| RT @JensenHuang: Today, with over 100 industry partners, we introduced the NVIDIA Open Agent Safety Platform, bringing … |
@DeepInfra |
Company |
Repost |
2026-09-29 |
43 |
0 |
4,257 |
0 |
0 |
0 |
| Agents need more than model-level guardrails. They also need runtime boundaries that control what they can access and d… |
@DeepInfra |
Company |
Original |
2026-09-28 |
427 |
7 |
3 |
1 |
0 |
0 |
| https://t.co/EoMwzcH4TG
https://t.co/vQMPl8Xj62
We just dropped support for newest models from @XiaomiMiMo
The cheap… |
@DeepInfra |
Company |
Original |
2026-09-23 |
749 |
21 |
0 |
3 |
0 |
0 |
| RT @ned_malki: I used my entire usage limit for BOTH Codex and Claude Code (2 accounts) to tackle a local build, and th… |
@DeepInfra |
Company |
Repost |
2026-09-21 |
54 |
0 |
2 |
0 |
0 |
0 |
| Encoder-decoder is back 😈!!! In DeepSeek V4.1 Flash the first 20 layers build the global KV that the next 20 read from,… |
@DeepInfra |
Company |
Original |
2026-09-18 |
1,136 |
33 |
3 |
0 |
0 |
4 |
| Inference is life |
@DeepInfra |
Company |
Original |
2026-09-12 |
568 |
10 |
2 |
0 |
0 |
0 |
| Persimmon is a genuinely different idea: a model of how people actually talk, not another assistant.
Proud to support … |
@DeepInfra |
Company |
Original |
2026-09-11 |
5,895 |
48 |
7 |
2 |
2 |
10 |
| RT @humansand: For AI to work with us, it needs to understand us
Today, we're introducing Persimmon, the first large-s… |
@DeepInfra |
Company |
Repost |
2026-09-11 |
58 |
0 |
133 |
0 |
0 |
0 |
| congrats to @humansand team on Persimmon release 💫 |
@DeepInfra |
Company |
Quote |
2026-09-10 |
1,532 |
22 |
3 |
3 |
0 |
1 |
| Two Ling 3.0 flash variants are now live on DeepInfra, both day 0 with @AntLingAGI
→ Ling-3.0-flash-Fin — finance-t… |
@DeepInfra |
Company |
Original |
2026-09-08 |
1,969 |
17 |
2 |
3 |
1 |
5 |
| Ling-3.0-flash-VL is live on DeepInfra — day 0 with @AntLingAGI.
https://t.co/jKmxpZw9CG |
@DeepInfra |
Company |
Quote |
2026-09-08 |
1,441 |
7 |
3 |
0 |
1 |
0 |
| 46% fewer errors 👀🚀 |
@DeepInfra |
Company |
Quote |
2026-09-03 |
593 |
9 |
0 |
0 |
0 |
0 |
| Congrats to @AntLingAGI on the launch of their new model! |
@DeepInfra |
Company |
Quote |
2026-09-03 |
507 |
3 |
0 |
0 |
0 |
1 |
| The @Zai_org team is on a roll. Another open-weight drop, and a seriously good one — congrats to everyone who shipped i… |
@DeepInfra |
Company |
Quote |
2026-08-28 |
1,438 |
28 |
5 |
2 |
0 |
1 |
| Day 0 support for GLM-5.3 on DeepInfra. 🚀
@Zai_org's latest flagship model brings major advances in complex coding, lo… |
@DeepInfra |
Company |
Original |
2026-08-28 |
672 |
16 |
2 |
1 |
0 |
0 |
| Video and audio, from one model.
Wan3.0-Video from @Alibaba_Wan is now on DeepInfra: 30-second clips at 1080P, omni-mo… |
@DeepInfra |
Company |
Original |
2026-08-27 |
15,654 |
9 |
4 |
2 |
2 |
2 |
| congrats to @Zai_org team, big milestone! |
@DeepInfra |
Company |
Quote |
2026-08-26 |
1,410 |
20 |
1 |
1 |
0 |
0 |
| Day 0 support for GLM-5.3-Flash on DeepInfra.
$0.15 in / $0.50 out per 1M. $0.03 cached.
