BroadRouter

Vertex AI API pricing

Updated

Vertex AI lists standard per-token prices on its own pricing page for 63 models. The cheapest is GPT OSS 20B at USD 0.07 input and USD 0.25 output per 1M tokens; the dearest is Claude Fable 5.1 at USD 10 / USD 50. It publishes cached-input prices for 50 of them, plus batch and priority tiers (no flex). Checked 2026-11-14.

Vertex AI hosts models it does not train. By maker: Google 17, Anthropic 15, xAI 7, Meta 6, DeepSeek 4, Qwen 4, and 5 more. 118 prices, each read from Vertex AI's own pricing page or one of 1 linked model pages, checked 2026-11-14. BroadRouter is BroadNet's own site and does not sell Vertex AI's services. Automated re-check 2026-11-16: 118 of 118 prices still matched the provider's page.

Models with a standard price
63
Median input / output
USD 0.75 / USD 2.50
Cached-input prices
50 of 63
Cheapest host for
3 of 54 shared models

Which models is Vertex AI the cheapest provider for?

Of the 54 models that Vertex AI and at least one other provider both price at the standard tier, Vertex AI has the lowest price for 3, ranked on a blend of 3 input tokens to 1 output token. It also ties the lowest price for 33 more, where another provider is listed first. It is the dearest for 8. Another 9 models have a standard price from Vertex AI only.

Models where Vertex AI is the cheapest provider
ModelVertex AI input / outputNext cheapestSaving on 3:1 blendProviders
Mistral Small 3.1 24B InstructUSD 0.10 / USD 0.30IBM watsonx.ai USD 0.106 / USD 0.3186%4
Mistral Medium 3USD 0.40 / USD 2IBM watsonx.ai USD 3.18 / USD 9.5083%2
Qwen3 Next 80B A3B ThinkingUSD 0.15 / USD 1.20GMI Cloud USD 0.15 / USD 1.5015%2

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

Vertex AI on the most widely hosted models
ModelVertex AIRankCheapest
OpenAI GPT OSS 120BUSD 0.09 / USD 0.368 of 21CoreWeave Forge USD 0.03 / USD 0.17
GLM 5.2USD 1.40 / USD 4.405 of 19DeepInfra USD 0.5625 / USD 1.80
DeepSeek V4.1 FlashUSD 0.30 / USD 1.205 of 16DeepInfra USD 0.14 / USD 0.42
Llama 3.3 70BUSD 0.72 / USD 0.729 of 14DeepInfra USD 0.10 / USD 0.32
DeepSeek V3.2USD 0.56 / USD 1.688 of 11GMI Cloud USD 0.2088 / USD 0.3096
Gemma 4 26B A4BUSD 0.15 / USD 0.6011 of 11DeepInfra USD 0.07 / USD 0.34

Which model makers does Vertex AI sell?

Vertex AI prices models from 11 makers. Google leads with 17 models. Standard prices, USD per 1M input / output tokens.

Vertex AI models by maker
MakerModelsCheapest modelMedian input / output
Google17Gemini 2.0 Flash Lite USD 0.075 / USD 0.30USD 0.75 / USD 3.75
Anthropic15Claude Haiku 5.5 USD 0.10 / USD 0.50USD 5 / USD 25
xAI7Grok 4.1 Fast Non-Reasoning USD 0.20 / USD 0.50USD 1.25 / USD 2.50
Meta6Muse Ember 1.0 USD 0.10 / USD 0.50USD 0.535 / USD 0.935
DeepSeek4DeepSeek V4.1 Flash USD 0.30 / USD 1.20USD 0.58 / USD 1.69
Qwen4Qwen3 235B A22B Instruct 2507 FP8 USD 0.22 / USD 0.88USD 0.185 / USD 1.20
Mistral AI3Mistral Small 3.1 24B Instruct USD 0.10 / USD 0.30USD 0.30 / USD 0.90
Z.ai3GLM 4.7 USD 0.60 / USD 2.20USD 1 / USD 3.20
OpenAI2GPT OSS 20B USD 0.07 / USD 0.25USD 0.08 / USD 0.305
MiniMax1MiniMax M2 USD 0.30 / USD 1.20—
Moonshot AI1Kimi K2 Thinking USD 0.60 / USD 2.50—

Vertex AI price list

USD per 1M tokens: 118 prices for 63 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 Vertex AI is cheaper. Of 35 hosted model prices with a maker price to compare, 0 are below the maker's and 0 above.

