↑↓ move↵ openesc close

Overage / LLM APIs

Baseten pricing and rate limits

LLM APIswww.baseten.coReport a correctionChange history (0)

Verified 2026-10-24 (1 day ago)Source: www.baseten.co/pricing

Models and cost at your volume

Beam: $0.64 / mo base $0 + Input tokens overage $0.40 + Output tokens overage $0.24

Uses the shared Overage cost function. Example volumes you can edit, not vendor data. Cached, batch and cache-write prices are listed below but not added to this total.

Baseten models, USD per 1M tokens, sortable
Beamunlisted$0.40$0.40 source$1.20$1.20Try Model API source$0.04$0.04 sourceunlistedunlistedunlisted$0.64
Muse Spark Openunlisted$1.25$1.25 source$4.25$4.25Try Model API source$0.15$0.15 sourceunlistedunlistedunlisted$2.10
GLM-5.3 Fastunlisted$2.10$2.10 source$6.60$6.60Try Model API source$0.21$0.21 sourceunlistedunlistedunlisted$3.42
GLM-5.3unlisted$1.40$1.40 source$4.40$4.40Try Model API source$0.14$0.14 sourceunlistedunlistedunlisted$2.28
GLM-5.3-Flashunlisted$0.15$0.15 source$0.50$0.50Try Model API source$0.03$0.03 sourceunlistedunlistedunlisted$0.25
GLM-5.2unlisted$1.40$1.40 source$4.40$4.40Try Model API source$0.14$0.14 sourceunlistedunlistedunlisted$2.28
GLM-5.2 Fastunlisted$2.10$2.10 source$6.60$6.60Try Model API source$0.21$0.21 sourceunlistedunlistedunlisted$3.42
DeepSeek V4.1 Flash 1017unlisted$0.30$0.30 source$1.20$1.20Try Model API source$0.007$0.007 sourceunlistedunlistedunlisted$0.54
DeepSeek V4.1 Flash Fastunlisted$0.60$0.60 source$2.40$2.40Try Model API source$0.014$0.014 sourceunlistedunlistedunlisted$1.08
DeepSeek V4.1 Flashunlisted$0.30$0.30 source$1.20$1.20Try Model API source$0.007$0.007 sourceunlistedunlistedunlisted$0.54
DeepSeek-V4-Flash-0731unlisted$0.13$0.13 source$0.26$0.26Try Model API source$0.028$0.028 sourceunlistedunlistedunlisted$0.182
DeepSeek V4 Pro 0813unlisted$1.32$1.32 source$3.96$3.96Try Model API source$0.132$0.132 sourceunlistedunlistedunlisted$2.112
Kimi K3unlisted$3$3.00 source$15$15.00Try Model API source$0.30$0.30 sourceunlistedunlistedunlisted$6
Nemotron 3.5 Super VLunlisted$0.20$0.20 source$0.50$0.50Try Model API source$0.04$0.04 sourceunlistedunlistedunlisted$0.30
NVIDIA Nemotron 3 Ultraunlisted$0.60$0.60 source$2.40$2.40Try Model API source$0.12$0.12 sourceunlistedunlistedunlisted$1.08
GPT OSS 120Bunlisted$0.10$0.10 source$0.50$0.50Try Model API sourceunlistedunlistedunlistedunlisted$0.20

USD per 1M tokens. "+" marks a model whose price changes with volume; the standard band is shown. Context in tokens (16 models).

Plans

Monthly cost per tier at the volume entered above
TierMonthly costBreakdown
Basic$0 / mo$0 / mo cheapestbase $0
ProContact salesunlistedContact sales
EnterpriseContact salesunlistedContact sales

Cheapest: Basic at $0/mo.

Example volumes you can edit; not vendor data. Costs use the shared Overage cost function, identical to the API and MCP. Usage the vendor does not price is excluded, never guessed. Optional add-ons are not included in these totals. Overage marked pay-as-you-go applies only if you enable it; otherwise the allowance is a hard cap.

Tiers

Baseten tiers: price, included allowances, overage rates, limits and features
ItemBasicProEnterprise
Base price
Price$0 / mo$0 per month, pay as you go sourceContact salesprice unlistedContact salesprice unlisted
Features
soc2yesunlistedunlisted
support slackunlistedyesunlisted

Prices in USD, per the vendor's billing period. Hover or focus a number for the line it came from, with a link to the stored snapshot. "unlisted" means the vendor does not publish it; we never fill the gap.

Rate limits

No rate limits recorded for this service: unlisted.

Change timeline

No changes recorded.

Tracking began 2026-10-24; no change has been detected since.

Sources

Captured source pages and their last snapshot
URLKindLast capturedSnapshot
www.baseten.co/pricingpricing2026-10-24snap_baseten-pricing-0_20261023T173933Z

Report a correction

Spotted a wrong or missing number on Baseten? Send the field, the value you see and a source link. Reports with a source are reviewed first.