Morph (@morphllm) header
Morph (@morphllm) profile picture

inference built for agents

San Francisco, CA
Joined May 2025
Photo by Morph (@morphllm)Photo by Morph (@morphllm)Photo by Morph (@morphllm)Photo by Morph (@morphllm)Photo by Morph (@morphllm)Photo by Morph (@morphllm)Photo by Morph (@morphllm)Photo by Morph (@morphllm)Photo by Morph (@morphllm)Photo by Morph (@morphllm)
Introducing DeepSeek V4.1 Flash 1017 Abliterated, live now on Morph, available through our Model APIs. It feels more important to release this than ever before, with hacks in the past week affecting everything from PHP to recognizable brands like Railway and OpenCode. Attackers now run abliterated models against your infrastructure 24/7. You need to do the same in defense. That said, we're not allowing just anyone to sign up and use this. You'll have to go through KYC and explain your intentions first. Fill out the form here to request access: morphllm.com/privileged-acce…
63
49
32
936
201,707
deepseek provider our heavy content processing changed again @morphllm is now our default and the best one to fit our conditions: quality, speed and affordable 275 tok/s at $0.63 per 1k steps, nearly wafer speed for ~35% less
1
1
4
234
intelligence can now buy its own intelligence powered by @CoinbaseBiz
Agents don't need credit cards. @morphllm now accepts USDC and USDT payments. That means agents can pay for their own intelligence. Thanks to Coinbase Business. Here's the flow ↓
2
6
1,739
RT @CoinbaseBiz: Agents don't have credit cards. @morphllm now accepts USDC and USDT payments. That means agents can pay for their own int…
3
53
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.
5
3
1
12
1,211
Introducing Reflex, a 27B decision model based on Qwen 3.5. It's the first decision model with cached pricing. Available now on our Model APIs and @OpenRouter. It's rare that you only want to ask one question about a piece of information. Say you're handling support tickets. For each ticket, you'll want to answer several questions: - which department? - is it urgent? - is the customer angry? - are they asking for a refund? - is this spam? With cached pricing, you only pay the premium once. $0.042/M input on the first request, then $0.008/M for however many requests follow. Try it here: morphllm.com/products/reflex
4
4
2
57
11,309
Tomorrow.
5
10
3
79
7,525
Morph retweeted
DeepSeek V4.1 Flash Abliterated from Morph is now live on Opper AI. @morphllm launched it last week for defenders, so they can run the kind of model attackers already use against their own infrastructure, for red teaming, vulnerability research and agent evaluations. Access stays gated like on Morph: sign up, tell us your use case and we enable it on your account. opper.ai/morph/deepseek-v4-1…
11
4
22
615
Our @coinbase integration is live. Agents will pay for intelligence on tap at runtime and will become cryptos highest volume use case Thrilled to partner with them
Stablecoins are the perfect way to pay for inference: global, no amount limits, no chargebacks, and up to 57% cheaper than cards. That’s why we partnered with @morphllm to bring USDC and USDT payments to its platform. 6 networks. No gas fees. 500+ wallets supported.
1
2
10
1,490
We're excited to announce a new partnership with the team at @morphllm to bring the latest abliterated open models to MindFort Swarms. In response to the rapid increase of agent-led cyberattacks, we needed a partner that was able to meet the inference requirements needed to run large scale agent swarms. MindFort is designed to let teams safely deploy security swarms to quickly find vulnerabilities in their products and services. Try today: mindfort.ai/morph
2
2
4
15
6,562
We're live on OpenRouter with DeepSeek v4.1-1017 Clear improvements on agentic coding across the board
DeepSeek V4.1 Flash 1017 is live on OpenRouter with DeepSeek as the first provider and many more providers on the way. @deepseek_ai's update to V4.1 Flash is more token efficient and shows major gains in agentic benchmarks. Use it now: openrouter.ai/deepseek/deeps…
3
40
9,531
We're live with deepseek-v4.1-flash-1017
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4
1
11
6,599
DeepSeek Flash V4.1 is now live on morph. Completely new architecture optimized for price to performance. GPT-5 level intelligence at just 5% of the cost. Expect an insanely high cache hit rate. This model fits 4x the amount of cache per unit of storage.
5
2
39
23,630
Morph now has the highest cache hit rate out of any provider serving Kimi K3 $200 spent on morph gets you 15% more Kimi tokens than that same $200 would on Modal and 64% more than it would on baseten will be doing the same for GLM-5.3 next
12
7
3
177
67,181