RightNow (YC F26) (@rightnow_co) header
RightNow (YC F26) (@rightnow_co) profile picture

The kernel lab behind instant AI

Joined February 2026
Photo by RightNow (YC F26) (@rightnow_co)Photo by RightNow (YC F26) (@rightnow_co)Photo by RightNow (YC F26) (@rightnow_co)Photo by RightNow (YC F26) (@rightnow_co)Photo by RightNow (YC F26) (@rightnow_co)Photo by RightNow (YC F26) (@rightnow_co)Photo by RightNow (YC F26) (@rightnow_co)Photo by RightNow (YC F26) (@rightnow_co)Photo by RightNow (YC F26) (@rightnow_co)Photo by RightNow (YC F26) (@rightnow_co)
one of our customers made this video about the RightNow decision model RightNow is a multimodal decision model. one model that takes text, PDFs, images, audio, video and robot state, with 1M context it reads what's happening and decides what to do next, fast enough to act in real time trained on our own kernels. v3 is live now rightnowai.co/rightnow
4
6
1
20
1,276
thanks @j0hnny_lit for this amazing demo!
1
6
131
batch on RightNow: 50% off list price on open models input, cached input, output. all half one JSONL file, up to 50 MiB. one POST to start the job every answer lands on your webhook as it finishes -- no polling, no output file to download a line that fails costs nothing you set a hard spending cap per job. it cannot run past it runs within 24 hours evals, synthetic data, backfills, embeddings-scale classification. anything that does not need an answer this second should not pay full price rightnowai.co
1
5
1
14
1,660
Hy4 flash by Tencent dropped 3 hours ago. it's live on RightNow our agent optimized its kernels in under 2 hours. no human in the loop 218 tok/s. 98% cache hit rate text and images in, text out. 1,048,576 token context. tool calls and strict JSON schema output USD 0.06 in. USD 0.01 cached in. USD 0.25 out -- per million tokens rightnowai.co/models/hy4-fla…
5
6
1
37
4,271
RightNow decision model v3 is live it makes decisions -- while the input is still arriving stream in text, JSON, robot state, a codebase, PDFs, images, voice or video. ask your questions. get an answer with a probability for every option ~30 ms per decision. $0.0001 per answered question. up to 1M tokens of context in one call built for the robot that has to act now, the agent that has to pick a tool, the support queue that has to route it's available now rightnowai.co/rightnow
6
20
8
309
30,211
RightNow makes AI models run faster on GPUs half the open model inference market already uses our kernels. NVIDIA got 14x more performance with them today we launch our own inference API. it runs on our fastest engine you get the best open models at full speed. pay per token, run batch at half price, reserve capacity, or get a dedicated deployment that is only yours own your AI rightnowai.co
24
10
1
68
7,770
Step 5 Preview from StepFun is live on RunInfra today. served in BF16 285 tok/s output. 46 ms to first token $0.90 per 1M input, $2.43 per 1M output, $0.09 per 1M cached. 1M token context, up to 1M output tokens OpenAI-compatible chat completions and Anthropic-compatible /v1/messages. text and image input, tool calling, JSON mode, streaming zero data retention. never used for training runinfra.ai/inference-api/st…
14
7
1
48
2,485
kimi k3.1 pro highspeed is coming soon at 250tps
5
6
2
47
3,729
RightNow (YC F26) retweeted
last month i was begging gpu providers for b300s at $7.9/hr now they're begging me to take them at $4.6/hr, no commitment something big is happening soon. ai gave us all its dessert and now it's time for the veggies
346
281
196
5,901
1,387,833
RightNow (YC F26) retweeted
a lot of decision models came out in the last two months. almost all of them work the same way. they read text, wait until the whole input has arrived, and then give you an answer that works for a support ticket. it doesn’t work for a robot, a phone call, or a video feed, where the input never really ends and the decision has to happen while it is still coming in so we spent half of our YC money training a model:) RightNow takes text, PDFs, images, voice, code, robot state and video, all in one model, and you can stream up to 1M tokens of context into it. it updates its decision as each piece arrives. on text it decides in 30 ms and we will make it less with our kernel optimization we trained it with what we call Reflex Training. the current decision models read everything first and answer once. RightNow is trained to decide on whatever has arrived so far, to hold back until the evidence is there, and then commit. it serves on what we call Reflex Architecture which keeps a probability for every option and updates it as each part of the input comes in we call this kind of model “System Zero”. system 1 is fast thinking and system 2 is slow reasoning. system zero is the step that comes before both, which is just deciding we will publish a technical paper on Reflex Training and Reflex Architecture. the model itself will stay closed source and available via RightNow API this is our first checkpoint and it’s still a little buggy. we launched it early because the fastest way to make it good is to have people use it:)
RightNow is out today. our first “System Zero” model it streams in text, JSON, PDFs, images, voice, codebases, robot state and video, and returns a decision with a probability for every option while the input is still arriving 30 ms decisions on text. up to 1,024 questions in one call. output is free system 1 is fast thinking. system 2 is slow reasoning. “System Zero” is the step before both -- the decision itself this is our first checkpoint. there is a lot of work ahead, and we decided to ship early to get your feedback. more features and fixes are shipping this week, with more checkpoints after rightnowai.co
41
49
9
995
74,680
RightNow (YC F26) retweeted
RightNow is out today. our first “System Zero” model it streams in text, JSON, PDFs, images, voice, codebases, robot state and video, and returns a decision with a probability for every option while the input is still arriving 30 ms decisions on text. up to 1,024 questions in one call. output is free system 1 is fast thinking. system 2 is slow reasoning. “System Zero” is the step before both -- the decision itself this is our first checkpoint. there is a lot of work ahead, and we decided to ship early to get your feedback. more features and fixes are shipping this week, with more checkpoints after rightnowai.co
21
31
12
401
83,983
RightNow (YC F26) retweeted
throw a rock in sf and you’ll hit 50 inference providers
44
29
16
961
52,781
glm 5.3 flash just got 51% cheaper on runinfra $0.05 per 1M input, down from $0.11. $0.01 per 1M cached input, down from $0.03. $0.22 per 1M output, down from $0.45 99.3% cache hit rate over the last 24h. most of your input tokens are billing at the cached rate that puts a full 1M context prompt at around 1 cent on a cache hit same speed: 254 tok/s, 703ms TTFT discount runs until nov 4, then standard rates resume automatically runinfra.ai/inference-api/gl…
13
10
2
76
8,352
runinfra endpoints are now on routerplus fast open-source inference, one more place to use it
3
7
2
39
4,711
RightNow (YC F26) retweeted
Replying to @rightnow_co
@runinfrai sure doesn't lie about cache optimization, that's for sure
2
3
4
344
runinfra coding plan is live the fastest open models in claude code, codex, opencode and 16 more agents. from $10 a month more usage per dollar and faster tok/s than other providers. both, not one or the other DeepSeek V4.1 Flash, GLM 5.3, Ornith 1.5 122B, Qwen3.8 27B and more. one sub up to 378 tok/s. up to 99.3% cache hit. cached input from $0.01 / 1M, so the plan goes further $10 → ~$12 of usage $29 → ~$35 $99 → ~$119 limits reset every 5 hours and every week. hit one and you pick: credits, or free standby. never a dead stop mid-task setup is one prompt -- paste it into your agent and it wires itself runinfra.ai/pricing?plan=cod…
29
17
5
273
60,750
Ornith 1.5 122B is live on runinfra. launch partner with @ornith_ , live from hour 0 302 tok/s output. 72ms to first reasoning token $0.20 / 1M input. $0.02 cached. $0.80 output 99.1% cache hit rate on agentic workloads one of the best models we've served for its size. 10B active and it holds up on real agent work OpenAI-compatible chat completions and Anthropic-compatible /v1/messages -- drop it into claude code as is zero data retention by default runinfra.ai/inference-api/or…
10
10
2
40
7,740
DeepSeek V4.1 Flash 1017 is live on RunInfra hour 0 support. day 0 is for slow teams 327 tok/s output. 30ms to first reasoning token $0.15 per 1M input, $0.60 per 1M output, $0.01 per 1M cached. 1M token context cache hit rate stays above 98% on agentic workloads. every hit and miss shows up in your dashboard, so you can check it yourself OpenAI-compatible chat completions and Anthropic-compatible /v1/messages. text and image input zero data retention. never used for training runinfra.ai/inference-api/de…
14
9
6
192
19,492