Vertex AI API prices by model
ModelTierInputCachedOutputContextvs makerSource
Claude Fable 5standard
batch
USD 10
USD 5
USD 1
USD 0.50
USD 50
USD 25
not statedsamesource
Claude Fable 5.1standard
batch
USD 10
USD 5
USD 0.25
USD 0.125
USD 50
USD 25
not statedsamesource
Claude Fable 5.2standard
batch
USD 8
USD 4
USD 0.20
USD 0.10
USD 40
USD 20
not statedsamesource
Claude Haiku 4.5standard
batch
USD 1
USD 0.50
USD 0.10
USD 0.05
USD 5
USD 2.50
not statedsamesource
Claude Haiku 5.5standard
batch
USD 0.10
USD 0.05
USD 0.01
USD 0.005
USD 0.50
USD 0.25
not statedsamesource
Claude Opus 4.5standard
batch
USD 5
USD 2.50
USD 0.50
USD 0.25
USD 25
USD 12.50
not statedsamesource
Claude Opus 4.6standard
batch
USD 5
USD 2.50
USD 0.50
USD 0.25
USD 25
USD 12.50
not statedsamesource
Claude Opus 4.7standard
batch
USD 5
USD 2.50
USD 0.50
USD 0.25
USD 25
USD 12.50
not statedsamesource
Claude Opus 4.8standard
batch
USD 5
USD 2.50
USD 0.50
USD 0.25
USD 25
USD 12.50
not statedsamesource
Claude Opus 5standard
batch
USD 5
USD 2.50
USD 0.50
USD 0.25
USD 25
USD 12.50
not statedsamesource
Claude Opus 5.5standard
batch
USD 4
USD 2.50
USD 0.20
USD 0.10
USD 20
USD 12.50
not statedsamesource
Claude Sonnet 4.5standard
batch
USD 3
USD 1.50
USD 0.30
USD 0.15
USD 15
USD 7.50
not statedsamesource
Claude Sonnet 4.6standard
batch
USD 3
USD 1.50
USD 0.30
USD 0.15
USD 15
USD 7.50
not statedsamesource
Claude Sonnet 5standard
batch
USD 2
USD 1
USD 0.20
—
USD 10
USD 5
not statedsamesource
Claude Sonnet 5.5standard
batch
USD 2
USD 1
USD 0.10
USD 0.05
USD 10
USD 5
not statedsamesource
Codestral 2standardUSD 0.30—USD 0.90not stated—source
DeepSeek R1 0528standard
batch
USD 1.35
USD 0.675
—
—
USD 5.40
USD 2.70
not stated—source
DeepSeek V3.1standard
batch
USD 0.60
USD 0.30
USD 0.06
—
USD 1.70
USD 0.85
not stated—source
DeepSeek V3.2standard
batch
USD 0.56
USD 0.28
USD 0.056
—
USD 1.68
USD 0.84
not stated—source
DeepSeek V4.1 FlashstandardUSD 0.30USD 0.03USD 1.20not statedsamesource
Gemini 2.0 Flashstandard
batch
USD 0.15
USD 0.075
—
—
USD 0.60
USD 0.30
not stated—source
Gemini 2.0 Flash Litestandard
batch
USD 0.075
USD 0.0375
—
—
USD 0.30
USD 0.15
not stated—source
Gemini 2.5 Flashstandard
batch
priority
USD 0.30
USD 0.15
USD 0.54
USD 0.03
—
USD 0.054
USD 2.50
USD 1.25
USD 4.50
not statedsamesource
Gemini 2.5 Flash-Litestandard
batch
priority
USD 0.10
USD 0.05
USD 0.18
USD 0.01
—
USD 0.018
USD 0.40
USD 0.20
USD 0.72
not statedsamesource
Gemini 2.5 Prostandard
batch
priority
USD 1.25
USD 0.625
USD 2.25
USD 0.125
—
USD 0.225
USD 10
USD 5
USD 18
not statedsamesource
Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite)standard
batch
priority
USD 0.25
USD 0.125
USD 0.45
USD 0.025
USD 0.0125
USD 0.045
USD 1.50
USD 0.75
USD 2.70
not statedsamesource
Gemini 3.1 Pro Previewstandard
batch
priority
USD 2
USD 1
USD 3.60
USD 0.20
—
USD 0.36
USD 12
USD 6
USD 21.60
not statedsamesource
Gemini 3.5 Flashstandard
batch
priority
USD 1.50
USD 0.75
USD 2.70
USD 0.15
USD 0.075
USD 0.27
USD 9
USD 4.50
USD 16.20
not stated—source
Gemini 3.5 Flash-Litestandard
batch
priority
USD 0.30
USD 0.15
USD 0.54
USD 0.03
USD 0.015
USD 0.054
USD 2.50
USD 1.25
USD 4.50
not statedsamesource
Gemini 3.6 Flashpromostandard
batch
priority
USD 0.75
USD 0.375
USD 1.35
USD 0.075
USD 0.0375
USD 0.135
