↑↓ move↵ openesc close

Overage / Compare / LLM APIs

Baseten vs Replicate pricing

Verified 2026-10-24 (1 day ago)Source: Baseten: www.baseten.co/pricing, Replicate: replicate.com/pricingVerified shows the older of the two.

Monthly cost at three volumes

Monthly cost of Baseten and Replicate at three volumes and at your own
VolumeBasetenReplicate
small1M input, 200K output$0.182 / moDeepSeek-V4-Flash-0731$5.75 / modeepseek-ai/deepseek-r1
growing50M input, 10M output$9.10 / moDeepSeek-V4-Flash-0731$287.50 / modeepseek-ai/deepseek-r1
scale1B input, 200M output$182 / moDeepSeek-V4-Flash-0731$5,750 / modeepseek-ai/deepseek-r1
your volumeset above$9.10 / moDeepSeek-V4-Flash-0731$287.50 / modeepseek-ai/deepseek-r1

Each cell is the cheapest feasible plan, or the chosen model, at that volume, from the shared Overage cost function. "Cheapest model" only considers models with both an input and an output price listed. Volumes are example scenarios you can edit.

Cheapest model per service, USD per 1M tokens

Cheapest priced model of each service
ServiceCheapest modelInputOutputModels listed
BasetenGPT OSS 120B$0.10$0.5016
Replicatedeepseek-ai/deepseek-r1$3.75$101

Every model

Every model of both services, USD per 1M tokens
ModelServiceInputOutput
GPT OSS 120BBaseten$0.10$0.50
DeepSeek-V4-Flash-0731Baseten$0.13$0.26
GLM-5.3-FlashBaseten$0.15$0.50
Nemotron 3.5 Super VLBaseten$0.20$0.50
DeepSeek V4.1 Flash 1017Baseten$0.30$1.20
DeepSeek V4.1 FlashBaseten$0.30$1.20
BeamBaseten$0.40$1.20
DeepSeek V4.1 Flash FastBaseten$0.60$2.40
NVIDIA Nemotron 3 UltraBaseten$0.60$2.40
Muse Spark OpenBaseten$1.25$4.25
DeepSeek V4 Pro 0813Baseten$1.32$3.96
GLM-5.3Baseten$1.40$4.40
GLM-5.2Baseten$1.40$4.40
GLM-5.3 FastBaseten$2.10$6.60
GLM-5.2 FastBaseten$2.10$6.60
Kimi K3Baseten$3$15
deepseek-ai/deepseek-r1Replicate$3.75$10

Models are compared by name and price, never by position. Pick one model per service, or "Cheapest model", in the cost table above.

Tiers, aligned by position

Tiers of Baseten and Replicate aligned by position: free, entry, mid, top
PositionBasetenReplicate
Free$0 / moBasicno tier
EntryContact salesProno tier
Midno tierno tier
TopContact salesEnterpriseno tier

Tightest rate limit

Tightest documented rate limit of each service
MeasureBasetenReplicate
Tightest limitunlistedunlisted

Changes in the last 90 days

No changes recorded.

No change detected for either service in the last 90 days.