Lyria 3.5 vs Inkling

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
Google DeepMind · activeLyria 3.5Verified Sep 3, 2026
Thinking Machines Lab · activeInklingVerified Sep 3, 2026

Technical Differences

Side-by-Side Facts

Indexable
FieldLyria 3.5Inkling
DeveloperGoogle DeepMindThinking Machines Lab
FamilyLyriaInkling
ModelLyria 3.5Inkling
VersionLyria 3.5Inkling
Lifecycleactiveactive
Released2026-07-292026-07-15
Knowledge cutoffUnknownUnknown
Input modalitiesText, ImageText, Image, Video, Audio
Output modalitiesText, AudioText
Context window1,048,5761,048,576
Total parametersUnknown975,000,000,000
Active parametersUnknown41,000,000,000
LicenseUnknownapache-2.0
Open weightsNoYes
API availableYesYes
Self-hostableNoYes
Provider accessGoogle AI (Standard), Google Gemini (Standard)Deepinfra (Standard), Fireworks Ai (Standard), Openrouter (Standard), Together Ai (Standard)
Capabilitiesgeneration, image-to-music, lyrics, music-generation, synthid, vocalsagents, chat, coding, generation, reasoning, tools, vision

14 comparable fields · 11 material differences · Pair passes the primary-source comparison gate

Lyria 3.5 Capabilities

generationimage-to-musiclyricsmusic-generationsynthidvocals
Input price
Output price
Serving providers2
Canonical IDlyria-3.5

Inkling Capabilities

agentschatcodinggenerationreasoningtoolsvision
Input price$0.95
Output price$4.05
Serving providers4
Canonical IDthinkingmachines/Inkling

Internal Comparison Graph

Related Comparisons

All audio comparisons →
APairBContext
vscross-developer peerstext
vscross-developer peersimage, text
vscross-developer peerstext
vscross-developer peersaudio
vscross-developer peersaudio
vscross-developer peersaudio, image, text, video
vscross-developer peersaudio, image, text, video
vscross-developer peersimage, text, video
vscross-developer peersaudio, image, text
vscross-developer peersaudio, image, text
vscross-developer peersimage, text
vscross-developer peersaudio, text

Primary Evidence

Sources and Freshness

Questions

Lyria 3.5 vs Inkling FAQs

Is Lyria 3.5 or Inkling better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Lyria 3.5 and Inkling, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Lyria 3.5 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, Lyria 3.5 or Inkling?+

Neither model has a larger sourced context window in this comparison. Lyria 3.5 is 1,048,576 and Inkling is 1,048,576.

Which performs better in benchmarks, Lyria 3.5 or Inkling?+

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

Can Lyria 3.5 or Inkling be self-hosted?+

Inkling is the only model in this pair currently marked as self-hostable. Lyria 3.5 is not marked open weight; Inkling is open weight.

Can Lyria 3.5 and Inkling understand images?+

Lyria 3.5 is documented with image input; Inkling is documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Lyria 3.5 or Inkling?+

Neither has a larger sourced maximum output. Lyria 3.5 is 65,536 and Inkling is —.

Do Lyria 3.5 and Inkling support reasoning and tool use?+

Lyria 3.5: image input. Inkling: reasoning, tool calling, and image input. Feature support does not establish relative quality.

Which is available from more inference providers, Lyria 3.5 or Inkling?+

Lyria 3.5 has 2 sourced provider routes; Inkling has 4, so Inkling has broader tracked availability.

Which offers better value, Lyria 3.5 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