@Zai_org's 320B-A18B multimo… |
@DeepInfra |
Company |
Original |
2026-08-26 |
1,838 |
41 |
6 |
5 |
0 |
1 |
| RT @StockMKTNewz: THE RISE OF THE DATA CENTER
Here's how much revenue Nvidia $NVDA has brought in each quarter over th… |
@DeepInfra |
Company |
Repost |
2026-08-23 |
41 |
0 |
58 |
0 |
0 |
0 |
| Introducing DeepInfra Sandboxes: isolated, on-demand compute for AI agents and developers to run code safely. Real VM i… |
@DeepInfra |
Company |
Original |
2026-08-19 |
1,600 |
26 |
4 |
3 |
3 |
5 |
| RT @brexHQ: Our summer fastest-growing vendors list just dropped, and the story is: infrastructure won. Turns out the r… |
@DeepInfra |
Company |
Repost |
2026-08-18 |
48 |
0 |
28 |
0 |
0 |
0 |
| Congratulations to @OpenRouter team! We are proud to be the largest inference provider on @OpenRouter with 97 models … |
@DeepInfra |
Company |
Quote |
2026-08-17 |
1,429 |
22 |
3 |
2 |
0 |
1 |
| DeepSeek-V4-Pro-0813 is live on DeepInfra.
Congrats to the @deepseek_ai team!
1.6T MoE, 49B active, 1M context.
Run… |
@DeepInfra |
Company |
Original |
2026-08-15 |
3,372 |
52 |
4 |
5 |
1 |
4 |
| Congrats to the @Z_AI team on GLM-5.3! 🚀
We’re proud to host their open-source models at DeepInfra and excited to see … |
@DeepInfra |
Company |
Quote |
2026-08-14 |
1,640 |
10 |
4 |
0 |
0 |
1 |
| New on DeepInfra: Qwen3.8-2.4T-A95B 🚀
@Alibaba_Qwen's latest sparse MoE — 2.4T total params, 95B active, 512 experts. … |
@DeepInfra |
Company |
Original |
2026-08-13 |
28,014 |
32 |
4 |
2 |
2 |
2 |
| RT @AntLingAGI: Thanks for our day0 partner @DeepInfra for the impeccable inference support! Try Ling-3.0-flash on Deep… |
@DeepInfra |
Company |
Repost |
2026-08-13 |
51 |
0 |
1 |
0 |
0 |
0 |
| New: Prompt Cache Retention on DeepInfra 🔥
Pin your prompt's KV cache for 5 min or 1 hour. Reuse skips prefill — faste… |
@DeepInfra |
Company |
Original |
2026-08-11 |
1,413 |
13 |
1 |
2 |
0 |
3 |
| Day 0: @nvidia Nemotron 3.5 Lightning is live on DeepInfra.
The fastest open model in its class — 30B MoE, 3B active pa… |
@DeepInfra |
Company |
Original |
2026-08-11 |
1,222 |
16 |
2 |
2 |
0 |
2 |
| Text-to-video for 2 cents.
FastWan2.2-TI2V-5B from @haoailab is live on DeepInfra: 5s clips, 720p @ 24 fps, ~3s genera… |
@DeepInfra |
Company |
Original |
2026-08-10 |
955 |
7 |
1 |
3 |
0 |
4 |
| DeepInfra is serving 700B+ new tokens/day just on @OpenRouter — and many more for our customers on private endpoints — … |
@DeepInfra |
Company |
Original |
2026-08-05 |
3,998 |
45 |
8 |
8 |
2 |
8 |
| Ling-3.0-flash is live on DeepInfra
A 124B MoE from @AntLingAGI with just 5.1B active params, large-model capacity at c… |
@DeepInfra |
Company |
Original |
2026-08-05 |
24,169 |
25 |
1 |
1 |
2 |
2 |
| @deepseek_ai's V4 Flash 0731 is rocking the leaderboards, and we're proud to serve it at the best price:
$0.09 / $0.18 … |
@DeepInfra |
Company |
Quote |
2026-08-03 |
2,169 |
24 |
3 |
5 |
1 |
3 |
| @Alibaba_Qwen's Qwen3.8-Max is now live on DeepInfra 🚀
Their 2.4T-parameter MoE flagship — a serious leap in coding an… |
@DeepInfra |
Company |
Original |
2026-08-03 |
792 |
17 |
1 |
1 |
0 |
1 |
| 🆕DeepSeek-V4-Flash-0731 is now on DeepInfra.
The official release of V4-Flash, much stronger agentic capabilities, and… |
@DeepInfra |
Company |
Original |
2026-07-31 |
3,694 |
22 |
2 |
7 |
1 |
2 |
| 🆕Nano Banana 2 is now on DeepInfra — in two versions 🍌
→ nano-banana-2: top-tier image generation + editing, now with … |
@DeepInfra |
Company |
Original |
2026-07-31 |
740 |
5 |
1 |
2 |
0 |
0 |
| 🆕Claude Opus 5 is now on DeepInfra.
