{"jtbdId":null,"categoryId":"cat-train-finetune","sort":"overall","minConfidence":"low","region":null,"asOf":"2026-10-19","freshness":{"scoreAsOfMin":"2026-09-14","scoreAsOfMax":"2026-10-19","contractAsOf":"2026-10-03","note":"asOf values come from each row's scores.asOf. They are not a live price or latency pull."},"rankContract":{"style":"editorial_weighted","notAnElo":true,"notComparableTo":["lmarena_elo","artificial_analysis_intelligence_index","openrouter_throughput_p50"],"sortMeans":"Higher catalog score first within this JTBD or category. Not cross-category comparable."},"priceSort":{"available":true,"param":"sort=price","direction":"ascending_cheapest_sourced_input_first","coverage":{"considered":16,"withSourcedInputTokenPrice":2,"excludedFromPriceSort":14,"label":"2 of 16 candidates have a sourced chat input $/1M; 14 candidates excluded from sort=price. Browser hours are not included."}},"unavailableFilters":[{"name":"throughput","reason":"No measured tokens/sec in this catalog. Do not invent TTFT."},{"name":"context_length","reason":"No structured context-window field yet. See research/gaps.md."}],"scoring":{"scale":"0-10","lockInRisk":"higher = more lock-in / worse; overall uses 10-lockInRisk","formula":"overall = 0.25*capabilityFit + 0.18*pricePerformance + 0.15*latencyReliability + 0.15*developerDx + 0.10*privacyPosture + 0.07*(10-lockInRisk) + 0.10*maturity. Raw lockInRisk stays higher=worse; only the aggregate inverts."},"results":[{"rank":1,"providerId":"unsloth","slug":"unsloth","name":"Unsloth","tagline":"Depot OSS fine-tune default. Hosted LoRA → Predibase/Fireworks/Together; dead OpenPipe → do not resurrect…","status":"active","categoryIds":["cat-train-finetune"],"regions":["global"],"overall":8.52,"scores":{"capabilityFit":8.8,"pricePerformance":9.2,"latencyReliability":7.5,"developerDx":9,"privacyPosture":8.5,"lockInRisk":2,"maturity":7.8,"overall":8.52,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Unsloth pricing: https://unsloth.ai/pricing","Unsloth: https://unsloth.ai","Unsloth + HF Jobs: https://huggingface.co/blog/unsloth-jobs"],"notes":"Depot OSS fine-tune default. Hosted LoRA → Predibase/Fireworks/Together; dead OpenPipe → do not resurrect. Run Unsloth on Modal/RunPod/HF Jobs."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":2,"providerId":"fireworks","slug":"fireworks","name":"Fireworks AI","tagline":"Top pick for production open-model serving with real DX. Prefer over random GPU DIY when you want tokens not…","status":"active","categoryIds":["cat-inference-apis","cat-train-finetune"],"regions":["us","global"],"overall":8.35,"scores":{"capabilityFit":8.6,"pricePerformance":8.8,"latencyReliability":8.4,"developerDx":9,"privacyPosture":7.5,"lockInRisk":3.5,"maturity":8,"overall":8.35,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Fireworks AI: https://fireworks.ai","Best LLM API Providers (Fireworks blog): https://fireworks.ai/blog/best-llm-api-providers"],"notes":"Top pick for production open-model serving with real DX. Prefer over random GPU DIY when you want tokens not ops."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":3,"providerId":"llama-parse","slug":"llama-parse","name":"LlamaParse","tagline":"Depot pick for document-parse (PDF/Office → LLM-ready markdown/JSON). Unstructured when you need ETL…","status":"active","categoryIds":["cat-search-scrape","cat-train-finetune"],"regions":["global","us","eu"],"overall":8.22,"scores":{"capabilityFit":9,"pricePerformance":7.8,"latencyReliability":8.4,"developerDx":8.8,"privacyPosture":8,"lockInRisk":4.8,"maturity":8.2,"overall":8.22,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["LlamaParse pricing: https://www.llamaindex.ai/pricing","LlamaParse credit rates: https://developers.llamaindex.ai/llamaparse/general/pricing/"],"notes":"Depot pick for document-parse (PDF/Office → LLM-ready markdown/JSON). Unstructured when you need ETL connectors/VPC pipelines; Reducto when agentic extraction accuracy on nasty forms beats LlamaParse in a bake-off."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":4,"providerId":"together","slug":"together","name":"Together AI","tagline":"Best catalog breadth for OSS models. Watch minimums and lifetime spend gates before you design around a gated…","status":"active","categoryIds":["cat-inference-apis","cat-train-finetune","cat-gpu-cloud"],"regions":["us","global"],"overall":8.2,"scores":{"capabilityFit":8.5,"pricePerformance":9,"latencyReliability":8,"developerDx":8.4,"privacyPosture":7.2,"lockInRisk":3.5,"maturity":8.2,"overall":8.2,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Together AI: https://www.together.ai","Together pricing: https://www.together.ai/pricing","Together docs: https://docs.together.ai"],"notes":"Best catalog breadth for OSS models. Watch minimums and lifetime spend gates before you design around a gated model."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":0.15,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":0.15,"skuId":null,"sku":null,"comparison":"min sourced input SKU among candidates; not quality-adjusted","usdPerMillionInputTokens":0.15}},{"rank":5,"providerId":"unstructured","slug":"unstructured","name":"Unstructured","tagline":"Best when you want connector-heavy document ETL or to self-host the OSS partitioner. LlamaParse remains the…","status":"active","categoryIds":["cat-search-scrape","cat-train-finetune"],"regions":["global","us"],"overall":8.12,"scores":{"capabilityFit":8.4,"pricePerformance":8.2,"latencyReliability":8.2,"developerDx":8,"privacyPosture":8.6,"lockInRisk":3.8,"maturity":8.2,"overall":8.12,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Unstructured pricing: https://unstructured.io/pricing","Unstructured: https://unstructured.io"],"notes":"Best when you want connector-heavy document ETL or to self-host the OSS partitioner. LlamaParse remains the agent-builder default parser; Reducto for max extraction accuracy."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":6,"providerId":"weights-biases","slug":"weights-biases","name":"Weights & Biases","tagline":"Use for training/fine-tune discipline. For pure agent request tracing, Langfuse/Helicone are leaner.","status":"active","categoryIds":["cat-observability","cat-train-finetune"],"regions":["global"],"overall":8.04,"scores":{"capabilityFit":8.8,"pricePerformance":6.8,"latencyReliability":9,"developerDx":8.2,"privacyPosture":7.8,"lockInRisk":5.5,"maturity":9.4,"overall":8.04,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Weights & Biases: https://wandb.ai"],"notes":"Use for training/fine-tune discipline. For pure agent request tracing, Langfuse/Helicone are leaner."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":7,"providerId":"reducto","slug":"reducto","name":"Reducto","tagline":"Use when LlamaParse Agentic still drops tables/forms. Depot still picks LlamaParse for default document-parse…","status":"active","categoryIds":["cat-search-scrape","cat-train-finetune"],"regions":["global","us","eu"],"overall":8.02,"scores":{"capabilityFit":9,"pricePerformance":7.2,"latencyReliability":8.2,"developerDx":8.4,"privacyPosture":8.6,"lockInRisk":4.5,"maturity":7.4,"overall":8.02,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Reducto pricing: https://reducto.ai/pricing","Reducto: https://reducto.ai"],"notes":"Use when LlamaParse Agentic still drops tables/forms. Depot still picks LlamaParse for default document-parse DX/ecosystem."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":8,"providerId":"lambda","slug":"lambda","name":"Lambda","tagline":"Best boring GPU cloud for research labs who want clusters without CoreWeave enterprise theater.","status":"active","categoryIds":["cat-gpu-cloud","cat-train-finetune"],"regions":["us"],"overall":7.97,"scores":{"capabilityFit":8.8,"pricePerformance":6.8,"latencyReliability":8.8,"developerDx":8.5,"privacyPosture":7.8,"lockInRisk":5.5,"maturity":8.6,"overall":7.97,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Lambda: https://lambda.ai"],"notes":"Best boring GPU cloud for research labs who want clusters without CoreWeave enterprise theater."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":9,"providerId":"vertex-ai","slug":"vertex-ai","name":"Google Vertex AI","tagline":"Enterprise Gemini path. Use AI Studio for prototypes, Vertex when security review starts asking questions.","status":"active","categoryIds":["cat-inference-apis","cat-train-finetune"],"regions":["global"],"overall":7.96,"scores":{"capabilityFit":9,"pricePerformance":7,"latencyReliability":9,"developerDx":7.2,"privacyPosture":8.8,"lockInRisk":7.5,"maturity":9.6,"overall":7.96,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Vertex AI: https://cloud.google.com/vertex-ai","Vertex AI pricing: https://cloud.google.com/vertex-ai/pricing"],"notes":"Enterprise Gemini path. Use AI Studio for prototypes, Vertex when security review starts asking questions."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":0.25,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":0.25,"skuId":null,"sku":null,"comparison":"min sourced input SKU among candidates; not quality-adjusted","usdPerMillionInputTokens":0.25}},{"rank":10,"providerId":"huggingface-inference","slug":"huggingface-inference","name":"Hugging Face Inference","tagline":"Perfect for Hub-native workflows and custom models. For hard production latency, graduate to…","status":"active","categoryIds":["cat-inference-apis","cat-train-finetune"],"regions":["global","us","eu"],"overall":7.95,"scores":{"capabilityFit":8.4,"pricePerformance":7.2,"latencyReliability":7.4,"developerDx":8.6,"privacyPosture":7.8,"lockInRisk":3.5,"maturity":9.2,"overall":7.95,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Hugging Face Inference Endpoints: https://huggingface.co/inference-endpoints","HF Hub: https://huggingface.co"],"notes":"Perfect for Hub-native workflows and custom models. For hard production latency, graduate to Fireworks/Together/Groq or your own GPUs."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":11,"providerId":"lightning-ai","slug":"lightning-ai","name":"Lightning AI","tagline":"Use when the team already lives in Lightning/PyTorch notebooks. Together/Unsloth remain Depot finetune…","status":"active","categoryIds":["cat-train-finetune","cat-gpu-cloud","cat-cpu-compute"],"regions":["global","us"],"overall":7.93,"scores":{"capabilityFit":8.6,"pricePerformance":7,"latencyReliability":8.2,"developerDx":9,"privacyPosture":7.4,"lockInRisk":4.8,"maturity":8.4,"overall":7.93,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Lightning AI pricing: https://lightning.ai/pricing","Lightning AI: https://lightning.ai"],"notes":"Use when the team already lives in Lightning/PyTorch notebooks. Together/Unsloth remain Depot finetune defaults; Modal for Python serverless agents."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":12,"providerId":"predibase","slug":"predibase","name":"Predibase","tagline":"Alive. Prefer when you serve dozens of LoRA adapters on shared GPUs. Together/Fireworks remain simpler…","status":"active","categoryIds":["cat-train-finetune","cat-inference-apis"],"regions":["us","global"],"overall":7.89,"scores":{"capabilityFit":8.4,"pricePerformance":8,"latencyReliability":7.8,"developerDx":8.2,"privacyPosture":7.8,"lockInRisk":4.5,"maturity":7.8,"overall":7.89,"kind":"curated_estimate","confidence":"medium","asOf":"2026-09-14","sources":["Predibase: https://predibase.com","LoRAX GitHub: https://github.com/predibase/lorax","Predibase plans (secondary): https://apis.io/plans/predibase/predibase-plans-pricing/"],"notes":"Alive. Prefer when you serve dozens of LoRA adapters on shared GPUs. Together/Fireworks remain simpler defaults for one-off SFT."