Command A vs Antigravity Agent

Benchmark Performance

Available Benchmarks

No Protocol-Matched Benchmark Yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.
FieldAt a Glance
Cohere · activeCommand AVerified Aug 29, 2026
Google DeepMind · previewAntigravity AgentVerified Aug 29, 2026

Technical Differences

Side-by-Side Facts

Indexable
FieldCommand AAntigravity Agent
DeveloperCohereGoogle DeepMind
FamilyCommand AGemini Agents
ModelCommand AAntigravity Agent
VersionCommand AAntigravity Agent
Lifecycleactivepreview
ReleasedUnknownUnknown
Knowledge cutoff2024-06-01Unknown
Input modalitiesTextText, Image
Output modalitiesTextText
Context window256,0001,048,576
Total parameters111,000,000,000Unknown
Active parametersUnknownUnknown
LicenseUnknownUnknown
Open weightsNoNo
API availableYesYes
Self-hostableNoNo
Provider accessCohere (Standard)Google AI (Standard)
Capabilitiesagents, chat, citations, multilingual, rag, structured_outputs, toolsgeneration, reasoning, tools

13 comparable fields · 9 material differences · Pair passes the primary-source comparison gate

Command A Capabilities

agentschatcitationsmultilingualragstructured outputstools
Input price$2.50
Output price$10.00
Serving providers1
Canonical IDcoherelabs/command-a-03-2025

Antigravity Agent Capabilities

generationreasoningtools
Input price
Output price
Serving providers1
Canonical IDgoogle-deepmind/antigravity-preview-05-2026

Internal Comparison Graph

Related Comparisons

All text comparisons →
APairBContext
vsfamily variantstext
vsfamily variantstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext

Primary Evidence

Sources and Freshness

Questions

Command A vs Antigravity Agent FAQs

Is Command A or Antigravity Agent better for coding?+

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

Which is cheaper, Command A or Antigravity Agent?+

Only Command A has a directly sourced input price: $2.50 per million tokens. Only Command A has a directly sourced output price: $10.00 per million tokens.

Which has a larger context window, Command A or Antigravity Agent?+

Antigravity Agent has the larger sourced context window. Command A supports 256,000 and Antigravity Agent supports 1,048,576.

Which performs better in benchmarks, Command A or Antigravity Agent?+

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

Can Command A or Antigravity Agent be self-hosted?+

Both models have the same recorded self-hosting status: unsupported. Command A is not marked open weight; Antigravity Agent is not marked open weight.

Can Command A and Antigravity Agent understand images?+

Command A is not documented with image input; Antigravity Agent is documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Command A or Antigravity Agent?+

Antigravity Agent has the larger sourced maximum output: Command A supports 8,000 and Antigravity Agent supports 65,536 output tokens.

Do Command A and Antigravity Agent support reasoning and tool use?+

Command A: tool calling. Antigravity Agent: reasoning, tool calling, and image input. Feature support does not establish relative quality.

Which is available from more inference providers, Command A or Antigravity Agent?+

Command A has 1 sourced provider route; Antigravity Agent has 1, a tie.

Which offers better value, Command A or Antigravity Agent?+

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