Edgee Turbo Models - Use Claude Code with Kimi K2.7 Code, MiniMax M2.7, and more

@sachamorard @Product Hunt is about consistency, S/O for this new launch! keep up the great, and keep launching 👏👏

@sachamorard fight the good fight to bring inference costs down! Can you guarantee that your compression is lossless?

@doganakbulut You can switch whenever you want, please be aware that this will result in a cache miss at providers level therefore we recommend waiting for the next session if you want to switch !

@doganakbulut Yep, we can switch mid-session whenever you want. Or we can switch automatically when you reach your Claude usage limit, or when the Anthropic API is down (quite often, isn't it? 😆)

Hey @mikebrandswarm 
Important clarification first: the models themselves don't run at the edge. What runs at the edge is the Edgee gateway. The models run on dedicated high-throughput inference infrastructure (ours, or partners like Together AI, Fireworks, and a few others depending on the model), and our gateway routes each request to the fastest path between your machine and the inference backend.

This split matters for your cold-start question. Here's how we handle it:

• The gateway itself has no cold start for a given PoP. It runs continuously across regions on infrastructure built for low-latency request handling.

• For the inference backend, we maintain persistent keep-alive connections to each provider so the first hit from a PoP doesn't pay a TCP/TLS handshake tax. We use HTTP/2 with multiplexing, TCP_NODELAY, and pre-warmed connection pools.

• Combined with provider keep-warm on their side, the practical result is sub-100ms TTFB from most PoPs to most Turbo Models, even on a request that hasn't been served from that PoP in hours.

On the stateful question:

LLM inference is fundamentally stateless per request. Every prompt carries its own context, and the model itself doesn't retain anything between calls. So there's nothing to reconcile across PoPs at our layer.

The interesting state lives on the provider side, specifically KV-cache and prompt cache. Each provider has their own strategy for how they keep that warm and how they route subsequent requests to the same warm replica. That's their domain and they're better at it than we'd ever be from the gateway layer. Our job is to pick the best provider for the model you asked for, route you to them on the fastest path, and stay out of the way.

Edgee owns the routing and connection optimization layer. Providers own the inference stateful layer. The specialization works because each side is doing what they're best at.

Happy to go deeper if you want, this is a fun part of the system.

@priya_kushwaha1 You'll see, Kimi K2.7 Code (turbo version) is really impressive. Looking forward to having your feedback

@anand_thakkar1 Yes, exactly! Edgee is able to fall back to the model/provider you choose.
Even without the turbo models, you can use it with Claude and fall back to Kimi when your usage limit is reached (or when Anthropic has an incident), for example.

@tina_chhabra Both points are exactly what we kept hearing in customer conversations before we built this.

On flat pricing: agentic workflows are genuinely unpredictable. One day you have a clean refactor, the next your agent is in a 30-minute edit-run-fix loop and you've burned $40. Knowing your monthly ceiling upfront is a different kind of freedom. It changes how teams use the tool because the meter isn't running in their heads.

On switching cost: this is the part most people underestimate. The quality gap between closed and open frontier models on coding tasks is far smaller than the gap in setup friction. We benchmarked GLM 5.1 and Kimi K2.6 Code against Sonnet on real coding sessions for weeks before this launch, and the outputs are genuinely close. But "close on output" doesn't matter if "setup takes a Saturday." So that's the actual battle: zero-config switching.

The whole point of routing through a gateway is that "trying a new model" becomes a 30-second toggle, not a project.

Thanks for the thoughtful comment 🙏

Hey @gilles_raymond, you again ;)
Yes on both.

Models: DeepSeek V4 and Qwen 3.5 Coder are both on the shortlist.

We're benchmarking them right now and they'll likely join the lineup in the next few weeks. The criteria we use: agentic capability, tool calling reliability, and inference infrastructure availability for genuine high-throughput serving.

Codex: yes. Turbo already works with Codex today through the same gateway.
And it works on Cursor, Copilot, OpenCode...
We focused the launch messaging on Claude Code because that's where the speed pain point is most acute in our user base, but the same flat $29/month gets you Turbo Models in Codex too.
❤️

Thank you @myselfkushal, this made my day. I just checked the contact form, got your details, and I'm sending you a calendar link by email right now. Looking forward to digging into the use case.

Quick question for the thread: I'm always curious which model in the Turbo lineup catches the eye of teams with video and multimodal workflows. Are you thinking GLM 5.1, Kimi K2.7 Code, or are you waiting for something we haven't shipped yet?

Talk soon 🙏

@gilles_raymond2 Honest answer: the gap is much smaller than it was 6 months ago, and on a lot of tasks it's gone.

We benchmarked GLM 5.1, Kimi K2.6, and MiniMax 2.7 against Sonnet 4.6 on real coding sessions for several weeks before this launch. Three patterns emerged:

• On focused tasks (write a function, fix a bug, refactor a file), outputs are genuinely comparable. A blind test wouldn't reliably pick the closed model.

• On long agentic loops with heavy tool calling, GLM 5.1 holds up best. It was trained explicitly for agentic workflows and it shows.

• On extreme long-context reasoning (whole-repo Q&A across hundreds of files), Sonnet still has a small edge for now.

The bigger insight from those weeks: the choice of model matters less than people think. The choice of how the model is served matters way more. A "weaker" model at 200 tok/s with no metered bill often produces a better dev experience than a "stronger" one crawling out tokens at premium pricing.

Haha, thanks@sarveshsea , accurate. I'm the founder and I still catch myself defending

my "main" model out of pure habit, then switching three times in the same session.

The honest truth is most devs don't need one perfect model, they need the right one for each task. Turbo just makes that switching free.

Thanks 🙏