USD 3.75
USD 1.875
USD 6.75
not statedsamesource
Gemini 3.7 Flashpromostandard
batch
priority
USD 0.75
USD 0.375
USD 1.35
USD 0.075
USD 0.0375
USD 0.135
USD 3.75
USD 1.875
USD 6.75
not stated—source
Gemini 3.8 Flashpromostandard
batch
priority
USD 0.75
USD 0.375
USD 1.35
USD 0.075
USD 0.0375
USD 0.135
USD 3.75
USD 1.875
USD 6.75
not statedsamesource
Gemini 3.8 Flash Cyberstandard
batch
priority
USD 1.50
USD 0.75
USD 2.70
USD 0.15
USD 0.075
USD 0.27
USD 7.50
USD 3.75
USD 13.50
not stated—source
Gemini 4 Argonpromostandard
batch
priority
USD 2
USD 1
USD 3.60
USD 0.10
USD 0.05
USD 0.18
USD 10
USD 5
USD 18
not statedsamesource
Gemini 4 Carbonpromostandard
batch
priority
USD 2
USD 1
USD 3.60
USD 0.10
USD 0.05
USD 0.18
USD 10
USD 5
USD 18
not statedsamesource
Gemini 4 Hydrogenstandard
batch
priority
USD 1.50
USD 0.75
USD 2.70
USD 0.075
USD 0.0375
USD 0.135
USD 7.50
USD 3.75
USD 13.50
not statedsamesource
Gemma 4 26B A4BstandardUSD 0.15USD 0.015USD 0.60not stated—source
GLM 4.7standardUSD 0.60USD 0.06USD 2.20not statedsamesource
GLM 5standardUSD 1USD 0.10USD 3.20not statedsamesource
GLM 5.2standardUSD 1.40USD 0.14USD 4.40not statedsamesource
GPT OSS 20Bstandard
batch
USD 0.07
USD 0.035
USD 0.007
—
USD 0.25
USD 0.125
not stated—source
Grok 4.1 Fast Non-ReasoningstandardUSD 0.20USD 0.05USD 0.50not stated—source
Grok 4.1 Fast ReasoningstandardUSD 0.20USD 0.05USD 0.50not stated—source
Grok 4.20 (non-reasoning)standardUSD 1.25USD 0.20USD 2.50not statedsamesource
Grok 4.20 (reasoning)standardUSD 1.25USD 0.20USD 2.50not statedsamesource
Grok 4.3standardUSD 1.25USD 0.20USD 2.50not statedsamesource
Grok 4.6standardUSD 2USD 0.50USD 6not statedsamesource
Grok 4.7standardUSD 2USD 0.50USD 6not statedsamesource
Kimi K2 ThinkingstandardUSD 0.60USD 0.06USD 2.50not stated—source
Llama 3.3 70Bstandard
batch
USD 0.72
USD 0.36
—
—
USD 0.72
USD 0.36
not stated—source
Llama 4 Maverick 17B 128E Instruct FP8standard
batch
USD 0.35
USD 0.175
—
—
USD 1.15
USD 0.575
not stated—source
Llama 4 Scout 17B 16E Instructstandard
batch
USD 0.25
USD 0.125
—
—
USD 0.70
USD 0.35
not stated—source
MiniMax M2standardUSD 0.30USD 0.03USD 1.20not stated—source
Mistral Medium 3standardUSD 0.40—USD 2not stated—source
Mistral Small 3.1 24B InstructstandardUSD 0.10—USD 0.30not stated—source
Muse Ember 1.0standardUSD 0.10USD 0.004USD 0.50not stated—source
Muse Spark 1.3standardUSD 1.25USD 0.15USD 4.25not stated—source
Muse Wonder 1.0standardUSD 4USD 0.20USD 20not stated—source
OpenAI GPT OSS 120Bstandard
batch
USD 0.09
USD 0.045
—
—
USD 0.36
USD 0.18
not stated—source
Qwen3 235B A22B Instruct 2507 FP8standard
batch
USD 0.22
USD 0.11
—
—
USD 0.88
USD 0.44
not stated—source
Qwen3 Coder 480B A35Bstandard
batch
USD 0.22
USD 0.11
USD 0.022
—
USD 1.80
USD 0.90
not stated—source
Qwen3 Next 80B A3B InstructstandardUSD 0.15—USD 1.20not stated—source
Qwen3 Next 80B A3B ThinkingstandardUSD 0.15—USD 1.20not stated—source
  • Cached "—" means Vertex AI's page shows no cache price for that row; budget cached tokens at the input price.
  • Context "not stated": Vertex AI's pricing page does not give context windows.
  • Promo: Vertex AI's page describes 5 prices as promotional or discounted; they can end without notice. Each model page has the list price where the source gives one.

