GPT-5.5 Pro vs Bonsai Image Ternary 4B
At a Glance
| Compare | GPT-5.5 ProOpenAI | Bonsai Image Ternary 4BPrismML |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $30.00Openai ↗ · Sep 3, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $180.00Openai ↗ · Sep 3, 2026 | Not reported |
| Context windowMaximum documented tokens | 1,050K | Not reported |
| Model facts checked | Sep 3, 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 | GPT-5.5 Pro | Bonsai Image Ternary 4B |
|---|---|---|
| Developer | OpenAI | PrismML |
| Family | Gpt 5 5 | Bonsai Image 4b |
| Model | GPT-5.5 Pro | Bonsai Image Ternary 4B |
| Version | GPT-5.5 Pro | Bonsai Image Ternary 4B |
| Lifecycle | active | active |
| Released | 2026-04-23 | 2026-05-21 |
| Knowledge cutoff | 2025-12-01 | Unknown |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Image |
| Context window | 1,050K | Unknown |
| Total parameters | Unknown | 4B |
| Active parameters | Unknown | Unknown |
| License | Unknown | apache-2.0 |
| Open weights | No | Yes |
| API available | Yes | No |
| Self-hostable | No | Yes |
| Provider access | Openai (Standard), Openrouter (Standard) | Unknown |
| Capabilities | chat, generation, reasoning, structured_outputs, tools | generation |
| Base model | Unknown | FLUX.2 Klein 4B |
| Default resolution | Unknown | 512 × 512 |
| Transformer size | Unknown | 1.21 GB |
| Weight format | Unknown | Ternary weights with FP16 group scales |
GPT-5.5 Pro Capabilities
Bonsai Image Ternary 4B Capabilities
Primary Evidence
Sources and Freshness
Questions
GPT-5.5 Pro vs Bonsai Image Ternary 4B FAQs
Is GPT-5.5 Pro or Bonsai Image Ternary 4B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both GPT-5.5 Pro and Bonsai Image Ternary 4B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, GPT-5.5 Pro or Bonsai Image Ternary 4B?+
Only GPT-5.5 Pro has a directly sourced input price: $30.00 per million tokens. Only GPT-5.5 Pro has a directly sourced output price: $180.00 per million tokens.
Which has a larger context window, GPT-5.5 Pro or Bonsai Image Ternary 4B?+
Neither model has a larger sourced context window in this comparison. GPT-5.5 Pro is 1,050K and Bonsai Image Ternary 4B is —.
Which performs better in benchmarks, GPT-5.5 Pro or Bonsai Image Ternary 4B?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can GPT-5.5 Pro or Bonsai Image Ternary 4B be self-hosted?+
Bonsai Image Ternary 4B is the only model in this pair currently marked as self-hostable. GPT-5.5 Pro is not marked open weight; Bonsai Image Ternary 4B is open weight.
Can GPT-5.5 Pro and Bonsai Image Ternary 4B understand images?+
GPT-5.5 Pro is documented with image input; Bonsai Image Ternary 4B is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, GPT-5.5 Pro or Bonsai Image Ternary 4B?+
Neither has a larger sourced maximum output. GPT-5.5 Pro is 128K and Bonsai Image Ternary 4B is —.
Do GPT-5.5 Pro and Bonsai Image Ternary 4B support reasoning and tool use?+
GPT-5.5 Pro: reasoning, tool calling, and image input. Bonsai Image Ternary 4B: none of these features are definitively sourced. Feature support does not establish relative quality.
Which is available from more inference providers, GPT-5.5 Pro or Bonsai Image Ternary 4B?+
GPT-5.5 Pro has 2 sourced provider routes; Bonsai Image Ternary 4B has 0, so GPT-5.5 Pro has broader tracked availability.
Which offers better value, GPT-5.5 Pro or Bonsai Image Ternary 4B?+
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.