{"subject":{"id":"unsloth","slug":"unsloth","name":"Unsloth","tagline":"Depot OSS fine-tune default. Hosted LoRA → Predibase/Fireworks/Together; dead OpenPipe → do not resurrect…","website":"https://unsloth.ai","status":"active","overall":8.52,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","lastReviewed":"2026-09-14","categoryIds":["cat-train-finetune"],"regions":["global"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14 (unsloth.ai/pricing): Free OSS local training (4/16-bit LoRA, Llama/Mistral/Gemma). Pro/Enterprise = contact-sales speed/VRAM multi-GPU claims (2.5×–30× marketing). No Unsloth-hosted GPU rate card — pair with HF Jobs / RunPod / Modal for cloud GPUs. HF blog docum…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://unsloth.ai","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."}},"relatedJtbdSlugs":["finetune","lora-serving-distillation"],"alternatives":[{"id":"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…","website":"https://www.together.ai","status":"active","overall":8.2,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.32,"roles":["same_jtbd_pick","same_jtbd_runner"],"sharedJtbdSlugs":["finetune","lora-serving-distillation"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":0.15,"rows":[{"id":"together-llama-33-70b-input","providerId":"together","sku":"Llama 3.3 70B","unit":"usd_per_million_input_tokens","amountUsd":1.04,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.04,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Serverless price-per-1M-tokens table. A separate fine-tune table also lists Llama 3.3 70B at different numbers and was not used."},{"id":"together-llama-33-70b-output","providerId":"together","sku":"Llama 3.3 70B","unit":"usd_per_million_output_tokens","amountUsd":1.04,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.04,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":null},{"id":"together-deepseek-v4-pro-0813-input","providerId":"together","sku":"DeepSeek V4 Pro 0813","unit":"usd_per_million_input_tokens","amountUsd":1.32,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1.32,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Serverless price-per-1M-tokens table. A separate fine-tune table also lists Llama 3.3 70B at different numbers and was not used."},{"id":"together-deepseek-v4-pro-0813-output","providerId":"together","sku":"DeepSeek V4 Pro 0813","unit":"usd_per_million_output_tokens","amountUsd":3.96,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":3.96,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":null},{"id":"together-deepseek-v4-pro-0813-cached","providerId":"together","sku":"DeepSeek V4 Pro 0813","unit":"usd_per_million_cached_input_tokens","amountUsd":0.13,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.13,"normalizationReason":"cached_input_not_a_single_rate","priceSortEligible":false,"qualifier":null},{"id":"together-gpt-oss-120b-input","providerId":"together","sku":"gpt-oss-120B","unit":"usd_per_million_input_tokens","amountUsd":0.15,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.15,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Serverless price-per-1M-tokens table. A separate fine-tune table also lists Llama 3.3 70B at different numbers and was not used."},{"id":"together-gpt-oss-120b-output","providerId":"together","sku":"gpt-oss-120B","unit":"usd_per_million_output_tokens","amountUsd":0.6,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.6,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":null},{"id":"together-glm-53-flash-input","providerId":"together","sku":"GLM-5.3-Flash","unit":"usd_per_million_input_tokens","amountUsd":0.15,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.15,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Serverless price-per-1M-tokens table. A separate fine-tune table also lists Llama 3.3 70B at different numbers and was not used."},{"id":"together-glm-53-flash-output","providerId":"together","sku":"GLM-5.3-Flash","unit":"usd_per_million_output_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":null},{"id":"together-glm-53-flash-cached","providerId":"together","sku":"GLM-5.3-Flash","unit":"usd_per_million_cached_input_tokens","amountUsd":0.03,"currency":"USD","sourceUrl":"https://www.together.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.03,"normalizationReason":"cached_input_not_a_single_rate","priceSortEligible":false,"qualifier":null}],"notesExcerpt":"As of 2026-09-14: Open-model inference + fine-tune on one OpenAI-compatible API; competitive per-token rates (often ~$0.15–$0.90/MTok class depending on model). Strong for Llama/Qwen/DeepSeek families; Dedicated endpoints available.