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)
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
35
3,785
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
306
29,125
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
23
10
1
67
7,633
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
2,449
kimi k3.1 pro highspeed is coming soon at 250tps
5
6
2
47
3,702
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
5,904
1,386,400
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
994
74,642
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
402
83,883
RightNow (YC F26) retweeted
throw a rock in sf and you’ll hit 50 inference providers
44
29
16
960
52,731
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
8,331
runinfra endpoints are now on routerplus fast open-source inference, one more place to use it
3
7
2
39
4,696
RightNow (YC F26) retweeted
Replying to @runinfrai
@runinfrai sure doesn't lie about cache optimization, that's for sure
2
3
4
343
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
60,678
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
7,723
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
191
19,484
half of all input tokens on runinfra now come from agents running at 97%+ cache hit over the last 48h, those agents averaged 98.7%. the best one hit 99.7% same agents, by model: DeepSeek V4.1 Flash: 98.8% GLM 5.3 Flash: 98.4% cached input is $0.03 / 1M. every hit and miss shows up in your dashboard runinfra.ai/
4
6
1
43
5,078
25% off DeepSeek V4.1 Flash and GLM 5.3 Flash on RunInfra. live now through oct 13 DeepSeek V4.1 Flash - input $0.14 → $0.10/M - cached $0.03 → $0.02/M - output $0.58 → $0.43/M GLM 5.3 Flash - input $0.11 → $0.08/M - cached $0.03 → $0.02/M - output $0.45 → $0.33/M rounded down in your favor -- up to 33% off per line. same API, same speed runinfra.ai/inference-api
4
5
1
25
2,959
deepseek V4.1 flash is live on runinfra 378 tok/s output. 30ms to first token $0.14 / 1M input. $0.03 cached. $0.58 output 1M context. 99.3% cache hit rate over the last 24h 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/de…
34
16
8
356
40,082
we spent september rewriting the kernels behind GLM 5.3 Flash. major release is live on RunInfra today 670 tok/s on Vercel AI Gateway $0.11 per 1M input, $0.45 per 1M output, $0.03 per 1M cached. 1M token context. FP8, vendor-native release it now runs on AMD. same model, same API, more capacity behind it 99.7% cache hit rate over the last 24 hours. every hit and miss shows up in your dashboard, so you can track the cache logs yourself 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/gl…
96
100
64
1,995
364,820
Vercel AI Gateway
4
2
74
19,521