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":13,"providerId":"aws-gpu","slug":"aws-gpu","name":"AWS GPU (EC2/P5/SageMaker)","tagline":"Use when AWS is destiny. For greenfield agent GPUs, neoclouds win on price and speed-to-pod.","status":"active","categoryIds":["cat-gpu-cloud","cat-train-finetune"],"regions":["global"],"overall":7.72,"scores":{"capabilityFit":9.4,"pricePerformance":4.8,"latencyReliability":9.5,"developerDx":7,"privacyPosture":9,"lockInRisk":8,"maturity":9.9,"overall":7.72,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["AWS EC2 GPU instances: https://aws.amazon.com/ec2/instance-types/","Amazon SageMaker: https://aws.amazon.com/sagemaker/"],"notes":"Use when AWS is destiny. For greenfield agent GPUs, neoclouds win on price and speed-to-pod."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":14,"providerId":"nvidia-nim","slug":"nvidia-nim","name":"NVIDIA NIM / NGC","tagline":"Choose when you self-host inference on NVIDIA GPUs and want blessed containers. For serverless tokens use…","status":"active","categoryIds":["cat-inference-apis","cat-gpu-cloud","cat-train-finetune"],"regions":["global","us"],"overall":7.66,"scores":{"capabilityFit":8.6,"pricePerformance":7,"latencyReliability":8,"developerDx":6.8,"privacyPosture":8.5,"lockInRisk":6,"maturity":9,"overall":7.66,"kind":"curated_estimate","confidence":"medium","asOf":"2026-10-19","sources":["NVIDIA NIM: https://www.nvidia.com/en-us/ai/","NVIDIA NGC: https://catalog.ngc.nvidia.com","NIM docs: https://docs.nvidia.com/nim/"],"notes":"Choose when you self-host inference on NVIDIA GPUs and want blessed containers. For serverless tokens use Fireworks/Groq."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":15,"providerId":"anyscale","slug":"anyscale","name":"Anyscale","tagline":"Default when your agent stack already is Ray or you need serious multi-node Python. For simple serverless GPU…","status":"active","categoryIds":["cat-gpu-cloud","cat-cpu-compute","cat-train-finetune"],"regions":["global","us"],"overall":7.46,"scores":{"capabilityFit":8.2,"pricePerformance":6.5,"latencyReliability":8,"developerDx":7.5,"privacyPosture":7.8,"lockInRisk":5.5,"maturity":8.2,"overall":7.46,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14","sources":["Anyscale pricing: https://www.anyscale.com/pricing","Anyscale: https://www.anyscale.com","Ray: https://www.ray.io"],"notes":"Default when your agent stack already is Ray or you need serious multi-node Python. For simple serverless GPU prefer Modal/RunPod."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}},{"rank":16,"providerId":"databricks-mosaic","slug":"databricks-mosaic","name":"Databricks Mosaic AI","tagline":"Pick only when your data/platform already is Databricks. Otherwise Bedrock/Vertex or direct APIs.","status":"active","categoryIds":["cat-inference-apis","cat-train-finetune","cat-vector-memory"],"regions":["global","us"],"overall":7.11,"scores":{"capabilityFit":8.4,"pricePerformance":4.8,"latencyReliability":8.5,"developerDx":6.8,"privacyPosture":8.2,"lockInRisk":7.8,"maturity":8.8,"overall":7.11,"kind":"curated_estimate","confidence":"medium","asOf":"2026-09-14","sources":["Databricks Mosaic AI: https://www.databricks.com/product/machine-learning","Databricks pricing: https://www.databricks.com/product/pricing","AI-ready data platforms 2026: https://www.nx1.io/blog/top-ai-ready-data-platforms-enterprise-multi-cloud-2026"],"notes":"Pick only when your data/platform already is Databricks. Otherwise Bedrock/Vertex or direct APIs."},"isDepotPick":false,"isRunnerUp":false,"sourcedInputUsdPerMillionTokens":null,"priceSort":{"skuKind":"chat_completion_input","unit":null,"amountUsd":null,"skuId":null,"sku":null,"comparison":"no matching sourced chat input $/1M; other units were not borrowed","usdPerMillionInputTokens":null}}],"quote":null,"editorialPriorAsOf":"2026-09-14","pricingLastVerifiedAt":"2026-10-27","jtbd":null,"jtbdAssumed":false,"assumptionNote":null,"defaultJtbd":"coding-agent","crossCategory":false,"note":"Cross-category / category-only board — overall scores are not comparable across categories."}