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://www.together.ai","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"decideHint":"/api/decide?jtbd=finetune","human":"/providers/together","compare":"/compare/unsloth-vs-together"},{"id":"predibase","slug":"predibase","name":"Predibase","tagline":"Alive. Prefer when you serve dozens of LoRA adapters on shared GPUs. Together/Fireworks remain simpler…","website":"https://predibase.com","status":"active","overall":7.89,"scoreKind":"curated_estimate","confidence":"medium","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.63,"roles":["same_jtbd_runner","same_jtbd_pick"],"sharedJtbdSlugs":["finetune","lora-serving-distillation"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14: Active managed LoRA/QLoRA + RL fine-tune (Rubrik-era Predibase); LoRAX OSS multi-adapter serving. Public token rates still not a clean first-party matrix — secondary sources cite serverless from ~$0.20/M and A10G-class GPUs ~$1.82/hr. Enterprise/VPC sales-led. C…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://predibase.com","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=finetune","human":"/providers/predibase","compare":"/compare/unsloth-vs-predibase"},{"id":"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…","website":"https://fireworks.ai","status":"active","overall":8.35,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.17,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["finetune","lora-serving-distillation"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"multiple_sourced_token_skus","shape":"sourced_rows","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"fireworks-embed-to-150m","providerId":"fireworks","sku":"Embeddings up to 150M params","unit":"usd_per_million_input_tokens","amountUsd":0.008,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.008,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"parameter-count bucket, not a named chat model"},{"id":"fireworks-embed-150-350m","providerId":"fireworks","sku":"Embeddings 150M-350M params","unit":"usd_per_million_input_tokens","amountUsd":0.016,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.016,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"parameter-count bucket"},{"id":"fireworks-embed-qwen3-8b","providerId":"fireworks","sku":"Qwen3 8B","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":"embedding_sku_excluded_from_provider_sort","priceSortEligible":false,"qualifier":"listed in the embeddings section after the parameter buckets"},{"id":"fireworks-train-lora-sft-to-16b","providerId":"fireworks","sku":"Managed training LoRA SFT up to 16B","unit":"usd_per_million_train_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":"training_token_price_not_inference","priceSortEligible":false,"qualifier":"per 1M training tokens"},{"id":"fireworks-gpu-h100","providerId":"fireworks","sku":"H100 80 GB","unit":"usd_per_gpu_hour","amountUsd":8,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-h200","providerId":"fireworks","sku":"H200 141 GB","unit":"usd_per_gpu_hour","amountUsd":8,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-b200","providerId":"fireworks","sku":"B200 180 GB","unit":"usd_per_gpu_hour","amountUsd":13,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-b300","providerId":"fireworks","sku":"B300 288 GB","unit":"usd_per_gpu_hour","amountUsd":15,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-gpu-gb300","providerId":"fireworks","sku":"GB300 288 GB","unit":"usd_per_gpu_hour","amountUsd":20,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_gpu_hour","priceSortEligible":false,"qualifier":"on-demand deployments; per-minute column also shown and not converted; reconfirmed 2026-10-27 (v0.12.139): page says 'Region-restricted deployments are priced at a 1.5x premium' (not stored as a separate row)"},{"id":"fireworks-serverless-chat-unavailable","providerId":"fireworks","sku":"serverless chat models","unit":"usd_per_million_input_tokens","amountUsd":null,"currency":"USD","sourceUrl":"https://fireworks.ai/pricing","asOf":"2026-10-03","normalizationStatus":"ambiguous","normalizedUsdPerMillionTokens":null,"normalizationReason":"page_points_elsewhere_for_serverless_chat_matrix","priceSortEligible":false,"qualifier":"fireworks.ai/pricing says to visit full pricing documentation for Standard/Priority/Fast serverless token rates. Those figures were not on this page and were not guessed."}],"notesExcerpt":"Serverless per-token + on-demand GPU; day-0 OSS model support; post-training stack. Free credits often available.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://fireworks.ai","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"decideHint":"/api/decide?jtbd=finetune","human":"/providers/fireworks","compare":"/compare/unsloth-vs-fireworks"},{"id":"lightning-ai","slug":"lightning-ai","name":"Lightning AI","tagline":"Use when the team already lives in Lightning/PyTorch notebooks. Together/Unsloth remain Depot finetune…","website":"https://lightning.ai","status":"active","overall":7.93,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.59,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["finetune","lora-serving-distillation"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14 (lightning.ai/pricing): Studio/cloud GPU hours on a public card — H100 New 80GB ~$4.50/hr on-demand (interruptible lower, ~$3.82–$4.58 class); T4/L4/A100 families also listed. Free Studio + credits to start. Team/seat SKUs (Pro/Teams) sit beside GPU-hour billing …","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://lightning.ai","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"decideHint":"/api/decide?jtbd=finetune","human":"/providers/lightning-ai","compare":"/compare/unsloth-vs-lightning-ai"},{"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.","website":"https://modal.com","status":"active","overall":8.44,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-10-19","deltaOverallVsSubject":-0.08,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["finetune"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unit_mismatch","normalizationReason":"unit_mismatch","shape":"sourced_rows","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"modal-nvidia-b300-usd-per-gpu-second","providerId":"modal","sku":"Nvidia B300","unit":"usd_per_gpu_second","amountUsd":0.001972,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-b200-usd-per-gpu-second","providerId":"modal","sku":"Nvidia B200","unit":"usd_per_gpu_second","amountUsd":0.001736,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-h200-sxm-usd-per-gpu-second","providerId":"modal","sku":"Nvidia H200 SXM","unit":"usd_per_gpu_second","amountUsd":0.001261,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-h100-sxm5-usd-per-gpu-second","providerId":"modal","sku":"Nvidia H100 SXM5","unit":"usd_per_gpu_second","amountUsd":0.001097,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-rtx-pro-6000-usd-per-gpu-second","providerId":"modal","sku":"Nvidia RTX PRO 6000","unit":"usd_per_gpu_second","amountUsd":0.000842,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-a100-80gb-usd-per-gpu-second","providerId":"modal","sku":"Nvidia A100 80GB","unit":"usd_per_gpu_second","amountUsd":0.000694,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-a100-40gb-usd-per-gpu-second","providerId":"modal","sku":"Nvidia A100 40GB","unit":"usd_per_gpu_second","amountUsd":0.000583,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-l40s-usd-per-gpu-second","providerId":"modal","sku":"Nvidia L40S","unit":"usd_per_gpu_second","amountUsd":0.000542,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-a10-usd-per-gpu-second","providerId":"modal","sku":"Nvidia A10","unit":"usd_per_gpu_second","amountUsd":0.000306,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-l4-usd-per-gpu-second","providerId":"modal","sku":"Nvidia L4","unit":"usd_per_gpu_second","amountUsd":0.000222,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-nvidia-t4-usd-per-gpu-second","providerId":"modal","sku":"Nvidia T4","unit":"usd_per_gpu_second","amountUsd":0.000164,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gpu_second","priceSortEligible":false,"qualifier":"Per-second rate shown with the per-second toggle. Not multiplied into an hour. Reconfirmed 2026-10-27 (v0.12.140): page also says 'Region selection 1.15 - 1.75x base prices' and 'Non-preemptible execution 3x base prices' (not stored as separate rows)."},{"id":"modal-cpu-physical-core-usd-per-core-second","providerId":"modal","sku":"CPU physical core","unit":"usd_per_core_second","amountUsd":0.0000131,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_core_second","priceSortEligible":false,"qualifier":"Physical core (2 vCPU). Minimum 0.125 cores."},{"id":"modal-memory-usd-per-gib-second","providerId":"modal","sku":"Memory","unit":"usd_per_gib_second","amountUsd":0.00000222,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gib_second","priceSortEligible":false,"qualifier":"Container memory."},{"id":"modal-sandbox-cpu-usd-per-core-second","providerId":"modal","sku":"Sandbox CPU","unit":"usd_per_core_second","amountUsd":0.00003942,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_core_second","priceSortEligible":false,"qualifier":"Modal Sandbox rate (page: 'Modal Sandbox pricing', 'CPU (non-preemptible)'; 'Sandboxes are billed at non-preemptible rates of 3x list price'), separate from the default CPU rate."},{"id":"modal-sandbox-memory-usd-per-gib-second","providerId":"modal","sku":"Sandbox memory","unit":"usd_per_gib_second","amountUsd":0.00000667,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gib_second","priceSortEligible":false,"qualifier":"Sandbox memory (page: 'Memory (non-preemptible)' under 'Modal Sandbox pricing')."},{"id":"modal-volumes-usd-per-gib-month","providerId":"modal","sku":"Volumes","unit":"usd_per_gib_month","amountUsd":0.09,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gib_month","priceSortEligible":false,"qualifier":"Includes 1 TiB/mo free, not folded into this rate."},{"id":"modal-network-egress-usd-per-gib","providerId":"modal","sku":"Network egress","unit":"usd_per_gib","amountUsd":0.04,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_gib","priceSortEligible":false,"qualifier":"See plan for included usage."},{"id":"modal-team-plan-usd-per-month","providerId":"modal","sku":"Team plan","unit":"usd_per_month","amountUsd":250,"currency":"USD","sourceUrl":"https://modal.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_month","priceSortEligible":false,"qualifier":"Plus compute. $100/mo credits not subtracted."