Hy4 from @TencentHunyuan is live on OpenRouter
Tencent's new flagship and the first Hy4 with vision: text and image input, reasoning on by default. Tencent reports clear gains over Hy4 Preview on agentic and long-horizon work: finance, frontend, games, office work and research.
/M output (50% off), 1M context.
openrouter.ai/tencent/hy4
Tencent's new flagship and the first Hy4 with vision: text and image input, reasoning on by default. Tencent reports clear gains over Hy4 Preview on agentic and long-horizon work: finance, frontend, games, office work and research.
/M output (50% off), 1M context.
openrouter.ai/tencent/hy4
2
1
20
968
Tencent's numbers: 44.4 on Terminal Bench 4.0, 78.9 on OSWorld 2.1 and 56.2 on AutomationBench v1.0.6.
See more:
hy.tencent.ai/research/hy4
See more:
hy.tencent.ai/research/hy4
0
0
0
129
Parallel Decisions is now on OpenRouter. Parallel Decisions delivers the highest accuracy on web-grounded decisions for System One models like Jev. Get web-grounded answers 13× faster at 1/16 the cost of OpenAI’s GPT Luna with native web search.
Ask questions about the live web ers with probabilities and citations in under a second.
Ask questions about the live web ers with probabilities and citations in under a second.
4
16
100
30,004
Bring your OpenRouter API key and your next idea. Exclusive for OpenRouter users, try it free for 7 days.
Select Parallel: Decisions Fast in the model list, or set your model ID to parallel/decisions-fast.
openrouter.ai/parallel/decis…
Select Parallel: Decisions Fast in the model list, or set your model ID to parallel/decisions-fast.
openrouter.ai/parallel/decis…
0
1
6
455
Gemini Omni 1.2 Flash from @GoogleAIStudio is live on OpenRouter
Google's video model, now with clips up to 15 seconds (1.1 topped out at 10) and about 30% lower per-second pricing. Text-to-video and image-to-video, 360p up to 4K, 16:9 or 9:16, with native audio. The same model e and video prompts on chat completions (131K context, $1.50/M in, $9/M out).
Video pricing per second: 360p $0.023, 720p $0.070, 1080p $0.104, 4K $0.209. The clip above is 15s at 1080p, one request through OpenRouter for about $1.56.
See more:
openrouter.ai/google/gemini-…
Google's video model, now with clips up to 15 seconds (1.1 topped out at 10) and about 30% lower per-second pricing. Text-to-video and image-to-video, 360p up to 4K, 16:9 or 9:16, with native audio. The same model e and video prompts on chat completions (131K context, $1.50/M in, $9/M out).
Video pricing per second: 360p $0.023, 720p $0.070, 1080p $0.104, 4K $0.209. The clip above is 15s at 1080p, one request through OpenRouter for about $1.56.
See more:
openrouter.ai/google/gemini-…
4
0
41
11,135
Reflex from @morphllm is live on OpenRouter!
The first decision model on OpenRouter with cached pricing, it takes an image or prompt + a typed question and sends back an answer with a probability.
The first decision model on OpenRouter with cached pricing, it takes an image or prompt + a typed question and sends back an answer with a probability.
5
3
11
1,099
The kinds of jobs it is built for:
- Verify damage for an insurance claim
- Decide if an agent session needs to be compressed
- Flag fraudulent transactions
- Choose the next step in a workflow
- Decide whether to escalate to a human
You can ask several questions about the same input in one call and the shared context will be reused.
- Verify damage for an insurance claim
- Decide if an agent session needs to be compressed
- Flag fraudulent transactions
- Choose the next step in a workflow
- Decide whether to escalate to a human
You can ask several questions about the same input in one call and the shared context will be reused.
1
0
1
59
Parakeet Ultra from @moondreamai is live on OpenRouter
Moondream's post-trained version of NVIDIA Parakeet TDT 0.6B v3: same architecture and speed, lower word error rate on every benchmark group. 25 European languages, with segment and word timestamps.
$0.06 per hour of audio, ct.
openrouter.ai/moondream/para…
Moondream's post-trained version of NVIDIA Parakeet TDT 0.6B v3: same architecture and speed, lower word error rate on every benchmark group. 25 European languages, with segment and word timestamps.
$0.06 per hour of audio, ct.
openrouter.ai/moondream/para…
2
0
21
9,870
Moondream reports 5.80% vs 6.26% WER on the Open ASR Leaderboard English sets and 9.55% vs 11.62% on the 25-language FLEURS set. The biggest drop is on long-form audio: 1.94% vs 2.71% on TED-LIUM.
See more: x.com/vikhyatk/statu…
See more: x.com/vikhyatk/statu…
Another speech-to-text model release:
Moondream Parakeet Ultra!
Same post-training pipeline applied to NVIDIA Parakeet, without the ternary quantization. Lower error rate and noise tolerance on every benchmark group.
0
0
1
376
Models on OpenRouter retweeted
🥷 New stealth model: Crouton Alpha
A highly efficient reasoning model built to scale out the work your agents repeat all day.
- Free to use
- 1M token context
- Text, image, audio, and video input
- No training on data
A highly efficient reasoning model built to scale out the work your agents repeat all day.
- Free to use
- 1M token context
- Text, image, audio, and video input
- No training on data
118
66
1,736
190,117
🥷 New stealth drop: stealth/crouton-alpha
- Free to use
- 1M token context
- Try it and tell us what you think
openrouter.ai/stealth/crouto…
- Free to use
- 1M token context
- Try it and tell us what you think
openrouter.ai/stealth/crouto…
🥷 New stealth model: Crouton Alpha
A highly efficient reasoning model built to scale out the work your agents repeat all day.
- Free to use
- 1M token context
- Text, image, audio, and video input
- No training on data
8
3
108
7,400
HeyGen Voice Turbo from @HeyGen is free on OpenRouter until November 30!
The lower-latency version of HeyGen's text-to-speech model, the one that topped the Artificial Analysis TTS leaderboard. $0, no credits needed.
Over 2,900 voice options, 39 languages, up to 5,000 streamed as 44.1 kHz audio.
See more: openrouter.ai/heygen/heygen-…
The lower-latency version of HeyGen's text-to-speech model, the one that topped the Artificial Analysis TTS leaderboard. $0, no credits needed.
Over 2,900 voice options, 39 languages, up to 5,000 streamed as 44.1 kHz audio.
See more: openrouter.ai/heygen/heygen-…
9
7
93
16,631
Models on OpenRouter retweeted
Krea 3 is 50% off on OpenRouter through Nov 10. Give it a product shot, a person, and a location, and it puts them together in one 2K image in as little as 9 seconds. @krea_ai
8
6
54
15,236
TBC mischief 1 is now live on OpenRouter 🧠🎬
Image-to-video from The Biological Computing Company: give it a starting image and a prompt, get back a 3s or 5s clip at 480p or 720p.
From $0.005 per second of video.
openrouter.ai/tbc/mischief-1
Image-to-video from The Biological Computing Company: give it a starting image and a prompt, get back a 3s or 5s clip at 480p or 720p.
From $0.005 per second of video.
openrouter.ai/tbc/mischief-1
4
3
26
10,675
See more:
x.com/AlexKsendzovsk…
x.com/AlexKsendzovsk…
today, we introduce a little mischief to the world.
for four years, we’ve been brewing real brain cells on electrodes to understand how they compute. now, we’ve turned those discoveries into a video model anyone can use.
from 0.5¢ a second, mischief 1 is at least 5x faster than st image-to-video model on @fal and @OpenRouter. soon to be on @awscloud marketplace.
it’s not a delusion anymore. biocompute is real, commercial and this is just the beginning.
happy halloween.
1
1
7
443
Joey 1 from @baseten is live on OpenRouter
A 2B decision model from Base Labs, post-trained from Qwen3.5-2B. Give it a state and typed questions; get back a choice, yes/no, or score with calibrated probabilities in a single forward pass.
$0.01/M input, free output, 16K context.
openrouter.ai/baseten/joey-1
A 2B decision model from Base Labs, post-trained from Qwen3.5-2B. Give it a state and typed questions; get back a choice, yes/no, or score with calibrated probabilities in a single forward pass.
$0.01/M input, free output, 16K context.
openrouter.ai/baseten/joey-1
3
2
15
857
It's the fastest and cheapest of the family: Baseten reports a 20 ms P50 latency, about 2.5x faster than Elephant 1. Same Decisions API as Elephant 1 and Mammoth 1, so switching is a one-line model change.
See more: baseten.co/blog/decisions…
See more: baseten.co/blog/decisions…
1
0
2
200
The Ecosystem team at OpenRouter has spent the last few months iterating on and measuring this new algorithm. It's now live for all our traffic, and will continue to improve!
Expect a technical deep dive in the next few weeks too.
Expect a technical deep dive in the next few weeks too.
We just shipped our biggest improvement to our provider router since the founding of OpenRouter.
Before, we prioritized mostly based on price. The new router now rewards the best quality inference for the actual cost of a request, so requests stay cheap but are also fast and at deliver more value automatically win more traffic, so every provider has a reason to keep improving. And every time a provider gets better, so does your inference on OpenRouter.
1
1
14
513