Kimi K2 Thinking vs Ternary Bonsai 1.7B

At a Glance

Compare
Kimi K2 ThinkingMoonshot AI
Pricing and Limits
Input priceFrom · USD / 1M tokens$0.60Openrouter · Sep 22, 2026Not reported
Output priceFrom · USD / 1M tokens$2.50Openrouter · Sep 22, 2026Not reported
Context windowMaximum documented tokens262K33K
Model facts checkedAug 28, 2026View model evidence →Sep 18, 2026View model evidence →

Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →

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

FieldKimi-K2-ThinkingTernary Bonsai 1.7B
DeveloperMoonshot AIPrismML
FamilyKimi K2 ThinkingBonsai 1 7b
ModelKimi-K2-ThinkingTernary Bonsai 1.7B
VersionKimi-K2-ThinkingTernary Bonsai 1.7B
Lifecycleactiveactive
Released2025-11-062026-04-18
Knowledge cutoffUnknownUnknown
Input modalitiesTextText
Output modalitiesTextText
Context window262K33K
Total parameters1T1.7B
Active parameters32BUnknown
Licenseotherapache-2.0
Open weightsYesYes
API availableYesNo
Self-hostableYesYes
Provider accessHugging Face (Standard), Openrouter (Standard)Unknown
Capabilitieschat, generation, reasoning, toolschat, generation
Effective bit widthUnknown1.58 bits per weight
Weight sizeUnknown0.46 GB
Weight formatUnknownTernary Q2_0

Kimi K2 Thinking Capabilities

chatgenerationreasoningtools
Serving providers2
Canonical IDmoonshotai/Kimi-K2-Thinking

Ternary Bonsai 1.7B Capabilities

chatgeneration
Serving providers0
Canonical IDprism-ml/Ternary-Bonsai-1.7B

Primary Evidence

Sources and Freshness

Questions

Kimi K2 Thinking vs Ternary Bonsai 1.7B FAQs

Is Kimi K2 Thinking or Ternary Bonsai 1.7B better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Kimi K2 Thinking and Ternary Bonsai 1.7B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Kimi K2 Thinking or Ternary Bonsai 1.7B?+

Only Kimi K2 Thinking has a directly sourced input price: $0.60 per million tokens. Only Kimi K2 Thinking has a directly sourced output price: $2.50 per million tokens.

Which has a larger context window, Kimi K2 Thinking or Ternary Bonsai 1.7B?+

Kimi K2 Thinking has the larger sourced context window. Kimi K2 Thinking supports 262K and Ternary Bonsai 1.7B supports 33K.

Which performs better in benchmarks, Kimi K2 Thinking or Ternary Bonsai 1.7B?+

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

Can Kimi K2 Thinking or Ternary Bonsai 1.7B be self-hosted?+

Both models have the same recorded self-hosting status: supported. Kimi K2 Thinking is open weight; Ternary Bonsai 1.7B is open weight.

Can Kimi K2 Thinking and Ternary Bonsai 1.7B understand images?+

Kimi K2 Thinking is not documented with image input; Ternary Bonsai 1.7B is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Kimi K2 Thinking or Ternary Bonsai 1.7B?+

Neither has a larger sourced maximum output. Kimi K2 Thinking is 131K and Ternary Bonsai 1.7B is —.

Do Kimi K2 Thinking and Ternary Bonsai 1.7B support reasoning and tool use?+

Kimi K2 Thinking: reasoning and tool calling. Ternary Bonsai 1.7B: none of these features are definitively sourced. Feature support does not establish relative quality.

Which is available from more inference providers, Kimi K2 Thinking or Ternary Bonsai 1.7B?+

Kimi K2 Thinking has 2 sourced provider routes; Ternary Bonsai 1.7B has 0, so Kimi K2 Thinking has broader tracked availability.

Which offers better value, Kimi K2 Thinking or Ternary Bonsai 1.7B?+

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