}],"notesExcerpt":"As of 2026-10-24 (modal.com/pricing, fetched 2026-10-24): Python-native serverless GPU/CPU billed per second of compute ('You never pay for idle resources'). GPU list rates per second: H100 SXM5 '$0.001097', H200 SXM '$0.001261', B200 '$0.001736', A100 80 GB '$0.000694', L40S '$0…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://modal.com","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"decideHint":"/api/decide?jtbd=finetune","human":"/providers/modal","compare":"/compare/unsloth-vs-modal"},{"id":"huggingface-inference","slug":"huggingface-inference","name":"Hugging Face Inference","tagline":"Perfect for Hub-native workflows and custom models. For hard production latency, graduate to…","website":"https://endpoints.huggingface.co","status":"active","overall":7.95,"scoreKind":"curated_estimate","confidence":"high","scoreAsOf":"2026-09-14","deltaOverallVsSubject":-0.57,"roles":["same_jtbd_runner"],"sharedJtbdSlugs":["finetune"],"pricing":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unit_mismatch","normalizationReason":"unit_mismatch","shape":"sourced_rows","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[{"id":"huggingface-inference-aws-nvidia-t4-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-t4 x1","unit":"usd_per_gpu_hour","amountUsd":0.5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-t4-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-t4 x4","unit":"usd_per_instance_hour","amountUsd":3,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-t4 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l4-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l4 x1","unit":"usd_per_gpu_hour","amountUsd":0.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l4-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l4 x4","unit":"usd_per_instance_hour","amountUsd":3.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-l4 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a10g-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a10g x1","unit":"usd_per_gpu_hour","amountUsd":1,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a10g-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a10g x4","unit":"usd_per_instance_hour","amountUsd":5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-a10g x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l40s-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l40s x1","unit":"usd_per_gpu_hour","amountUsd":1.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l40s-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l40s x4","unit":"usd_per_instance_hour","amountUsd":8.3,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-l40s x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-l40s-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-l40s x8","unit":"usd_per_instance_hour","amountUsd":23.5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-l40s x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a100-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a100 x1","unit":"usd_per_gpu_hour","amountUsd":2.5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a100-x2-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a100 x2","unit":"usd_per_instance_hour","amountUsd":5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-a100 x2 instance (2 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 2. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a100-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a100 x4","unit":"usd_per_instance_hour","amountUsd":10,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-a100 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-a100-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-a100 x8","unit":"usd_per_instance_hour","amountUsd":20,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-a100 x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-h200-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-h200 x1","unit":"usd_per_gpu_hour","amountUsd":5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-h200-x2-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-h200 x2","unit":"usd_per_instance_hour","amountUsd":10,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-h200 x2 instance (2 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 2. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-h200-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-h200 x4","unit":"usd_per_instance_hour","amountUsd":20,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-h200 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-nvidia-h200-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"aws nvidia-h200 x8","unit":"usd_per_instance_hour","amountUsd":40,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole aws nvidia-h200 x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-t4-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-t4 x1","unit":"usd_per_gpu_hour","amountUsd":0.5,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-l4-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-l4 x1","unit":"usd_per_gpu_hour","amountUsd":0.7,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-l4-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-l4 x4","unit":"usd_per_instance_hour","amountUsd":3.