Kimi K2.6 vs Ternary Bonsai 1.7B
At a Glance
| Compare |  Kimi K2.6Moonshot AI |  Ternary Bonsai 1.7BPrismML |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v2.5 | #32 of 4650.5 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 33.6–67.0 | UnrankedNot in the 46-model eligible cohort |
| CostLower is better · Published-token output estimate | #21 of 44$0.095 per LiveBench case | UnrankedNot in the 44-model eligible cohort |
| EfficiencyHigher is better · MM Efficiency v1.5 | #24 of 3850.1 score · 2/3 sources · provisional · missing ARC-AGI-2 · full-core range 41.7–58.4 | UnrankedNot in the 38-model eligible cohort |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.75Deepinfra ↗ · Sep 21, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $3.50Deepinfra ↗ · Sep 21, 2026 | Not reported |
| Context windowMaximum documented tokens | 262K | 33K |
| Model facts checked | Aug 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
Side-by-Side Facts
| Field | Kimi-K2.6 | Ternary Bonsai 1.7B |
|---|---|---|
| Developer | Moonshot AI | PrismML |
| Family | Kimi K2 6 | Bonsai 1 7b |
| Model | Kimi-K2.6 | Ternary Bonsai 1.7B |
| Version | Kimi-K2.6 | Ternary Bonsai 1.7B |
| Lifecycle | active | active |
| Released | 2026-04-20 | 2026-04-18 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
| Context window | 262K | 33K |
| Total parameters | 1T | 1.7B |
| Active parameters | 32B | Unknown |
| License | other | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Yes | No |
| Self-hostable | Yes | Yes |
| Provider access | Deepinfra (Standard), Fireworks Ai (Standard), Hugging Face (Standard), Openrouter (Standard), Together Ai (Standard) | Unknown |
| Capabilities | chat, generation, reasoning, tools | chat, generation |
| Effective bit width | Unknown | 1.58 bits per weight |
| Weight size | Unknown | 0.46 GB |
| Weight format | Unknown | Ternary Q2_0 |
Kimi K2.6 Capabilities
Ternary Bonsai 1.7B Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
Kimi-K2.6Moonshot AI | vs |  GPT-6 AstraOpenAI | cross-developer peersimage, text |
Claude Fable 5.1Anthropic | vs | Kimi-K2.6Moonshot AI | cross-developer peersimage, text |
 Gemini 3.1 ProGoogle DeepMind | vs | Kimi-K2.6Moonshot AI | cross-developer peerstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | Kimi-K2.6Moonshot AI | cross-developer peersimage, text |
Kimi-K2.6Moonshot AI | vs | Grok 4.6xAI | cross-developer peersimage, text |
Kimi-K2.6Moonshot AI | vs |  Qwen3.8-MaxQwen | cross-developer peersimage, text |
Kimi-K2.6Moonshot AI | vs | Kimi-K3Moonshot AI | family variantsembedding, image, text |
 MiniMax-M3MiniMax | vs | Kimi-K2.6Moonshot AI | cross-developer peersimage, text |
Kimi-K2.6Moonshot AI | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Kimi-K2.6Moonshot AI | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | Kimi-K2.6Moonshot AI | cross-developer peersimage, text |
 Mistral Large 3Mistral AI | vs | Kimi-K2.6Moonshot AI | cross-developer peersimage, text |
Primary Evidence
Sources and Freshness
Questions
Kimi K2.6 vs Ternary Bonsai 1.7B FAQs
Is Kimi K2.6 or Ternary Bonsai 1.7B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Kimi K2.6 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 K2.6 or Ternary Bonsai 1.7B?+
Only Kimi K2.6 has a directly sourced input price: $0.75 per million tokens. Only Kimi K2.6 has a directly sourced output price: $3.50 per million tokens.
Which has a larger context window, Kimi K2.6 or Ternary Bonsai 1.7B?+
Kimi K2.6 has the larger sourced context window. Kimi K2.6 supports 262K and Ternary Bonsai 1.7B supports 33K.
Which performs better in benchmarks, Kimi K2.6 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 K2.6 or Ternary Bonsai 1.7B be self-hosted?+
Both models have the same recorded self-hosting status: supported. Kimi K2.6 is open weight; Ternary Bonsai 1.7B is open weight.
Can Kimi K2.6 and Ternary Bonsai 1.7B understand images?+
Kimi K2.6 is 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 K2.6 or Ternary Bonsai 1.7B?+
Neither has a larger sourced maximum output. Kimi K2.6 is — and Ternary Bonsai 1.7B is —.
Do Kimi K2.6 and Ternary Bonsai 1.7B support reasoning and tool use?+
Kimi K2.6: reasoning, tool calling, and image input. 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 K2.6 or Ternary Bonsai 1.7B?+
Kimi K2.6 has 5 sourced provider routes; Ternary Bonsai 1.7B has 0, so Kimi K2.6 has broader tracked availability.
Which offers better value, Kimi K2.6 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.