DeepInfra
@DeepInfra
Followers
4K
Following
47
Media
33
Statuses
394
Fast ML inference. Run top AI models using a simple API.
Palo Alto
Joined February 2023
Not a promo. Not a catch. Just fast GPUs priced right. Build more. Pay less. DeepInfra. 🔥. #AIInfra #LLM #Inference #B200 #DeepInfra
3
4
22
Generate videos in just a few seconds. Try Grok Imagine, free for a limited time.
801
3K
10K
Two new models just landed from OpenAI - and they’re live on DeepInfra. 🟢 gpt-oss-20B → $0.04 / $0.16 per Mtoken.🔵 gpt-oss-120B → $0.09 / $0.45 per Mtoken. Agentic, fast, open-source. As always - best price.
3
5
46
🚀OlmOCR on DeepInfra🚀. 🔥 New LLM-based OCR model by @allen_ai .💸 Scrape 1000-page PDFs for just $0.15.📊 300x cheaper than competitor price
5
17
208
🎬 ByteDance’s SeeDance-T2V is now live on DeepInfra!.An advanced AI model for multi-shot video generation - smooth, coherent, and prompt-accurate. 💰 $1.20 / Mtoken. #AI #text2video #DeepInfra #ByteDance.
4
2
25
GLM-4.5 is here — latest drop from @Zai_org 🚀.Built for agentic workflows: reasoning, coding, tools. ✅ GLM-4.5 → 355B total / 32B active → $0.60 / $2.20 per Mtoken.✅ GLM-4.5-Air → 106B total / 12B active → $0.20 / $1.10. Smart models, smart prices. Cheapest at DeepInfra!
7
21
336
Built for serious work. Now hosted on DeepInfra.
deepinfra.com
Qwen3-235B-A22B-Thinking-2507 is the Qwen3's new model with scaling the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning. . Try out API on the Web
0
1
4
Newest Qwen3-235B “Thinking” is now live on DeepInfra 🧠.Most advanced reasoning model by @Alibaba_Qwen. ⚡️A powerful model tuned for logical reasoning, deeper context use, and high-complexity tasks. 💸 $0.13 / $0.60 per Mtoken (FP8). #LLMs #Qwen #DeepInfra #Inference
3
2
18
🚀 We now have a Turbo version of Qwen3‑Coder at $0.30/M input tokens $1.20/M output tokens. ⚡️Same accuracy (within 1% of original).⚡️2× faster & cheaper. One of the best open coding models - now faster & more affordable on DeepInfra 👇
8
13
139