BroadRouter

Baseten API pricing

Updated

Baseten lists standard per-token prices on its own pricing page for 14 models. The cheapest is DeepSeek V4 Flash 0731 at USD 0.13 input and USD 0.26 output per 1M tokens; the dearest is Kimi K3 at USD 3 / USD 15. It publishes cached-input prices for 13 of them, plus fast prices. Checked 2026-11-14.

Baseten hosts models it does not train. By maker: DeepSeek 4, Z.ai 3, Moonshot AI 2, NVIDIA 2, Meta 1, OpenAI 1, and 1 more. 18 prices, each read from Baseten's own pricing page, checked 2026-11-14. BroadRouter is BroadNet's own site and does not sell Baseten's services. Automated re-check 2026-11-16: 18 of 18 prices still matched the provider's page.

Models with a standard price
14
Median input / output
USD 0.50 / USD 1.80
Cached-input prices
13 of 14
Cheapest host for
2 of 14 shared models

Which models is Baseten the cheapest provider for?

Of the 14 models that Baseten and at least one other provider both price at the standard tier, Baseten has the lowest price for 2, ranked on a blend of 3 input tokens to 1 output token (all of them tied with another provider at the same price). It is the dearest for 3.

Models where Baseten is the cheapest provider
ModelBaseten input / outputNext cheapestSaving on 3:1 blendProviders
Muse Spark OpenUSD 1.25 / USD 4.25Fireworks AI USD 1.25 / USD 4.25tie4
Beam 1.0 501B A23BUSD 0.40 / USD 1.20DigitalOcean USD 0.40 / USD 1.20tie3

The 6 models Baseten sells that the most other providers also sell, with Baseten's rank among them on the 3:1 blend.

Baseten on the most widely hosted models
ModelBasetenRankCheapest
GLM 5.3USD 1.40 / USD 4.406 of 24DeepInfra USD 0.5625 / USD 2.50
OpenAI GPT OSS 120BUSD 0.10 / USD 0.509 of 21CoreWeave Forge USD 0.03 / USD 0.17
GLM 5.3 FlashUSD 0.15 / USD 0.503 of 20GMI Cloud USD 0.075 / USD 0.25
GLM 5.2USD 1.40 / USD 4.405 of 19DeepInfra USD 0.5625 / USD 1.80
Kimi K3USD 3 / USD 155 of 18Chutes USD 1.85 / USD 9.50
DeepSeek V4.1 FlashUSD 0.30 / USD 1.205 of 16DeepInfra USD 0.14 / USD 0.42

Which model makers does Baseten sell?

Baseten prices models from 7 makers. DeepSeek leads with 4 models. Standard prices, USD per 1M input / output tokens.

Baseten models by maker
MakerModelsCheapest modelMedian input / output
DeepSeek4DeepSeek V4 Flash 0731 USD 0.13 / USD 0.26USD 0.30 / USD 1.20
Z.ai3GLM 5.3 Flash USD 0.15 / USD 0.50USD 1.40 / USD 4.40
Moonshot AI2Kimi K3.1 Pro USD 2 / USD 10USD 2.50 / USD 12.50
NVIDIA2NVIDIA Nemotron 3.5 Super VL USD 0.20 / USD 0.50USD 0.40 / USD 1.45
Meta1Muse Spark Open USD 1.25 / USD 4.25—
OpenAI1OpenAI GPT OSS 120B USD 0.10 / USD 0.50—
Reflection AI1Beam 1.0 501B A23B USD 0.40 / USD 1.20—

Baseten price list

USD per 1M tokens: 18 prices for 14 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means Baseten is cheaper. Of 8 hosted model prices with a maker price to compare, 0 are below the maker's and 0 above.

