{"id":"serverless-gpu","slug":"serverless-gpu","name":"Serverless GPU inference/jobs","shortName":"Serverless GPU inference/jobs","problemStatement":"Run GPU work with scale-to-zero and minimal ops.","whenNotTopPick":"Need cheapest raw GPU-seconds on familiar pods (RunPod) or one-click public models (Replicate).","categoryIds":["cat-gpu-cloud","cat-cpu-compute"],"depotPickProviderId":"modal","depotPickRationale":"dx + pricePerf + reliability. Modal wins Python DX; RunPod wins flexible $/GPU.","runnersUpIds":["runpod","replicate","beam","baseten","chutes","friendli","koyeb"],"weights":{"capabilityFit":0.22,"pricePerformance":0.25,"latencyReliability":0.15,"developerDx":0.12,"privacyPosture":0.08,"lockInRisk":0.08,"maturity":0.1},"methodologyNotes":"dx + pricePerf + reliability. Modal wins Python DX; RunPod wins flexible $/GPU.","tags":["serverless"],"depth":{"whenNotToUse":{"text":"Need cheapest raw GPU-seconds on familiar pods (RunPod) or one-click public models (Replicate).","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"runpod","name":"RunPod","overallForJob":8.34,"pickOverallForJob":8.36,"beatsPickOn":["pricePerformance","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":4.5,"runnerUpLockInRisk":3.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[],"migration":"Runner-up RunPod has lower stored lock-in risk (3.5 vs 4.5, 0–10, higher = more lock-in).","migrationReason":null,"derivedFrom":"stored lockInRisk scores, provider tags (oss, self-host, openai-compat, open-models), free rows that list this job, and verbatim provider notes. No migration guide was invented."}},"freshness":{"pick":{"score":{"asOf":"2026-10-19","ageDays":8,"stale":false,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-10-19","ageDays":8,"stale":false,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":2,"sourcesReachable":2,"pricingRows":18,"pricingRowsReconfirmed":18,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}}},"depotPick":{"id":"modal","slug":"modal","name":"Modal","tagline":"Depot darling for Python agent backends and bursty GPU jobs. If you think in functions not VMs, start here.","overall":8.36},"runnersUp":[{"id":"runpod","slug":"runpod","name":"RunPod","tagline":"Depot default for self-serve GPUs. Secure Cloud for anything customer-facing; Community/spot for batch.","overall":8.34},{"id":"replicate","slug":"replicate","name":"Replicate","tagline":"Ship a model demo by lunch. Migrate hot paths to Modal/RunPod/Fireworks when the bill hurts.","overall":7.63},{"id":"beam","slug":"beam","name":"Beam","tagline":"Viable Modal/RunPod alternative for serverless endpoints. Evaluate cold starts on your workload.","overall":7.57},{"id":"baseten","slug":"baseten","name":"Baseten","tagline":"Strong custom-model serving alternative to Replicate/Modal when you bring your own model.","overall":7.93},{"id":"chutes","slug":"chutes","name":"Chutes","tagline":"Budget open-model overflow with a now-pinned public TEE matrix. Depot open-model production pick stays…","overall":7.42},{"id":"friendli","slug":"friendli","name":"FriendliAI","tagline":"Open-model production peer when latency/tool-calling matter. Fireworks remains depot open-model default…","overall":7.99},{"id":"koyeb","slug":"koyeb","name":"Koyeb","tagline":"Serverless GPU/app peer for EU-friendly deploys. Depot neocloud pick stays Nebius; interruptible Salad…","overall":8.11}]}