SmolVLA 450M vs Inkling

At a Glance

Compare
SmolVLA 450MHugging Face LeRobot
InklingThinking Machines Lab
Intelligence, Cost, and Efficiency
IntelligenceHigher is better · MM Intelligence v2.5UnrankedNot in the 46-model eligible cohort#34 of 4645.4 score · 3/3 sources · complete
CostLower is better · Published-token output estimateUnrankedNot in the 44-model eligible cohort#18 of 44$0.090 per LiveBench case
EfficiencyHigher is better · MM Efficiency v1.5UnrankedNot in the 38-model eligible cohort#28 of 3848.1 score · 3/3 sources · complete
Pricing and Limits
Context windowMaximum documented tokensNot reported1,049K
Model facts checkedAug 29, 2026View model evidence →Sep 3, 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 450MInkling
DeveloperHugging Face LeRobotThinking Machines Lab
FamilySmolVLAInkling
ModelSmolVLA 450MInkling
Version450MInkling
Lifecycleactiveactive
Released2025-06-032026-07-15
Knowledge cutoffUnknownUnknown
Input modalitiesText, Image, Robot stateText, Image, Video, Audio
Output modalitiesRobot actionText
Context windowUnknown1,049K
Total parameters450M975B
Active parametersUnknown41B
Licenseapache-2.0apache-2.0
Open weightsYesYes
API availableNoYes
Self-hostableYesYes
Provider accessUnknownDeepinfra (Standard), Fireworks Ai (Standard), Openrouter (Standard), Together Ai (Standard)
Capabilitiesasynchronous-inference, fine-tuning, low-cost-hardware, manipulationagents, chat, coding, generation, reasoning, tools, vision
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

Inkling Capabilities

agentschatcodinggenerationreasoningtoolsvision
Model typeUnknown
InferenceUnknown
Action representationUnknown
Supported embodimentsUnknown
Canonical IDthinkingmachines/Inkling

Primary Evidence

Sources and Freshness

Questions

SmolVLA 450M vs Inkling FAQs

Is SmolVLA 450M or Inkling better for coding?+

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

Which is cheaper, SmolVLA 450M or Inkling?+

Only Inkling has a directly sourced input price: $0.95 per million tokens. Only Inkling has a directly sourced output price: $4.05 per million tokens.

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

Neither model has a larger sourced context window in this comparison. SmolVLA 450M is — and Inkling is 1,049K.

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

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

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

Both models have the same recorded self-hosting status: supported. SmolVLA 450M is open weight; Inkling is open weight.

Can SmolVLA 450M and Inkling understand images?+

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

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

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

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

SmolVLA 450M: image input. Inkling: reasoning, tool calling, and image input. Feature support does not establish relative quality.

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

SmolVLA 450M has 0 sourced provider routes; Inkling has 4, so Inkling has broader tracked availability.

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

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