Inference pricing

The price of each open model in USD, for each region and service tier, and how Munito AI bills a request.

Each model has a posted price in USD:

  • Chat and decision models: for each million tokens.
  • OCR models: for each 1,000 pages.
  • The region and the service tier of a request select the price.

Chat models

Prices in USD for each million tokens.

DeepSeek-V4-Flash deepseek-ai/deepseek-v4-flash

RegionTierInputCached inputOutput
Globalstandard$0.099$0.019$0.25
Globalpriority$0.17$0.033$0.44
Globalflex$0.05$0.0095$0.13
EUstandard$0.11$0.022$0.28
EUpriority$0.19$0.039$0.49
EUflex$0.055$0.011$0.14

Not served in the US.

DeepSeek-V4.1-Flash-1017 (preview) deepseek-ai/deepseek-v4.1-flash-1017

RegionTierInputCached inputOutput
Globalstandard$0.27$0.0054$1.00
Globalpriority$0.47$0.0095$1.80
Globalflex$0.14$0.0027$0.50
EUstandard$0.30$0.006$1.20
EUpriority$0.53$0.011$2.10
EUflex$0.15$0.003$0.60

Not served in the US.

Gemma 4 12B google/gemma-4-12b

RegionTierInputCached inputOutput
Globalstandard$1.00$1.00$0.15
Globalpriority$1.80$1.80$0.26
Globalflex$0.50$0.50$0.075
EUstandard$1.10$1.10$0.17
EUpriority$1.90$1.90$0.30
EUflex$0.55$0.55$0.085

Not served in the US.

GLM-5.3-Flash zai-org/glm-5.3-flash

RegionTierInputCached inputOutput
Globalstandard$0.13$0.027$0.45
Globalpriority$0.23$0.047$0.79
Globalflex$0.065$0.014$0.23
EUstandard$0.15$0.03$0.50
EUpriority$0.26$0.053$0.88
EUflex$0.075$0.015$0.25

Not served in the US.

Kolibri 1 aleph-alpha/kolibri-1

RegionTierInputCached inputOutput
Globalstandard$0.13$0.078$0.51
Globalpriority$0.23$0.14$0.89
Globalflex$0.065$0.039$0.26
EUstandard$0.16$0.094$0.56
EUpriority$0.28$0.16$0.98
EUflex$0.08$0.047$0.28

Not served in the US.

Qwen3.8-27B qwen/qwen3.8-27b

RegionTierInputCached inputOutput
Globalstandard$0.18$0.05$2.40
Globalpriority$0.32$0.088$4.20
Globalflex$0.09$0.025$1.20
EUstandard$0.20$0.11$2.70
EUpriority$0.35$0.19$4.70
EUflex$0.10$0.055$1.40
USstandard$0.20$0.055$2.70
USpriority$0.35$0.096$4.70
USflex$0.10$0.028$1.40

Decision models

Prices in USD for each million tokens.

Cygnet (preview) blockbrain/cygnet

RegionTierInputCached inputOutput
Globalstandard$0.05$0.05$0.15
Globalpriority$0.088$0.088$0.26
Globalflex$0.025$0.025$0.075
EUstandard$0.15$0.15$0.17
EUpriority$0.26$0.26$0.30
EUflex$0.075$0.075$0.085

Not served in the US.

pplx-decider-v1.2 (preview) perplexity-ai/pplx-decider-v1.2

RegionTierInputCached inputOutput
Globalstandard$0.02$0.02$0
Globalpriority$0.035$0.035$0
Globalflex$0.01$0.01$0
EUstandard$0.03$0.03$0
EUpriority$0.053$0.053$0
EUflex$0.015$0.015$0

Not served in the US.

OCR models

Prices in USD for each 1,000 pages.

LightOnOCR-3-4B lightonai/lightonocr-3-4b

RegionTierPer 1,000 pages
Globalstandard$4.00
Globalpriority$7.00
Globalflex$2.00
EUstandard$4.40
EUpriority$7.70
EUflex$2.20
USstandard$4.40
USpriority$7.70
USflex$2.20

Auto munito/ocr-auto

RegionTierPer 1,000 pages
Globalstandard$4.00
Globalpriority$7.00
Globalflex$2.00
EUstandard$4.40
EUpriority$7.70
EUflex$2.20
USstandard$4.40
USpriority$7.70
USflex$2.20

Fast munito/ocr-fast

RegionTierPer 1,000 pages
Globalstandard$2.00
Globalpriority$3.50
Globalflex$1.00
EUstandard$2.20
EUpriority$3.85
EUflex$1.10
USstandard$2.20
USpriority$3.85
USflex$1.10

How a request is billed

UsageBilled as
Input tokensThe input price
Cached input tokensThe cached input price. Prompt caching is automatic, and a cache write is free.
Output tokensThe output price. Reasoning text counts as output.
Audio inputThe input price. One second of audio is 25 input tokens. See Speech to text.
OCR pagesThe price of each page that the model reads
  • Region. The global host, api.munito.ai, bills the global price. The EU and US hosts bill the price of their region. A regional model ID, such as qwen/qwen3.8-27b@eu, also bills the price of its region. See Regions.
  • Service tier. priority costs more than standard, and flex costs less. The munito-service-tier response header gives the tier that Munito AI bills.
  • Overflow. When overflow answers a request, you pay your price of the model that you asked for.

Pay for usage

  • Free tier. A new account with a verified phone number can use the free tier, when capacity is available.
  • Prepaid credits. Buy credits on the Billing page of the console. Usage takes the prices on this page from the balance. The total of the credits that you buy sets your usage tier.
  • Automatic top-up. Turn it on in Billing, with a saved card. When the balance falls to your threshold, the card buys credits up to your target.
  • Balance at zero. The account continues on the free tier. Its usage tier comes back with new credits.
  • Spend limits. Owners and administrators set daily and monthly spend limits in Billing. The Admin API reads them.
  • Billing history. Billing lists each credit purchase with its invoice.
  • Committed spend. For a monthly invoice and volume rates, see Committed spend.

Prices do not include VAT and other taxes. Munito AI adds them where the law requires. Paid use is for business and professional users. See the Terms.

See your own prices

The Models page of the console shows the prices of your organization. A contract can give your organization lower prices.