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

What service tiers does Vertex AI publish?

  • batch (41 rows). Across 41 models with both prices, the median batch price is 50% below standard (range 50% below standard to 38% below standard).
  • priority (14 rows). Across 14 models with both prices, the median priority price is 1.8× standard. Vertex AI row note: “Global endpoint; non-global regions cost 10% more.”

Cached input: 50 of 63 standard prices include a cache-read price, a median 10% of the input price. What cached input means.

What we recorded about Vertex AI's pricing page: Vertex AI (now sold as Gemini Enterprise Agent Platform; cloud.google.com/vertex-ai/generative-ai/pricing redirects to the Model Garden pricing page). Rows with maker Google (Gemini, Gemma) are first-party prices; all other rows are partner models Google hosts as managed APIs, priced on the Partner Models page. Global endpoint unless noted; regional endpoints often cost more. Gemini 1.5/1.0 (per-character legacy pricing), image, audio, TTS, embedding, OCR and robotics models are not listed.

Is Vertex AI cheaper than the model makers' own APIs?

Mostly it charges the same as the maker. Of 35 standard prices for models whose maker sells its own API, 0 are below the maker's price, 0 above and 35 the same, on the 3:1 blend. The median difference is zero.

BroadNet Inference and Vertex AI

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 2 models that Vertex AI prices: BroadNet Gemma 4 VL 26B at USD 0.10 / USD 0.22 against Vertex AI's USD 0.15 / USD 0.60 (BroadNet is cheaper on the 3:1 blend); DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against Vertex AI's USD 0.30 / USD 1.20 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.

More on Vertex AI

Questions

How much does the Vertex AI API cost per token?

Vertex AI's standard prices run from USD 0.07 input and USD 0.25 output per 1M tokens (GPT OSS 20B) to USD 10 / USD 50 (Claude Fable 5.1). The median across 63 standard prices is USD 0.75 input and USD 2.50 output per 1M, which is USD 0.00000075 per input token. Input, cached input and output are billed separately.

What is the cheapest model on Vertex AI?

GPT OSS 20B, at USD 0.07 input and USD 0.25 output per 1M tokens (USD 0.115 on a 3:1 input-to-output blend). The cheapest from other makers: Gemini 2.0 Flash Lite (Google) at USD 0.075 / USD 0.30; Claude Haiku 5.5 (Anthropic) at USD 0.10 / USD 0.50; Grok 4.1 Fast Non-Reasoning (xAI) at USD 0.20 / USD 0.50.

Is Vertex AI cheaper than other providers?

It depends on the model. Of 54 models that other providers also price, Vertex AI is the cheapest standard price for 3, for example Mistral Small 3.1 24B Instruct, Mistral Medium 3 and Qwen3 Next 80B A3B Thinking; it ties the lowest price, without beating it, for 33 more; another provider is cheaper for 18; and it is the dearest for 8. Its median rank is 1 of a median 5 providers, on a 3:1 input-to-output blend.

Does Vertex AI have batch, cached or priority pricing?

Cached input: yes, for 50 of 63 standard prices, at a median 10% of the input price. Other tiers: batch on 41 rows (median input 50% below standard); priority on 14 rows (median input 1.8× standard).

How much does a chatbot cost per month on Vertex AI?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 7.40 on GPT OSS 20B, USD 98.55 on Gemini 3.8 Flash (the middle of Vertex AI's list) and USD 1,314 on Claude Fable 5. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity