Model Markets
Get Free API KeyAPI

SmolVLA 450M vs Jev

At a Glance

Compare
SmolVLA 450MHugging Face LeRobot
JevTypeSafe
Pricing and Limits
Context windowMaximum documented tokensNot reported64K
Model facts checkedAug 29, 2026View model evidence →Sep 17, 2026View model evidence →
Different Model RolesThese models do not share a sourced market category. Their primary-source facts remain comparable below, while performance claims require matched evidence.

Available Benchmarks

All benchmark results →
No Protocol-Matched Benchmark Yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.

Side-by-Side Facts

FieldSmolVLA 450MJev
DeveloperHugging Face LeRobotTypeSafe
FamilySmolVLAJev
ModelSmolVLA 450MJev
Version450MJev
Lifecycleactiveactive
Released2025-06-032026-09-15
Knowledge cutoffUnknownUnknown
Input modalitiesText, Image, Robot stateText, Model-specific input
Output modalitiesRobot actionModel-specific input
Context windowUnknown64K
Total parameters450MUnknown
Active parametersUnknownUnknown
Licenseapache-2.0Unknown
Open weightsYesNo
API availableNoYes
Self-hostableYesNo
Provider accessUnknownTypeSafe (Standard)
Capabilitiesasynchronous-inference, fine-tuning, low-cost-hardware, manipulationcalibrated-confidence, parallel-evaluation, structured_outputs, typed-decisions
Maximum Choice cardinalityUnknown255 options
Default request rate limitUnknown1200 requests per minute
State plus longest question limitUnknown32000 tokens
Combined state and questions limitUnknown64000 tokens
Default token rate limitUnknown250000 tokens per second
Robotics model typeVision-language-action modelUnknown
Action representationContinuous action chunks from a flow-matching action expertUnknown
Control architectureSmolVLM2 backbone with flow-matching action expertUnknown
Inference locationOn deviceUnknown
Native control rate (Hz)UnknownUnknown
Supported embodimentsSO-100, SO-101, LeKiwi, LIBERO FrankaUnknown
Training dataCompatibly licensed LeRobot community datasets totaling fewer than 30,000 episodes in the cited release.Unknown

SmolVLA 450M Capabilities

asynchronous-inferencefine-tuninglow-cost-hardwaremanipulation
Model typeVision-language-action model
InferenceOn device
Action representationContinuous action chunks from a flow-matching action expert
Supported embodiments4
Canonical IDlerobot/smolvla_base

Jev Capabilities

calibrated-confidenceparallel-evaluationstructured outputstyped-decisions
Model typeUnknown
InferenceUnknown
Action representationUnknown
Supported embodimentsUnknown
Canonical IDtypesafe/jev

Related Comparisons

APairBContext
vscross-developer peers
vscross-developer peers
vscross-developer peers
vscross-developer peers
vscross-developer peers
vscross-developer peers
vscross-developer peers
vscross-developer peers
vscross-developer peers
vscross-developer peers
vscross-developer peers
vscross-developer peers

Primary Evidence

Sources and Freshness

SmolVLA: Efficient Vision-Language-Action Model trained on LeRobot Community DataHugging Face · observed Aug 29, 2026Models | TypeSafe AITypeSafe · observed Sep 17, 2026

Questions

SmolVLA 450M vs Jev FAQs

Is SmolVLA 450M or Jev better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both SmolVLA 450M and Jev, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, SmolVLA 450M or Jev?+

Only Jev has a directly sourced input price: $0.042 per million tokens. Only Jev has a directly sourced output price: $0.000 per million tokens.

Which has a larger context window, SmolVLA 450M or Jev?+

Neither model has a larger sourced context window in this comparison. SmolVLA 450M is — and Jev is 64K.

Which performs better in benchmarks, SmolVLA 450M or Jev?+

There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.

Can SmolVLA 450M or Jev be self-hosted?+

SmolVLA 450M is the only model in this pair currently marked as self-hostable. SmolVLA 450M is open weight; Jev is not marked open weight.

Can SmolVLA 450M and Jev understand images?+

SmolVLA 450M is documented with image input; Jev is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, SmolVLA 450M or Jev?+

Neither has a larger sourced maximum output. SmolVLA 450M is — and Jev is —.

Do SmolVLA 450M and Jev support reasoning and tool use?+

SmolVLA 450M: image input. Jev: none of these features are definitively sourced. Feature support does not establish relative quality.

Which is available from more inference providers, SmolVLA 450M or Jev?+

SmolVLA 450M has 0 sourced provider routes; Jev has 1, so Jev has broader tracked availability.

Which offers better value, SmolVLA 450M or Jev?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback