The unified interface for LLMs. 400+ models (incl. 50+ free), the best prices, explorable data, private chat, & a unified API. openrouter.ai/discord
- Tweets 5,818
- Following 387
- Followers 155,197
- Likes 5,998
Agentic usage is up 34x since the start of February 2026.
Agentic usage is also now about 8x higher than human usage across OpenRouter on a weekly basis.
10
8
77
7,238
Voxtral TTS 3: voices that adjust emotion, pace and emphasis to the conversation, in 35+ languages and 50+ dialects.
openrouter.ai/mistralai/voxt…
3
1,552
Voxtral Mini Transcribe 3: the smaller, lower-cost speech-to-text model in the family.
openrouter.ai/mistralai/voxt…
1
2
1,608
Voxtral Small Transcribe 3: Mistral reports it beats Whisper, Scribe v2 and Gemini 3.5 Transcribe on multilingual transcription.
openrouter.ai/mistralai/voxt…
1
3
270
All three models have EU-hosted and zero-data-retention endpoints on OpenRouter, through the same /audio/transcriptions and /audio/speech API as our other speech models.
2
10
481
Voxtral 3 from @MistralAI is now on OpenRouter!
Mistral released two new speech-to-text models and a new text-to-speech model, across 50+ languages.
Introducing Voxtral 3: state-of-the-art Transcribe and Speech models powering Mistral’s new voice agents API. 🧵
7
4
69
6,069
Use it now: openrouter.ai/inception/merc…
Read more:
1/4 Today, we’re releasing Mercury 3. Mercury 3 is by far our most powerful model and the most intelligent diffusion LLM ever released. It outperforms GPT-6 Luna and Haiku 5.5 on quality while running at 1000+ tok/sec.
1
18
5,723
Mercury 3 is live on OpenRouter!
@_inception_ai's new diffusion model generates 1,000+ tok/s with 1M context, 4x more than Mercury 2.5. Inception reports it beats GPT-6 Luna and Haiku 5.5 on IFBench, GPQA Diamond, and SWE-Bench Atlas.
50% off at launch: $0.10/M in, $0.35/M out
46
32
735
43,906
Read more:
MiniMax M3.1 Flash: Space Performance + Bunny Speed
🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash.
💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed.
API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens.
Model weights will arrive on Oct 23.
API: platform.minimax.io
M Plan: minimax.io/m-plan
MiniMax Code for desktop: agent.minimax.io/download
7
4,347
MiniMax reports 72.5% on AutomationBench-AA and 73.67% on DeepSWE. In their evals it also edges DeepSeek V4.1 Flash (1017) on Automation-Bench and HLE.
After the free period: $0.15/M input, $0.60/M output, $0.015/M cached input. MiniMax plans to release the weights later this week.
3
26
3,384
Thank you to everyone who put it through its paces. Your feedback helped MiniMax fix bugs and ship upgrades mid-stealth:
- 38% faster time to first token (1.95s → 1.22s)
- 45% more throughput (70 → 100 tok/s)
- Error rate cut in half (1.4% → 0.7%)
2
1
37
3,878
Stealth model reveal 🐰
Space Bunny was OpenRouter’s #1 model for 10 straight days, processing 56.7T tokens! The most of any stealth model we’ve run.
Space Bunny hopped off OpenRouter on Oct 5. It's back today as @MiniMax_AI's M3.1 Flash, and it's free for the next 72 hours.
59
79
1,102
126,574
OpenRouter retweeted
A few months ago, we built a self-improving security agent called Sentinel to help protect OpenRouter users. It runs 24/7 across all activity to look for activity anomalies, signs of end-user account takeover, user key theft, and more.
It continuously makes improvements based on signals from our trust and safety team, with a 0.05% action reversal rate (similar to false positive rate) this month. Anyone app can leverage its protection by implementing OpenRouter OAuth: openrouter.ai/docs/guides/ov…
And if you want to be a part of real autoresearch in action, join us! jobs.ashbyhq.com/openrouter/…
15
10
65
9,561
Gave my coding agent every frontier model on @OpenRouter and let a router pick the best one for each step.
Guess which model ended up doing most of the work
3
2
25
6,844
OpenRouter retweeted
Today, we are launching OpenRouter Armor in beta.
Tool calls allow agents to interact with the world, and regex-based filtering often isn't enough to detect unwanted tool calls.
Armor uses @typesafeai's Jev model to guard against out of policy tool calls before your agent executes them, with better performance than Claude Code's auto classifier at a fraction of the cost.
81
68
1,163
149,722
We're live on OpenRouter with DeepSeek v4.1-1017
Clear improvements on agentic coding across the board
DeepSeek V4.1 Flash 1017 is live on OpenRouter with DeepSeek as the first provider and many more providers on the way.
@deepseek_ai's update to V4.1 Flash is more token efficient and shows major gains in agentic benchmarks.
Use it now: openrouter.ai/deepseek/deeps…
3
30
6,014
Classify: use the Decisions API to automatically detect an agent stuck in a loop, and halt or nudge it on thresholds you set.
openrouter.ai/docs/cookbook/…
7
12
4,677
Looking for a weekend project? Two new OpenRouter cookbooks on @scaledown_team's task-specific models (currently 20% off!), each a ready-to-run recipe for a workflow problem.
Summarize: compact a 100-step agent session while keeping the facts it still needs.
openrouter.ai/docs/cookbook/…
19
6
114
13,452