Softwr

AI · head to head

Banana vs DNAnexus

Banana logo

Banana

AI

ML inference at scale

From
$1200/month
Rated
-
DNAnexus logo

DNAnexus

Research

Regulated cloud platform for genomic and multiomic data, with GxP and FedRAMP coverage

From
On request
Rated
-

The short version

  • Each has a real cost: Banana banana shut down its serverless GPU infrastructure on 31 March 2024 at noon PST and told customers to migrate to another provider by that time; DNAnexus no pricing is published, so an organisation cannot compare the total cost against running the same pipelines on its own cloud account until it is deep in a sales process.
  • They diverge on capability: Banana covers GPU inference, DNAnexus covers Governed data storage.
  • Prices and features above were last checked on 31 August 2026.

Where they differ

Only the attributes on which Banana and DNAnexus actually diverge.

Attributes where Banana and DNAnexus differ
AttributeBananaDNAnexus
Starting price$1200/monthOn request
Pricing modelsubscriptionquote
PlatformsCloud, ApiWeb, Linux
CategoryAIResearch
Founded2021Unknown

Identical on both: free tier (No), user rating (Not yet rated).

What each one covers

Drawn from each product's published feature list. An absence here means we hold no record of it - not that the product lacks it.

Only in Banana

  • GPU inference
  • Auto-scaling
  • Docker deployment
  • Low latency
  • REST API
  • Python SDK
  • Cloud support
  • Api support

Only in DNAnexus

  • Governed data storage
  • Workflow execution
  • App building
  • Controlled collaboration
  • Compliance posture
  • Cohort browsing

What people use each for

The jobs each tool is most often brought in to do.

Banana

  • Historically, serverless GPU inference for machine learning modelsnot DNAnexus
  • Migration reference for teams that ran models on Banana before the 2024 shutdownnot DNAnexus

DNAnexus

  • A clinical diagnostics laboratory that needs a CLIA and CAP aligned environment for production sequencing pipelines without building the compliance evidence itselfnot Banana
  • A pharma sponsor analysing genomic endpoints in a registrational programme where 21 CFR Part 11 records are requirednot Banana
  • A biobank or consortium giving hundreds of external researchers governed access to a dataset too large to distributenot Banana
  • A diagnostics vendor packaging its pipeline as a versioned app so partner laboratories can run it without receiving the source codenot Banana

Where each one falls short

Documented limitations, not opinions. Every one is a constraint you would hit in normal use.

Banana

  • Banana shut down its serverless GPU infrastructure on 31 March 2024 at noon PST and told customers to migrate to another provider by that time
  • The vendor's own sunset notice names limited runway, retention problems and GPU supply constraints as the reasons for closing
  • The banana.dev site still displays pricing tiers, but every tier links to the sunset notice rather than to a purchase

DNAnexus

  • No pricing is published, so an organisation cannot compare the total cost against running the same pipelines on its own cloud account until it is deep in a sales process.
  • Compute and storage are billed through the platform rather than at underlying cloud list price, so the compliance envelope carries a persistent margin on every terabyte and core hour, which grows with the science rather than staying fixed.
  • Data egress at genomic scale is slow and chargeable, so leaving the platform later is a real project rather than a contract decision, and that gravity weakens negotiating position at renewal.
  • The regulated and validated configurations sit in a higher commercial tier than the research configuration, so an organisation that starts in research mode and later needs GxP faces a repricing rather than a setting change.
  • Bioinformaticians used to running Nextflow on their own infrastructure find the platform abstractions constraining, and porting an existing pipeline into the app model is engineering work that does not carry over to any other platform.

Pricing, plan by plan

Banana

$1200/month
  • Team$1200/month
    • 10 team members
    • 5 projects
    • 50 max parallel GPUs
  • Enterprise$null/custom
    • Custom seat limit
    • Custom GPU configuration

DNAnexus

On request
  • DNAnexus Platform$undefined/year
    • Quoted per organisation through a sales process
    • Storage and compute billed through the platform rather than at cloud list price
    • Regulated and validated configurations are a separate commercial tier

Which should you pick?

Choose Banana if

  • You need gpu inference.
  • You work on Cloud, Api.
  • You also want auto-scaling.

Choose DNAnexus if

  • You need governed data storage.
  • You work on Web, Linux.
  • You also want workflow execution.

Questions people ask

Is Banana or DNAnexus better?
Neither clearly leads. Banana starts at $1200/month and DNAnexus at On request, and user ratings are close enough to be indistinguishable. Choose on capability and platform support.
Which is cheaper, Banana or DNAnexus?
Banana starts at $1200/month and DNAnexus at On request.
Does Banana or DNAnexus run on more platforms?
Banana runs on Cloud, Api. DNAnexus runs on Web, Linux.
What is Banana best used for?
Banana is most often used for historically, serverless gpu inference for machine learning models, migration reference for teams that ran models on banana before the 2024 shutdown. Of those, historically, serverless gpu inference for machine learning models and migration reference for teams that ran models on banana before the 2024 shutdown are not what DNAnexus is typically brought in for.
What can Banana do that DNAnexus cannot?
Banana covers GPU inference, Auto-scaling, Docker deployment, Low latency. DNAnexus covers Governed data storage, Workflow execution, App building, Controlled collaboration.

Answered from the vendors’ own pages

Banana: How much does Banana's Team plan cost?

The Team plan costs $1,200 per month plus the cost of compute resources at cost with zero markup applied.

Source
DNAnexus: Why pay for DNAnexus instead of raw AWS?

For the compliance evidence. GxP, FedRAMP, CLIA, CAP and Part 11 coverage removes a validation programme most organisations would otherwise have to build and maintain themselves.

Banana: What is the maximum team size on Banana's Team plan?

The Team plan includes 10 team members and supports a maximum of 5 projects with up to 50 parallel GPUs.

Source
DNAnexus: Is validated use included?

No. Regulated and validated configurations sit in a separate commercial tier from ordinary research use.

Banana: Does Banana offer an Enterprise plan with custom pricing?

Banana offers an Enterprise plan with custom pricing plus at-cost compute, including SAML SSO, automation API, and dedicated support.

Source
DNAnexus: Can I get my data out?

Yes, but egress at genomic scale is chargeable and slow, so plan exit costs at the point of signing.

DNAnexus: Does it host UK Biobank?

Yes, DNAnexus hosts the UK Biobank research analysis platform, which has its own access approval and cost terms.

Share

Related pages

Other head to heads