just an hour since release, and Kimi K3 is already up on Fireworks openrouter.ai/moonshotai/k... 4 times lower latency, twice as fast looks like they still have some stability problems, but this model will be everywhere in a day or two 🙂 Claude Opus on any plan is probably cheaper now though? 😏
Post
openrouter.aiKimi K3 - API Pricing & BenchmarksKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. $3 per million input tokens, $15 per million output tokens. 1,048,576 token context window. Higher uptime with 3 pr...
Agree. My point is that token pricing is a poor proxy for outcome quality, so list prices are too. We benchmark actual task outcomes (llmbench.kapualabs.com), and the differences are huge. You can easily pay 100× more and still get a worse result.
llmbench.kapualabs.comThe Right-Sized LLM BenchmarkCheapest LLM that's good enough for the work you're doing — per step of your pipeline.
but no coding benchmarks? and most of these models don't even qualify for most tasks? I don't understand how these are scored 🤔
0 reposts0 likes