero Data Retention, now live on OpenRouter. 🔒
Available across Grok 4.3, 4.20 and Build 0.1. Turn on ZDR and you're covered.
Browse Grok ZDR models: openrouter.ai/models?zdr=tru…
16
13
375
23,342
TIP 💡@Zai_org GLM-5.2 providers are working on faster and faster inference! Today's new endpoints include @wafer_ai and @FireworksAI_HQ fast variants.
Set your model to "z-ai/glm-5.2:nitro" to continuously get the fastest provider based on live traffic data.
23
34
599
65,387
See the live provider rankings here: openrouter.ai/z-ai/glm-5.2?t…
8
5,319
Interface + inference, in one place.
@OpenWebUI now runs on OpenRouter.
Give your team one chat interface, one unified bill, and access to 400+ frontier and open models through a single API.
9
15
241
17,129
OpenRouter retweeted
Excited to be speaking at @aiDotEngineer World Fair this year!
Over the past year at @OpenRouter, I've had the opportunity to work closely with model providers and AI builders across the ecosystem, giving me a front-row seat to how production AI is evolving—and where it's headed next.
If you'll be in San Francisco, I'd love to connect.
See you at AI Engineer World's Fair!
3
2
28
3,587
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 👇
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! 🧵
9
23
324
65,454
Official OpenRouter MCP: help your agents pull live data about model pricing, benchmarks, popularity, and more!
Avoid the accidental bad model slug being written into your codebase.
Introducing the OpenRouter MCP, live model intelligence right inside your agent
Your agent builds and ships, but when it comes to choosing the right model for the right job, it guesses from 6 month old training data
Watch it pick, price, and test the right model:
1
7
3,093
OpenRouter retweeted
Design Arena’s benchmarks now help power @OpenRouter’s MCP
Get live model intelligence directly in your agent!
The model performance rankings come from our new Benchmarks API, allowing your agent to query live benchmark scores (incl Artificial Analysis and Design Arena)
Fun result: @Zai_org’s GLM-5.2 is the best available model for both coding & design
Docs: openrouter.ai/docs/api/api-r…
1
6
30
6,103
We’re proud to announce that @DesignArena benchmarks now help power @OpenRouter’s MCP
Openrouter 🤝 DesignArena
The model performance rankings come from our new Benchmarks API, allowing your agent to query live benchmark scores (incl Artificial Analysis and Design Arena)
Fun result: @Zai_org’s GLM-5.2 is the best available model for both coding & design
Docs: openrouter.ai/docs/api/api-r…
1
2
31
7,403
OpenRouter retweeted
"Which model should I use for this?"
Stop your agent from putting Sonnet 4 and GPT-4o everywhere.
The @OpenRouter MCP helps your agent leverage real-time benchmarks, live pricing data, and empirical usage data across the market
Introducing the OpenRouter MCP, live model intelligence right inside your agent
Your agent builds and ships, but when it comes to choosing the right model for the right job, it guesses from 6 month old training data
Watch it pick, price, and test the right model:
5
3
61
8,984
Introducing the OpenRouter MCP, live model intelligence right inside your agent
Your agent builds and ships, but when it comes to choosing the right model for the right job, it guesses from 6 month old training data
Watch it pick, price, and test the right model:
85
201
2,142
242,974
Pick, price, test, and wire in a model in under a minute
Connect in two commands:
claude mcp add --transport http openrouter mcp.openrouter.ai/mcp
claude mcp login openrouter
Works with all your favorite agents
Available now on openrouter.ai/mcp
1
1
60
10,172
The model performance rankings come from our new Benchmarks API, allowing your agent to query live benchmark scores (incl Artificial Analysis and Design Arena)
Fun result: @Zai_org’s GLM-5.2 is the best available model for both coding & design
Docs: openrouter.ai/docs/api/api-r…
2
2
64
22,116