RT @pingToven: the provider operations team at openrouter is absolutely cooking on automations. 727 new endpoints added in august alone, 23…

0 3

在 X 上查看 →

Apply here: https://jobs.ashbyhq.com/openrouter/44ef374e-b234-4d77-b002-8b38b4fda18f Share proof of exceptionality and creativity: communities you've built, events you've run, things you made that people loved.

3 0

在 X 上查看 →

We're hiring a Community Lead. Our Discord has 60k+ members and is one of the most active AI communities anywhere. We're looking for its primary steward: run events and challenges, build our mod and ambassador programs, and bring what the community cares about back to the team.

55 2

在 X 上查看 →

On pricing: Fable 5.1 keeps Fable 5 pricing at $10/M input tokens and $50/M output tokens. Prompt cache reads drop to $0.25/M tokens, 75% below the old cache-read rate. Read more:

17 0

在 X 上查看 →

Claude Fable 5.1 from @AnthropicAI is live on OpenRouter. A direct upgrade for Fable 5 workloads, with the biggest gains in agentic coding, long-running workflows, visual code generation, finance, and analysis. Try it: https://openrouter.ai/anthropic/claude-fable-5.1

313 18

在 X 上查看 →

Scaffold the project and run the batch: $ render workflows init --language node $ render workflows start runPromptBatch Node and Python, local dev through render workflows dev, deploy with render workflows create. Read more at: https://openrouter.ai/docs/guides/community/render

4 1

在 X 上查看 →

Each run calls Auto Router with openrouter/auto, and every result keeps completion.model, so you can see which model OpenRouter picked for each prompt. One caveat worth knowing: a retry can repeat a billable call if the first request succeeded but the task failed before

3 0

在 X 上查看 →

Render provisions compute for those runs on demand and deprovisions it when they finish, so the fan-out needs no pre-provisioned worker pool.

4 0

在 X 上查看 →

A web service has to hold an HTTP request open for the whole batch. A Workflow task keeps running after that request ends, retries on its own, and fans out one run per prompt, so a single slow call never blocks the rest.

4 0

在 X 上查看 →

OpenRouter now runs inside @render Workflows. Stop putting LLM batches in your web service. Each prompt becomes its own task run, queued, retried, and fanned out by Render, with the model call routed by OpenRouter.

0:13

98 12

在 X 上查看 →

Browse image benchmarks here: https://openrouter.ai/benchmarks/media/images

2 0

在 X 上查看 →

Tip 💡 browse image models in our benchmark explorer and quickly edit the prompt in your agent, or in the Chatroom

0:41

44 2

在 X 上查看 →

2/ Use it now: https://openrouter.ai/inception/mercury-2.5-preview

48 2

在 X 上查看 →

1/ The fastest reasoning LLM is now live exclusively on OpenRouter. Mercury 2.5 Preview from @_inception_ai reaches 1,107 tokens/sec through parallel token generation, with tunable reasoning, parallel tool calls, and schema-aligned JSON. Built for latency-sensitive workloads.

0:06

508 27

在 X 上查看 →

TIP 💡: Check https://openrouter.ai/docs/guides/ori/changelog to see everything that's new with Ori TUI, Ori Harness, and Ori Eval:

32 3

在 X 上查看 →

RT @jjacky: jesus christ i implore you to run ori eval inside devin and setup an automation to re-run it every month to always be using…

0 14

在 X 上查看 →

GLM-5.3 from @Zai_org is now open-weight and live on OpenRouter. Built for complex software engineering, long-horizon agents, and cybersecurity, with 1M context and configurable reasoning effort. Try it: https://openrouter.ai/z-ai/glm-5.3

307 13

在 X 上查看 →

Elaboration on the headline figure: - Luna grew by 13.8x - Terra by 5.6x - Sol by 1.1x

47 0

在 X 上查看 →

More insights on the impact of these discounts in the full piece: https://openrouter.ai/blog/insights/gpt-5-6-discounts-jevons-paradox/

27 1

在 X 上查看 →

Importantly, many of the users with Terra/Luna usage during the discount window kept using the models after the discounts were retired. Overall tokens post-discount were actually higher on a daily average basis than during the window (mostly thanks to a few whales)

64 0

在 X 上查看 →

Some of the additional tokens were from older OpenAI models. But the bulk of the increase were net new tokens + stealing share from competitors.

89 0

在 X 上查看 →

What happened when GPT 5.6 Terra and Luna were heavily discounted on OpenRouter? Token usage exploded by 13.8x Jevons Paradox = as technology makes the use of a resource more efficient, total consumption of that resource increases rather than decreases 🧵

1.7K 146

在 X 上查看 →

RT @koblovinamerica: I'm excited to share that after an incredibly fulfilling 6.5 years of building @tryramp, I've joined @OpenRouter as VP…

0 13

在 X 上查看 →

RT @alexatallah: Excited to welcome Nik Koblov to OpenRouter as our head of engineering! Nik previously led engineering through hypergrowt…

0 10

在 X 上查看 →