Anthropic's most advanced Opus model, built for long-running agents, with real gai… |
@DeepInfra |
Company |
Original |
2026-07-27 |
2,055 |
24 |
1 |
3 |
0 |
0 |
| 🆕The gap between prototyping an AI agent and running one reliably, around the clock, has always been infrastructure: pr… |
@DeepInfra |
Company |
Original |
2026-07-22 |
1,052 |
10 |
1 |
1 |
1 |
1 |
| This is the one we've been excited about. Vera is the CPU built for exactly what we do — running agents at scale. Thank… |
@DeepInfra |
Company |
Quote |
2026-07-21 |
1,093 |
2 |
0 |
0 |
0 |
1 |
| Proud to be the independent benchmark behind @nvidia Vera launch.
We run agents in production so we measured the CPU b… |
@DeepInfra |
Company |
Quote |
2026-07-21 |
954 |
9 |
1 |
0 |
0 |
1 |
| 🆕Tencent Hy3 is now on DeepInfra.
A 295B MoE model (21B active) that punches way above its weight. Tencent says it riv… |
@DeepInfra |
Company |
Original |
2026-07-21 |
659 |
7 |
1 |
1 |
0 |
1 |
| We run agents in production. So when NVIDIA built Vera CPU for agents, we benchmarked it ourselves.
@nvidia Vera CPU … |
@DeepInfra |
Company |
Original |
2026-07-21 |
14,416 |
21 |
2 |
1 |
2 |
1 |
| 🆕New on DeepInfra: the Flex service tier.
Not every request needs an answer this second. Flex runs latency-tolerant wo… |
@DeepInfra |
Company |
Original |
2026-07-17 |
843 |
8 |
1 |
3 |
0 |
1 |
| Retrieval is where AI agents live or die. Miss the right context and the agent reasons from the wrong place.
@nvidia … |
@DeepInfra |
Company |
Original |
2026-07-16 |
686 |
11 |
4 |
1 |
0 |
0 |
| Big milestone for DeepInfra 📷
We've opened our first international #datacenter in Toronto!
The new facility will host… |
@DeepInfra |
Company |
Original |
2026-07-08 |
1,208 |
23 |
4 |
4 |
1 |
1 |
| 🆕Open models just hit frontier-level agent performance.
@LangChain tuned their Deep Agents harness for NVIDIA Nemotron… |
@DeepInfra |
Company |
Original |
2026-07-08 |
1,051 |
10 |
1 |
1 |
0 |
2 |
| 🆕Claude is now on DeepInfra.
We've added two Anthropic models:
Claude Sonnet 5: near-Opus intelligence for coding, ag… |
@DeepInfra |
Company |
Original |
2026-07-07 |
3,582 |
35 |
1 |
4 |
2 |
3 |
| This looks really awesome. Many flops, much #NVIDIA B300s, deep infrastructure. https://t.co/h7RWmIEsRp |
@DeepInfra |
Company |
Original |
2026-07-04 |
35,908 |
104 |
18 |
6 |
9 |
15 |
| Text to video in ~2.4 seconds.
FastWan-QAD-FP8-1.3B is now on DeepInfra 🆕
5-second 480p clips from a prompt, landscap… |
@DeepInfra |
Company |
Original |
2026-07-02 |
1,450 |
17 |
3 |
3 |
1 |
3 |
| 🆕🚀Batch API is live on DeepInfra.
Run large inference jobs → embeddings, evals, classification, summarization — asynch… |
@DeepInfra |
Company |
Original |
2026-07-02 |
3,450 |
10 |
4 |
1 |
1 |
0 |
| New on DeepInfra: Priority Service Tier.⚡️
Your latency-critical traffic jumps to the front of the queue, lower TTFT, … |
@DeepInfra |
Company |
Original |
2026-07-01 |
1,039 |
10 |
3 |
2 |
0 |
0 |
| We're proud to serve our models on @nvidia inference stack 🚀 |
@DeepInfra |
Company |
Quote |
2026-06-30 |
1,983 |
11 |
1 |
1 |
0 |
4 |
| We’ve been building on @nvidia's inference stack from day one — TensorRT-LLM, Dynamo, NVFP4 on Blackwell.
When DeepSee… |
@DeepInfra |
Company |
Original |
2026-06-30 |
712 |
5 |
0 |
1 |
0 |
2 |
| We keep thinking "How did she do it?"
🎬 Just shipped: LTX-2.3-Distilled-Diffusers is live on Deep Infra.
1080p. 5 seco… |
@DeepInfra |
Company |
Original |
2026-06-25 |
620 |
11 |
1 |
2 |
0 |
1 |
| @Zai_org GLM 5.2 = GPT-5.5 coding performance
at 1/6th the cost.
open weights.
now $1 / $4 / $0.18 per 1M tokens … |
@DeepInfra |
Company |
Original |
2026-06-22 |
908 |
15 |
3 |
1 |
0 |
1 |
| GLM 5.2 prices just dropped 🔥
$1.40 → $1.20 input
$4.40 → $4.20 output
$0.25 → $0.20 cached
cached tokens down 20% - h… |
@DeepInfra |
Company |
Original |
2026-06-18 |
1,009 |
10 |
1 |
2 |
0 |
1 |
| Your own AI agent, always on, from $13/mo. 📷
Deep Infra Hosted Agents: OpenClaw (web dashboard) or Hermes (SSH/termina… |
@DeepInfra |
Company |
Original |
2026-06-18 |
1,290 |
14 |
2 |
2 |
0 |
5 |
| 📉 Price cut on @NVIDIAAI Nemotron 3 Ultra.
