Meet the performance-obsessed teams shaping the future
Baseten is the infrastructure choice for teams shipping high-stakes, high-performance AI products.
How Writer helps businesses transform with AI seeing 60% higher tokens per second with Baseten
How Gamma achieves 5x faster image generation without an in-house ML team
OpenEvidence delivers instant, accurate medical information with the Baseten Inference Stack
How OpenEvidence trains accurate, domain-specific models with Baseten Training
How Rime.ai achieved state-of-the-art p99 latencies on Baseten
Superhuman achieves 80% faster embedding model inference with Baseten
Zed Industries serves 2x faster code completions with the Baseten Inference Stack
By partnering with Baseten, Zed achieved 45% lower latency, 3.6x higher throughput, and 100% uptime for their Edit Prediction feature.
45%
lower p90 latency
3.6x
higher throughput
Bland AI breaks latency barriers with record-setting speed using Baseten
Read more
Wispr Flow creates effortless voice dictation with Llama on Baseten
Read more
Latent delivers pharmaceutical search with 99.999% uptime on Baseten
Read more
Building AI Agents, Open Code, and Open Source Coding with Dax Raad
Watch now
Praktika delivers ultra-low-latency transcription for global language education with Baseten
Read more
From datasets to deployed models: How Oxen helps companies train faster
Read more
Scaled Cognition offers ultra-fast AI agents you can trust
Read more
Patreon saves nearly $600k/year in ML resources with Baseten
Read more
How Sully.ai returned 30M+ clinical minutes to healthcare using open-source models.
Read moreChosen by the world's most ambitious builders
Case study
Case study
Case study
Case study
Case study
Case study
Case study
Case study
Case study
Case study
Case study
Case study
Case study
Case study
