Ternary Bonsai 1.7B vs Hy4 preview
At a Glance
| Compare |  Ternary Bonsai 1.7BPrismML |  Hy4 previewTencent |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | Not reported | $0.834Openrouter ↗ · Sep 22, 2026 |
| Output priceFrom · USD / 1M tokens | Not reported | $2.501Openrouter ↗ · Sep 22, 2026 |
| Context windowMaximum documented tokens | 33K | 1,000K |
| Model facts checked | Sep 18, 2026View model evidence → | Sep 2, 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 | Ternary Bonsai 1.7B | Hy4 preview |
|---|---|---|
| Developer | PrismML | Tencent |
| Family | Bonsai 1 7b | Hy4 |
| Model | Ternary Bonsai 1.7B | Hy4 preview |
| Version | Ternary Bonsai 1.7B | Hy4 preview |
| Lifecycle | active | preview |
| Released | 2026-04-18 | 2026-08-28 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
| Context window | 33K | 1,000K |
| Total parameters | 1.7B | 770B |
| Active parameters | Unknown | 49B |
| License | apache-2.0 | apache-2.0 |
| Open weights | Yes | Yes |
| API available | No | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | Openrouter (Standard) |
| Capabilities | chat, generation | chat, generation, reasoning, tools |
| Effective bit width | 1.58 bits per weight | Unknown |
| Weight size | 0.46 GB | Unknown |
| Weight format | Ternary Q2_0 | Unknown |
Ternary Bonsai 1.7B Capabilities
Hy4 preview Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
 GPT-6 AstraOpenAI | vs | Ternary Bonsai 1.7BPrismML | cross-developer peerstext |
Claude Fable 5.1Anthropic | vs | Ternary Bonsai 1.7BPrismML | cross-developer peerstext |
 Gemini 3.1 ProGoogle DeepMind | vs | Ternary Bonsai 1.7BPrismML | cross-developer peerstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | Ternary Bonsai 1.7BPrismML | cross-developer peerstext |
Ternary Bonsai 1.7BPrismML | vs | Grok 4.6xAI | cross-developer peerstext |
Ternary Bonsai 1.7BPrismML | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
 Kimi-K3Moonshot AI | vs | Ternary Bonsai 1.7BPrismML | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | Ternary Bonsai 1.7BPrismML | cross-developer peerstext |
Ternary Bonsai 1.7BPrismML | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | Ternary Bonsai 1.7BPrismML | cross-developer peerstext |
 Mistral Large 3Mistral AI | vs | Ternary Bonsai 1.7BPrismML | cross-developer peerstext |
| vs | Ternary Bonsai 1.7BPrismML | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
Ternary Bonsai 1.7B vs Hy4 preview FAQs
Is Ternary Bonsai 1.7B or Hy4 preview better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Ternary Bonsai 1.7B and Hy4 preview, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Ternary Bonsai 1.7B or Hy4 preview?+
Only Hy4 preview has a directly sourced input price: $0.834 per million tokens. Only Hy4 preview has a directly sourced output price: $2.501 per million tokens.
Which has a larger context window, Ternary Bonsai 1.7B or Hy4 preview?+
Hy4 preview has the larger sourced context window. Ternary Bonsai 1.7B supports 33K and Hy4 preview supports 1,000K.
Which performs better in benchmarks, Ternary Bonsai 1.7B or Hy4 preview?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can Ternary Bonsai 1.7B or Hy4 preview be self-hosted?+
Both models have the same recorded self-hosting status: supported. Ternary Bonsai 1.7B is open weight; Hy4 preview is open weight.
Can Ternary Bonsai 1.7B and Hy4 preview understand images?+
Ternary Bonsai 1.7B is not documented with image input; Hy4 preview is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Ternary Bonsai 1.7B or Hy4 preview?+
Neither has a larger sourced maximum output. Ternary Bonsai 1.7B is — and Hy4 preview is —.
Do Ternary Bonsai 1.7B and Hy4 preview support reasoning and tool use?+
Ternary Bonsai 1.7B: none of these features are definitively sourced. Hy4 preview: reasoning and tool calling. Feature support does not establish relative quality.
Which is available from more inference providers, Ternary Bonsai 1.7B or Hy4 preview?+
Ternary Bonsai 1.7B has 0 sourced provider routes; Hy4 preview has 1, so Hy4 preview has broader tracked availability.
Which offers better value, Ternary Bonsai 1.7B or Hy4 preview?+
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.