$0.50 in / $2.20 out / $0.10 cached per 1M — output down 12%, cached down 33… |
@DeepInfra |
Company |
Original |
2026-06-16 |
461 |
7 |
1 |
2 |
0 |
0 |
| Congrats on the launch @Zai_org 🚀
Day zero on DeepInfra → https://t.co/X9YqVcuBM4 |
@DeepInfra |
Company |
Quote |
2026-06-16 |
1,097 |
11 |
2 |
0 |
0 |
0 |
| @Zai_org's GLM-5.2 — day zero on DeepInfra 🔥
744B/40B MoE, MIT-licensed, full 1M ctx, High/Max thinking-effort.
Top op… |
@DeepInfra |
Company |
Original |
2026-06-16 |
8,938 |
48 |
4 |
2 |
0 |
4 |
| Step 3.7 Flash is Live on DeepInfra: An Agentic, Multimodal Model Built for Production https://t.co/lblfIyrvC6 |
@DeepInfra |
Company |
Original |
2026-06-13 |
15,655 |
50 |
2 |
1 |
1 |
7 |
| @nvidia Blackwell powers agentic AI, and DeepInfra is one of the places you can run it.
New AgentPerf benchmark from @… |
@DeepInfra |
Company |
Original |
2026-06-12 |
1,249 |
9 |
2 |
0 |
0 |
1 |
| We just added text-to-music on DeepInfra.
ACE-Step v1.5 XL — open-source, full song generation from a text prompt. Voc… |
@DeepInfra |
Company |
Original |
2026-06-12 |
1,154 |
16 |
0 |
1 |
1 |
4 |
| Big upgrade to @bria_ai_'s video background removal on DeepInfra — shipping today.
2x better quality · 9x faster · 33x… |
@DeepInfra |
Company |
Original |
2026-06-10 |
1,421 |
8 |
2 |
2 |
1 |
3 |
| Lol https://t.co/pSsNhHD8mf |
@DeepInfra |
Company |
Original |
2026-06-06 |
2,183 |
11 |
0 |
1 |
1 |
2 |
| We just added @NVIDIA Nemotron 3.x to DeepInfra — Day 0.
Two open and highly efficient models, live now:
→ Nemotron 3 U… |
@DeepInfra |
Company |
Original |
2026-06-04 |
2,247 |
12 |
0 |
2 |
2 |
0 |
| NVIDIA Cosmos 3 is live on DeepInfra.
The first open world foundation model for physical AI that reasons before it gene… |
@DeepInfra |
Company |
Original |
2026-06-03 |
868 |
6 |
1 |
1 |
0 |
0 |
| We are really excited about Nemotron 3 Ultra. |
@DeepInfra |
Company |
Quote |
2026-06-01 |
590 |
5 |
0 |
0 |
0 |
0 |
| The right question, and one too few enterprises are asking. Thanks @realmtbman and @palebluenexus for having our co-fou… |
@DeepInfra |
Company |
Quote |
2026-05-14 |
1,581 |
5 |
3 |
0 |
0 |
1 |
| "I wasn't sure what we'd build. I just wanted to work with my co-founders. We ended up deciding to do AI infrastructure… |
@DeepInfra |
Company |
Original |
2026-05-13 |
746 |
4 |
0 |
1 |
0 |
1 |
| New on DeepInfra: Realtime TTS 2.0 from @inworld_ai
• Prompt emotion + tone in plain English
• Cross-lingual voices
•… |
@DeepInfra |
Company |
Original |
2026-05-05 |
799 |
5 |
1 |
1 |
0 |
0 |
| DeepInfra has raised its $107M in Series B funding 🚀
AI is moving from training to production-scale deployment, and in… |
@DeepInfra |
Company |
Original |
2026-05-04 |
12,572 |
56 |
9 |
7 |
6 |
12 |
| DeepInfra is now a first-class provider in @OpenClaw. One key, every model. 🦞 |
@DeepInfra |
Company |
Quote |
2026-05-01 |
1,922 |
12 |
4 |
2 |
1 |
0 |
| Two new ways to make video on DeepInfra 🎬
Wan2.7-I2V - turn any image into cinematic motion. Subjects, style, even text… |
@DeepInfra |
Company |
Original |
2026-04-29 |
458 |
2 |
1 |
1 |
0 |
1 |
| DeepInfra × Hugging Face
DeepInfra is live on @HuggingFace Inference Providers.