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-l4 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-a100-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-a100 x1","unit":"usd_per_gpu_hour","amountUsd":3.6,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-a100-x2-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-a100 x2","unit":"usd_per_instance_hour","amountUsd":7.2,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-a100 x2 instance (2 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 2. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-a100-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-a100 x4","unit":"usd_per_instance_hour","amountUsd":14.4,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-a100 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-a100-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-a100 x8","unit":"usd_per_instance_hour","amountUsd":28.8,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-a100 x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-h100-x1-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-h100 x1","unit":"usd_per_gpu_hour","amountUsd":10,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"gpu_hour_not_coerced_to_per_million_tokens","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Single-GPU (x1) instance: the instance-hour rate is the GPU-hour rate. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-h100-x2-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-h100 x2","unit":"usd_per_instance_hour","amountUsd":20,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-h100 x2 instance (2 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 2. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-h100-x4-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-h100 x4","unit":"usd_per_instance_hour","amountUsd":40,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-h100 x4 instance (4 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 4. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-nvidia-h100-x8-usd-per-gpu-hour","providerId":"huggingface-inference","sku":"gcp nvidia-h100 x8","unit":"usd_per_instance_hour","amountUsd":80,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_instance_hour","priceSortEligible":false,"qualifier":"Dedicated Inference Endpoints hourly rate for the whole gcp nvidia-h100 x8 instance (8 GPUs): the GPU Instances table prints 'Hourly rate' per instance next to a separate 'GPUs' column. Instance-hour price, not a per-GPU rate, never divided by 8. Billed per minute. CPU instance table not copied. Deprecated Ice Lake rows omitted. Unit label corrected 2026-10-27 (v0.12.138) from usd_per_gpu_hour; amount unchanged, re-checked on the page 2026-10-27."},{"id":"huggingface-inference-aws-inf2-x1-usd-per-hour","providerId":"huggingface-inference","sku":"aws inf2 x1","unit":"usd_per_hour","amountUsd":0.75,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"Inferentia2 accelerator hour. Not a token price. Re-checked on the page 2026-10-27."},{"id":"huggingface-inference-gcp-tpu-v5e-1x1-usd-per-hour","providerId":"huggingface-inference","sku":"gcp tpu v5e 1x1","unit":"usd_per_hour","amountUsd":1.2,"currency":"USD","sourceUrl":"https://huggingface.co/docs/inference-endpoints/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"TPU v5e accelerator hour. Not a token price. Re-checked on the page 2026-10-27."}],"notesExcerpt":"Inference Providers (pay-as-you-go access to partner inference providers plus Hugging Face's own hf-inference provider) + dedicated Inference Endpoints ('Pay for what you use, per minute' per https://endpoints.huggingface.co, fetched 2026-10-25; instance rates are the price rows:…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://endpoints.huggingface.co","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"decideHint":"/api/decide?jtbd=finetune","human":"/providers/huggingface-inference","compare":"/compare/unsloth-vs-huggingface-inference"}],"rankContract":{"style":"editorial_weighted","notAnElo":true,"note":"deltaOverallVsSubject is Depot overall (0–10) minus the subject. It is not Arena Elo and not an Artificial Analysis index."},"freshness":{"scoreAsOfMin":"2026-09-14","scoreAsOfMax":"2026-10-19","contractAsOf":"2026-10-03"},"honesty":["Alternatives are other catalog providers that share a JTBD as pick or runner-up. If fewer than three exist, same-category active providers fill the list and are labeled same_category.","Overall deltas are catalog scores. kind=curated_estimate is not a lab measurement.","Pricing rows are sourced or explicitly null. Do not parse pricingNotes. A single normalized USD figure is set only for a provider with exactly one token row."],"links":{"human":"/alternatives/unsloth","machine":"/api/alternatives?provider=unsloth","provider":"/api/providers/unsloth","canonical":"/api/canonical"}}