Ternary Bonsai 4B vs Inkling
At a Glance
| Compare |  Ternary Bonsai 4BPrismML | InklingThinking Machines Lab |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v2.5 | UnrankedNot in the 46-model eligible cohort | #34 of 4645.4 score · 3/3 sources · complete |
| CostLower is better · Published-token output estimate | UnrankedNot in the 44-model eligible cohort | #18 of 44$0.090 per LiveBench case |
| EfficiencyHigher is better · MM Efficiency v1.5 | UnrankedNot in the 38-model eligible cohort | #28 of 3848.1 score · 3/3 sources · complete |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | Not reported | $0.95Deepinfra ↗ · Sep 21, 2026 |
| Output priceFrom · USD / 1M tokens | Not reported | $4.05Deepinfra ↗ · Sep 21, 2026 |
| Context windowMaximum documented tokens | 33K | 1,049K |
| Model facts checked | Sep 18, 2026View model evidence → | Sep 3, 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 4B | Inkling |
|---|---|---|
| Developer | PrismML | Thinking Machines Lab |
| Family | Bonsai 4b | Inkling |
| Model | Ternary Bonsai 4B | Inkling |
| Version | Ternary Bonsai 4B | Inkling |
| Lifecycle | active | active |
| Released | 2026-04-18 | 2026-07-15 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text, Image, Video, Audio |
| Output modalities | Text | Text |
| Context window | 33K | 1,049K |
| Total parameters | 4B | 975B |
| Active parameters | Unknown | 41B |
| License | apache-2.0 | apache-2.0 |
| Open weights | Yes | Yes |
| API available | No | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | Deepinfra (Standard), Fireworks Ai (Standard), Openrouter (Standard), Together Ai (Standard) |
| Capabilities | chat, generation | agents, chat, coding, generation, reasoning, tools, vision |
| Effective bit width | 1.58 bits per weight | Unknown |
| Weight size | 1.07 GB | Unknown |
| Weight format | Ternary Q2_0 | Unknown |
Ternary Bonsai 4B Capabilities
Inkling Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
 GPT-6 AstraOpenAI | vs | Ternary Bonsai 4BPrismML | cross-developer peerstext |
Claude Fable 5.1Anthropic | vs | Ternary Bonsai 4BPrismML | cross-developer peerstext |
 Gemini 3.1 ProGoogle DeepMind | vs | Ternary Bonsai 4BPrismML | cross-developer peerstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | Ternary Bonsai 4BPrismML | cross-developer peerstext |
Ternary Bonsai 4BPrismML | vs | Grok 4.6xAI | cross-developer peerstext |
Ternary Bonsai 4BPrismML | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
 Kimi-K3Moonshot AI | vs | Ternary Bonsai 4BPrismML | cross-developer peerstext |
 MiniMax-M3MiniMax | vs | Ternary Bonsai 4BPrismML | cross-developer peerstext |
Ternary Bonsai 4BPrismML | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Ternary Bonsai 4BPrismML | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | Ternary Bonsai 4BPrismML | cross-developer peerstext |
 Mistral Large 3Mistral AI | vs | Ternary Bonsai 4BPrismML | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
Ternary Bonsai 4B vs Inkling FAQs
Is Ternary Bonsai 4B or Inkling better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Ternary Bonsai 4B and Inkling, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Ternary Bonsai 4B 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, Ternary Bonsai 4B or Inkling?+
Inkling has the larger sourced context window. Ternary Bonsai 4B supports 33K and Inkling supports 1,049K.
Which performs better in benchmarks, Ternary Bonsai 4B or Inkling?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can Ternary Bonsai 4B or Inkling be self-hosted?+
Both models have the same recorded self-hosting status: supported. Ternary Bonsai 4B is open weight; Inkling is open weight.
Can Ternary Bonsai 4B and Inkling understand images?+
Ternary Bonsai 4B is not documented with image input; Inkling is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Ternary Bonsai 4B or Inkling?+
Neither has a larger sourced maximum output. Ternary Bonsai 4B is — and Inkling is —.
Do Ternary Bonsai 4B and Inkling support reasoning and tool use?+
Ternary Bonsai 4B: none of these features are definitively sourced. Inkling: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, Ternary Bonsai 4B or Inkling?+
Ternary Bonsai 4B has 0 sourced provider routes; Inkling has 4, so Inkling has broader tracked availability.
Which offers better value, Ternary Bonsai 4B 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.