Run DeepSeek V4, Kimi-K2.6, GLM-5.1 and… |
@DeepInfra |
Company |
Original |
2026-04-29 |
24,648 |
69 |
14 |
8 |
1 |
18 |
| DeepInfra is an official launch partner for @nvidia Nemotron™ 3 Nano Omni — live today.
One open multimodal 30B-A3B m… |
@DeepInfra |
Company |
Original |
2026-04-28 |
4,469 |
44 |
6 |
2 |
0 |
8 |
| Price drop alert on DeepInfra:
• GLM-5.1 → $1.05 / $3.50 / $0.205
• GLM-5 → $0.60 / $2.08 / $0.12
• MiniMax-M2.5 → $0… |
@DeepInfra |
Company |
Original |
2026-04-27 |
5,007 |
56 |
4 |
8 |
0 |
15 |
| DeepSeek V4 is live on DeepInfra at launch 🔥
V4-Pro: 1.6T MoE / 49B active. Frontier-tier reasoning.
$1.74 in · $3.… |
@DeepInfra |
Company |
Original |
2026-04-24 |
1,054 |
23 |
1 |
7 |
0 |
1 |
| We added Qwen3.6-35B-A3B to the catalog.
Small-active MoE, fast, cheap.
$0.20/M in · $1.00/M out per 1M tokens |
@DeepInfra |
Company |
Original |
2026-04-23 |
887 |
10 |
1 |
2 |
1 |
4 |
| @Kimi_Moonshot's latest K2.6 is now running on DeepInfra.
1T / 32B MoE, 256K context.
$0.55/$2.50/$0.15 per 1M tokens |
@DeepInfra |
Company |
Original |
2026-04-22 |
2,770 |
28 |
3 |
2 |
1 |
1 |
| Wan2.2-T2V-A14B from @Alibaba_Wan is on Deep Infra. 27B MoE T2V model, hosted and ready via API. No data stored, no set… |
@DeepInfra |
Company |
Original |
2026-04-14 |
874 |
7 |
1 |
2 |
0 |
0 |
| We are hiring new grads. If you have CS degree, 3.8GPA from top school and want to do inference. Apply here https://t.c… |
@DeepInfra |
Company |
Original |
2026-04-11 |
701 |
5 |
0 |
0 |
0 |
3 |
| Gemma 4 is live on DeepInfra.
Both models, best price anywhere.
26B: $0.08 in / $0.35 out / $0.01 cached
31B: $0.1… |
@DeepInfra |
Company |
Original |
2026-04-08 |
787 |
13 |
2 |
3 |
0 |
3 |
| @DeepInfra is at HumanX. Ping us in the app if you want to connect. https://t.co/P7GJeBcft9 |
@DeepInfra |
Company |
Original |
2026-04-08 |
399 |
3 |
0 |
0 |
0 |
1 |
| Day 0. GLM-5.1 from @Zai_org is live on DeepInfra.
Open source getting close to GPT-5.4 and Claude Opus 4.6.
Powered b… |
@DeepInfra |
Company |
Original |
2026-04-07 |
1,279 |
9 |
4 |
1 |
1 |
1 |
| DeepInfra roller coaster pitch! #cloudfest. Iskren did awesome job https://t.co/YVCl3PZVb4 |
@DeepInfra |
Company |
Original |
2026-03-28 |
609 |
10 |
2 |
4 |
0 |
0 |
| Excited for GLM-5.1 from @Zai_org 👀
We’ll support it on DeepInfra as a Day-0 partner - early access already underway. |
@DeepInfra |
Company |
Quote |
2026-03-27 |
1,468 |
20 |
1 |
2 |
0 |
1 |
| Step-3.5-Flash is live on DeepInfra.
0.18s TTFT. 131 TPS.
$0.10 in | $0.30 out | $0.02 cached / 1M tokens.
Fast enough … |
@DeepInfra |
Company |
Original |
2026-03-26 |
732 |
12 |
2 |
2 |
0 |
1 |
| The #1 ranked TTS model is now on DeepInfra.
@inworld_ai TTS-1.5 tops Artificial Analysis for expressiveness - 30% bet… |
@DeepInfra |
Company |
Original |
2026-03-25 |
552 |
7 |
1 |
2 |
0 |
1 |
| Day 3 of #GTC in San Jose and the energy is still going strong.
So many great conversations with customers, partners,… |
@DeepInfra |
Company |
Original |
2026-03-18 |
502 |
9 |
1 |
0 |
0 |
0 |
| Deep Infra and NVIDIA are working together on NVIDIA NemoClaw - an open-source stack that simplifies running OpenClaw a… |
@DeepInfra |
Company |
Original |
2026-03-16 |
3,920 |
31 |
5 |
6 |
0 |
10 |
| Heading to GTC today — so much to see this week.