Baseten API prices by model
ModelTierInputCachedOutputContextvs makerSource
Beam 1.0 501B A23BstandardUSD 0.40USD 0.04USD 1.20not stated—source
DeepSeek V4 Flash 0731standardUSD 0.13USD 0.028USD 0.261,000,000—source
DeepSeek V4 Pro 0813standardUSD 1.32USD 0.132USD 3.961,000,000samesource
DeepSeek V4.1 Flashstandard
fast
USD 0.30
USD 0.60
USD 0.007
USD 0.014
USD 1.20
USD 2.40
1,000,000samesource
DeepSeek V4.1 Flash 1017standard
fast
USD 0.30
USD 0.60
USD 0.007
USD 0.014
USD 1.20
USD 2.40
1,000,000samesource
GLM 5.2standard
fast
USD 1.40
USD 2.10
USD 0.14
USD 0.21
USD 4.40
USD 6.60
not statedsamesource
GLM 5.3standard
fast
USD 1.40
USD 2.10
USD 0.14
USD 0.21
USD 4.40
USD 6.60
not statedsamesource
GLM 5.3 FlashstandardUSD 0.15USD 0.03USD 0.50not statedsamesource
Kimi K3standardUSD 3USD 0.30USD 151,000,000samesource
Kimi K3.1 ProstandardUSD 2USD 0.20USD 101,048,576samesource
Muse Spark OpenstandardUSD 1.25USD 0.15USD 4.251,000,000—source
NVIDIA Nemotron 3 UltrastandardUSD 0.60USD 0.12USD 2.40not stated—source
NVIDIA Nemotron 3.5 Super VLstandardUSD 0.20USD 0.04USD 0.501,000,000—source
OpenAI GPT OSS 120BstandardUSD 0.10—USD 0.50not stated—source
  • Cached "—" means Baseten's page shows no cache price for that row; budget cached tokens at the input price.
  • Context "not stated": the source does not give it (10 of 18 rows have one).

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What service tiers does Baseten publish?

  • fast (4 rows). Across 4 models with both prices, the median fast price is 1.75× standard (range 1.5× standard to 2× standard). Baseten row note: “Context from the model library page (https://www.baseten.co/library/deepseek-v41-flash-fast/), stated as 1M.”

Cached input: 13 of 14 standard prices include a cache-read price, a median 10% of the input price. What cached input means.

What we recorded about Baseten's pricing page: Model APIs token pricing table on baseten.co/pricing (columns: input, cache input, output per 1M tokens). Model ids and context come from baseten.co/library pages where available. Base Labs mammoth-1, elephant-1 and joey-1 (input-only "decision" models) left out.

Is Baseten cheaper than the model makers' own APIs?

Mostly it charges the same as the maker. Of 8 standard prices for models whose maker sells its own API, 0 are below the maker's price, 0 above and 8 the same, on the 3:1 blend. The median difference is zero.

BroadNet Inference and Baseten

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 2 models that Baseten prices: DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against Baseten's USD 0.30 / USD 1.20 (BroadNet is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against Baseten's USD 1.40 / USD 4.40 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.

More on Baseten

Questions

How much does the Baseten API cost per token?

Baseten's standard prices run from USD 0.13 input and USD 0.26 output per 1M tokens (DeepSeek V4 Flash 0731) to USD 3 / USD 15 (Kimi K3). The median across 14 standard prices is USD 0.50 input and USD 1.80 output per 1M, which is USD 0.0000005 per input token. Input, cached input and output are billed separately.

What is the cheapest model on Baseten?

DeepSeek V4 Flash 0731, at USD 0.13 input and USD 0.26 output per 1M tokens (USD 0.1625 on a 3:1 input-to-output blend). The cheapest from other makers: GLM 5.3 Flash (Z.ai) at USD 0.15 / USD 0.50; Kimi K3.1 Pro (Moonshot AI) at USD 2 / USD 10; NVIDIA Nemotron 3.5 Super VL (NVIDIA) at USD 0.20 / USD 0.50.

Is Baseten cheaper than other providers?

It depends on the model. Of 14 models that other providers also price, Baseten is the cheapest standard price for 2 (all of them tied with another provider), for example Muse Spark Open and Beam 1.0 501B A23B; another provider is cheaper for 12; and it is the dearest for 3. Its median rank is 5 of a median 15.5 providers, on a 3:1 input-to-output blend.

Does Baseten have batch, cached or priority pricing?

Cached input: yes, for 13 of 14 standard prices, at a median 10% of the input price. Other tiers: fast on 4 rows (median input 1.75× standard).

How much does a chatbot cost per month on Baseten?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 10.87 on DeepSeek V4 Flash 0731, USD 38.16 on Beam 1.0 501B A23B (the middle of Baseten's list) and USD 394.20 on Kimi K3. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity