pi 0.7 vs Inkling

At a Glance

Compare
pi 0.7Physical Intelligence
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

Fieldpi 0.7Inkling
DeveloperPhysical IntelligenceThinking Machines Lab
FamilypiInkling
Modelpi 0.7Inkling
Version0.7Inkling
Lifecycleactiveactive
Released2026-04-162026-07-15
Knowledge cutoffUnknownUnknown
Input modalitiesText, Image, Robot stateText, Image, Video, Audio
Output modalitiesRobot actionText
Context windowUnknown1,049K
Total parametersUnknown975B
Active parametersUnknown41B
LicenseUnknownapache-2.0
Open weightsNoYes
API availableUnknownYes
Self-hostableUnknownYes
Provider accessUnknownDeepinfra (Standard), Fireworks Ai (Standard), Openrouter (Standard), Together Ai (Standard)
Capabilitiescross-embodiment, dexterous-manipulation, language-steering, visual-subgoalsagents, chat, coding, generation, reasoning, tools, vision
Robotics model typeVision-language-action modelUnknown
Action representationContinuous robot actions conditioned by multimodal promptsUnknown
Control architectureHigh-level policy, world model, and action expertUnknown
Inference locationUnknownUnknown
Native control rate (Hz)UnknownUnknown
Supported embodimentsmobile manipulators, bimanual UR5e, multiple fixed manipulatorsUnknown
Training dataRobot demonstrations, autonomous data, egocentric human data, and multimodal web data described by the publisher.Unknown

pi 0.7 Capabilities

cross-embodimentdexterous-manipulationlanguage-steeringvisual-subgoals
Model typeVision-language-action model
InferenceUnknown
Action representationContinuous robot actions conditioned by multimodal prompts
Supported embodiments3
Canonical IDphysical-intelligence/pi-0.7

Inkling Capabilities

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

Primary Evidence

Sources and Freshness

Questions

pi 0.7 vs Inkling FAQs

Is pi 0.7 or Inkling better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both pi 0.7 and Inkling, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, pi 0.7 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, pi 0.7 or Inkling?+

Neither model has a larger sourced context window in this comparison. pi 0.7 is — and Inkling is 1,049K.

Which performs better in benchmarks, pi 0.7 or Inkling?+

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

Can pi 0.7 or Inkling be self-hosted?+

Inkling is the only model in this pair currently marked as self-hostable. pi 0.7 is not marked open weight; Inkling is open weight.

Can pi 0.7 and Inkling understand images?+

pi 0.7 is documented with image input; Inkling is documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, pi 0.7 or Inkling?+

Neither has a larger sourced maximum output. pi 0.7 is — and Inkling is —.

Do pi 0.7 and Inkling support reasoning and tool use?+

pi 0.7: image input. Inkling: reasoning, tool calling, and image input. Feature support does not establish relative quality.

Which is available from more inference providers, pi 0.7 or Inkling?+

pi 0.7 has 0 sourced provider routes; Inkling has 4, so Inkling has broader tracked availability.

Which offers better value, pi 0.7 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