If you're around, come say hi at Booth #4022.
Let's go
#GTC2026 #NV… |
@DeepInfra |
Company |
Original |
2026-03-16 |
728 |
4 |
1 |
0 |
0 |
0 |
| @NVIDIA GTC starts tomorrow.
If you're in San Jose this week - come find us at Booth #4022.
Happy to talk models, inf… |
@DeepInfra |
Company |
Original |
2026-03-16 |
310 |
7 |
0 |
1 |
0 |
0 |
| Kimi K2.5 Turbo just dropped on Deep Infra 🚀
#1 by speed: 341 tokens/sec
#1 by price: $0.90/1M tokens
… |
@DeepInfra |
Company |
Original |
2026-03-13 |
25,917 |
305 |
19 |
12 |
1 |
76 |
| We are excited to launch @NVIDIA Nemotron 3 Super on DeepInfra!
Built for complex multi-agent applications, this open h… |
@DeepInfra |
Company |
Original |
2026-03-11 |
4,183 |
22 |
7 |
4 |
0 |
0 |
| New voice model on DeepInfra 🔊
Qwen3-TTS from @Alibaba_Qwen brings:
• voice cloning from a ~3s sample
• expressive to… |
@DeepInfra |
Company |
Original |
2026-03-09 |
3,342 |
13 |
3 |
2 |
0 |
13 |
| 🚀 New launch with @PrunaAI
We’ve just added p-video to DeepInfra - a real-time AI video model supporting:
• Text, ima… |
@DeepInfra |
Company |
Original |
2026-02-26 |
1,350 |
16 |
4 |
2 |
0 |
0 |
| Big one.
We’ve partnered with @Alibaba_Qwen to bring Qwen3-Max-Thinking into the DeepInfra ecosystem.
Their latest fl… |
@DeepInfra |
Company |
Original |
2026-02-20 |
513 |
10 |
1 |
4 |
0 |
0 |
| MiniMax-M2.5 from @MiniMax_AI is live on DeepInfra!
80.2% SWE-Bench Verified.
Agentic tool use + search.
Office + rea… |
@DeepInfra |
Company |
Original |
2026-02-18 |
850 |
8 |
3 |
1 |
0 |
1 |
| We’re now serving Qwen3-Max, the flagship model from @Alibaba_Qwen
Top-tier reasoning.
Serious coding capability.
Prod… |
@DeepInfra |
Company |
Original |
2026-02-13 |
2,033 |
6 |
1 |
2 |
1 |
0 |
| Low-res images killing your product pages?
Clarity AI upscalers (Creative / Crystal / Flux) are live on DeepInfra.
Bui… |
@DeepInfra |
Company |
Original |
2026-02-12 |
404 |
3 |
1 |
1 |
0 |
0 |
| DeepInfra x @NVIDIA Blackwell x @latitudeio
Latitude runs large-scale MoE models on our Blackwell-powered inference p… |
@DeepInfra |
Company |
Original |
2026-02-12 |
1,976 |
6 |
2 |
2 |
0 |
1 |
| Day-0 with @Zai_org: GLM-5 is live on DeepInfra 🔥
Built for long-horizon agents that plan, orchestrate, and self-correc… |
@DeepInfra |
Company |
Original |
2026-02-11 |
12,580 |
149 |
8 |
7 |
2 |
33 |
| #1 speed #1 latency BEST blended price
DeepInfra tops @ArtificialAnlys for GLM-4.7-Flash
⚡️ 105.7 tok/s | ⏱… |
@DeepInfra |
Company |
Original |
2026-02-05 |
699 |
10 |
2 |
2 |
0 |
1 |
| Last week we were in DC for the Cursor AI Hackathon and even with rough weather, the energy inside was 🔥
Huge shoutou… |
@DeepInfra |
Company |
Original |
2026-02-04 |
461 |
9 |
1 |
5 |
0 |
2 |
| Big milestone for @NVIDIAAIDev
We're happy to host the Nemotron family models on DeepInfra with optimized inference, … |
@DeepInfra |
Company |
Quote |
2026-02-03 |
2,419 |
12 |
1 |
0 |
0 |
3 |
| Shipping with @bria_ai_: FIBO Edit (images) + 6 video tools for production workflows - Eraser, Upscale, Remove BG, Mask… |
@DeepInfra |
Company |
Original |
2026-01-30 |
544 |
4 |
2 |
2 |
0 |
1 |
| Shipping Kimi-K2.5: strong agentic workflows, clean vision-language understanding, instant & thinking modes.
At th… |
@DeepInfra |
Company |
Original |
2026-01-30 |
419 |
9 |
2 |
2 |
0 |
0 |
| Now live on Deepinfra with Day-0 support in partnership with @NVIDIAAIDev + @nvidia
Nemotron 3 Nano NVFP4 on NVIDIA B2… |
@DeepInfra |
Company |
Original |
2026-01-28 |
277 |
6 |
1 |
1 |
0 |
0 |
| New on DeepInfra: HiggsAudioV2.5 by @boson_ai - high-quality TTS with clear delivery, stable prosody, and consistent p… |
@DeepInfra |
Company |
Original |
2026-01-26 |
524 |
6 |
1 |
3 |
0 |
1 |
| New on DeepInfra 🔥 FLUX.2 Klein 9B from @bfl.
Higher fidelity, steady consistency, still fast enough for production. G… |
@DeepInfra |
Company |
Original |
2026-01-23 |
634 |
4 |
1 |
2 |
0 |
0 |
| 😀 Proud to be the largest provider of models
#inference #ai |
@DeepInfra |
Company |
Quote |
2026-01-09 |
360 |
6 |
1 |
0 |
0 |
0 |
| More ways to use it. Olmo-3.1-32B-Instruct is on @openrouter and hosted on DeepInfra.
$0.20 in / $0.60 out. Private en… |
@DeepInfra |
Company |
Quote |
2026-01-08 |
308 |
2 |
1 |
0 |
0 |
0 |
| Now hosting @allen_ai Olmo-3.1-32B-Instruct on DeepInfra. Designed for solid reasoning and clean instruction following… |
@DeepInfra |
Company |
Original |
2026-01-06 |
593 |
6 |
2 |
1 |
1 |
0 |
| Holiday drop: GLM-4.7 from @Zai_org is live on DeepInfra. Built for coding, complex reasoning, and agent workflows.
We… |
@DeepInfra |
Company |
Original |
2025-12-23 |
976 |
11 |
3 |
2 |
0 |
0 |
| Reminder:
Our ALL @bria_ai_ models are free until year-end, so go try them out!
That includes Fibo, our JSON-friendly… |
@DeepInfra |
Company |
Original |
2025-12-22 |
439 |
6 |
2 |
1 |
0 |
0 |
| 🔥DeepSeek-V3.2 just got cheaper on Deepinfra!
$0.26 in / $0.39 out per 1M tokens.
$0.13 cached / 1M tokens (50% of in… |
@DeepInfra |
Company |
Original |
2025-12-17 |
837 |
14 |
4 |
2 |
0 |
1 |
| Newest top-tier image model from Black Forest Labs @bfl_ml: FLUX.2 [max] on DeepInfra! It reads the web for context, ke… |
@DeepInfra |
Company |
Original |
2025-12-16 |
284 |
3 |
1 |
1 |
0 |
0 |
| @NVIDIAAIDev Nemotron 3 Nano is live on DeepInfra. We’re an official launch partner, bringing this open reasoning mode… |
@DeepInfra |
Company |
Original |
2025-12-15 |
1,043 |
6 |
2 |
1 |
0 |
0 |
| Nemotron 3 Nano is trained on NVIDIA-curated synthetic reasoning data and reinforced to support more human-like reasoni… |
@DeepInfra |
Company |
Quote |
2025-12-15 |
336 |
2 |
1 |
0 |
0 |
0 |
| New on DeepInfra: @Zai_org's GLM-4.6V.
Make your agents see.
Screenshots, charts, receipts, diagrams.
$0.30 in / $0.9… |
@DeepInfra |
Company |
Original |
2025-12-09 |
317 |
5 |
2 |
1 |
0 |
0 |
| 🚀 Latest DeepSeek 3.2 is now live on the @DeepInfra inference platform!
Super excited about this model and what it can … |
@DeepInfra |
Company |
Original |
2025-12-03 |
666 |
7 |
4 |
1 |
1 |
0 |
| Our @PrunaAI models are live
You can edit and generate an image in 1 second without compromising quality. It's pretty… |
@DeepInfra |
Company |
Quote |
2025-12-01 |
1,062 |
8 |
3 |
1 |
0 |
1 |
| Nice upgrade. Embeddings unlock better search, memory, and agents. DeepInfra is ready for high-throughput pipelines; DM… |
@DeepInfra |
Company |
Quote |
2025-11-20 |
379 |
4 |
1 |
0 |
0 |
0 |
| @minimax_ai's MiniMax-M2 is live on DeepInfra.
Built for code + agents with 10B active params, fast and efficient.
$0… |
@DeepInfra |
Company |
Original |
2025-11-12 |
381 |
7 |
1 |
1 |
1 |
1 |
| Now live: Kimi K2 Thinking on DeepInfra.
@Kimi_Moonshot's most capable open “thinking” model built for complex reasonin… |
@DeepInfra |
Company |
Original |
2025-11-12 |
315 |
5 |
1 |
1 |
0 |
0 |
| We have launched the new FIBO model from @bria_ai_ It is #1 in alignment, #1 in aesthetics, and #1 smallest model compa… |
@DeepInfra |
Company |
Original |
2025-11-10 |
620 |
6 |
1 |
1 |
1 |
0 |
| A bit late but we had fun at @nvidia Washington DC GTC conference! We even had a celeb sighting 👀
Was great to meet n… |
@DeepInfra |
Company |
Original |
2025-11-07 |
589 |
2 |
1 |
0 |
0 |
0 |
| Love this update from @Kimi_Moonshot team. Tool calling matters a ton for agentic AI, and DeepInfra is proud to be at … |
@DeepInfra |
Company |
Quote |
2025-10-29 |
655 |
5 |
0 |
1 |
0 |
0 |
| Thrilled to be a Day 0 partner with @nvidia. Nemotron vision-language model is now served on DeepInfra.
More details h… |
@DeepInfra |
Company |
Original |
2025-10-28 |
347 |
7 |
1 |
1 |
0 |
0 |
| We’re at NVIDIA GTC Washington DC next week (Tue–Wed)! Who’s going?
Come say hi at Booth I-9, we'd love to meet you.
… |
@DeepInfra |
Company |
Original |
2025-10-23 |
691 |
5 |
1 |
0 |
0 |
0 |
| Interesting paper alert: https://t.co/z0XKxbzrnF |
@DeepInfra |
Company |
Original |
2025-10-22 |
628 |
4 |
1 |
0 |
0 |
1 |
| We’re the first to host the newest OCR model by @allen_ai - olmOCR-2-7B-1025, now live on DeepInfra.
$0.14 in / $0.80 o… |
@DeepInfra |
Company |
Quote |
2025-10-22 |
765 |
8 |
0 |
1 |
0 |
2 |
| Happy hour trivia is tonight!
6-9pm
7 Social SF
See you there! |
@DeepInfra |
Company |
Quote |
2025-10-22 |
683 |
2 |
0 |
1 |
0 |
0 |
| Great initiative by @openrouter - making real-world provider variance transparent.
DeepInfra is among the launch provid… |
@DeepInfra |
Company |
Quote |
2025-10-22 |
3,613 |
12 |
2 |
0 |
0 |
2 |
| PaddleOCR-VL-0.9B is has been live on DeepInfra since the weekend!
Blazing-fast, vision-language OCR you can deploy in… |
@DeepInfra |
Company |
Original |
2025-10-20 |
874 |
9 |
2 |
4 |
0 |
2 |
| If you did not know we have the Google Veo 3.1 model on Deep Infra.
Check out the video our production team made. Hol… |
@DeepInfra |
Company |
Original |
2025-10-16 |
767 |
8 |
2 |
0 |
0 |
1 |
| This event with @nvidia and @vllm_project is going to be awesome, sign up before we run out of room!
10 days and cou… |
@DeepInfra |
Company |
Quote |
2025-10-12 |
712 |
4 |
1 |
0 |
0 |
1 |
| Good news: now @FactoryAI users get 25% off the first $20 of usage every month. It’s applied automatically with BYOK. A… |
@DeepInfra |
Company |
Quote |
2025-10-08 |
7,432 |
25 |
7 |
1 |
0 |
8 |
| Trivia night in SF on Oct 22 with @nvidia and @vllm_project. All things open-source and inference. Link below. |
@DeepInfra |
Company |
Quote |
2025-10-08 |
874 |
4 |
1 |
1 |
0 |
0 |
| New coder model: Qwen3-Coder-30B-A3B-Instruct . 30.5B params, MoE efficiency, 256K→1M context, excels at tool use and m… |
@DeepInfra |
Company |
Original |
2025-10-08 |
800 |
12 |
1 |
1 |
0 |
4 |
| Deep Infra is available via @FactoryAI CLI. Use best agentic open source models at cheapest price and top quality
#in… |
@DeepInfra |
Company |
Quote |
2025-10-07 |
5,344 |
28 |
3 |
0 |
0 |
7 |
| We made an appearance last night! Whose going to what events this @Techweek_ ?
#sftechweek |
@DeepInfra |
Company |
Quote |
2025-10-07 |
727 |
4 |
1 |
0 |
0 |
0 |
| 👾 Think you can out-nerd your peers? Join @nvidia , @DeepInfra, and @vllm_project for trivia night. From GPUs to pop c… |
@DeepInfra |
Company |
Original |
2025-10-06 |
1,142 |
8 |
3 |
2 |
0 |
1 |
