Code Cushman 001 vs Perceptron Mk1
Code Cushman 001 (2021) and Perceptron Mk1 (2026) are agentic coding models from OpenAI and Perceptron. Code Cushman 001 ships a not-yet-sourced context window, while Perceptron Mk1 ships a 33K-token context window. This comparison covers specs, pricing, capabilities, benchmarks, provider availability, and production fit. It focuses on practical selection signals rather than broad model-family marketing. The goal is to make the tradeoff clear before deeper testing.
Perceptron Mk1 is safer overall; choose Code Cushman 001 when coding workflow support matters.
Decision scorecard
Local evidence first| Signal | Code Cushman 001 | Perceptron Mk1 |
|---|---|---|
| Decision fit | Coding | Vision and JSON / Tool use |
| Context window | — | 33K |
| Cheapest output | - | $1.5/1M tokens |
| Provider routes | 0 tracked | 1 tracked |
| Shared benchmarks | 0 rows | 0 rows |
Decision tradeoffs
- Local decision data tags Code Cushman 001 for Coding.
- Perceptron Mk1 has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Perceptron Mk1 has broader tracked provider coverage for fallback and procurement flexibility.
- Perceptron Mk1 uniquely exposes Vision, Multimodal, and Reasoning in local model data.
- Local decision data tags Perceptron Mk1 for Vision and JSON / Tool use.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output prices on this page.
Code Cushman 001
Unavailable
No complete token price in local provider data
Perceptron Mk1
$495
Cheapest tracked route: OpenRouter
Cost delta unavailable until both models have sourced input and output token prices.
Switch friction
- No overlapping tracked provider route is sourced for Code Cushman 001 and Perceptron Mk1; plan for SDK, billing, or endpoint changes.
- Perceptron Mk1 adds Vision, Multimodal, and Reasoning in local capability data.
- No overlapping tracked provider route is sourced for Perceptron Mk1 and Code Cushman 001; plan for SDK, billing, or endpoint changes.
- Check replacement coverage for Vision, Multimodal, and Reasoning before moving production traffic.
Specs
| Specification | ||
|---|---|---|
| Released | 2021-11-03 | 2026-05-12 |
| Context window | — | 33K |
| Parameters | — | — |
| Architecture | decoder only | decoder only |
| License | Proprietary | Proprietary |
| Knowledge cutoff | - | - |
Pricing and availability
| Pricing attribute | Code Cushman 001 | Perceptron Mk1 |
|---|---|---|
| Input price | - | $0.15/1M tokens |
| Output price | - | $1.5/1M tokens |
| Providers | - |
Capabilities
| Capability | Code Cushman 001 | Perceptron Mk1 |
|---|---|---|
| Vision | No | Yes |
| Multimodal | No | Yes |
| Reasoning | No | Yes |
| Function calling | No | No |
| Tool use | No | No |
| Structured outputs | No | Yes |
| Code execution | No | No |
Benchmarks
No shared benchmark rows are currently sourced for this pair.
Deep dive
The capability footprint differs most on vision: Perceptron Mk1, multimodal input: Perceptron Mk1, reasoning mode: Perceptron Mk1, and structured outputs: Perceptron Mk1. Both models share the core language-model surface, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.
Pricing coverage is uneven: Code Cushman 001 has no token price sourced yet and Perceptron Mk1 has $0.15/1M input tokens. Provider availability is 0 tracked routes versus 1. Treat unknown pricing as an integration gap, then verify the route you will actually call before estimating production spend.
Choose Code Cushman 001 when coding workflow support are central to the workload. Choose Perceptron Mk1 when reasoning depth and broader provider choice are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship. This keeps the decision grounded in measurable tradeoffs instead of brand-level assumptions. It also helps separate model capability from provider packaging, which can change cost and latency. For teams standardizing a stack, that distinction is often the difference between a benchmark win and a reliable deployment.
FAQ
Is Code Cushman 001 or Perceptron Mk1 open source?
Code Cushman 001 is listed under Proprietary. Perceptron Mk1 is listed under Proprietary. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for vision, Code Cushman 001 or Perceptron Mk1?
Perceptron Mk1 has the clearer documented vision signal in this comparison. If vision is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Which is better for multimodal input, Code Cushman 001 or Perceptron Mk1?
Perceptron Mk1 has the clearer documented multimodal input signal in this comparison. If multimodal input is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Which is better for reasoning mode, Code Cushman 001 or Perceptron Mk1?
Perceptron Mk1 has the clearer documented reasoning mode signal in this comparison. If reasoning mode is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Which is better for structured outputs, Code Cushman 001 or Perceptron Mk1?
Perceptron Mk1 has the clearer documented structured outputs signal in this comparison. If structured outputs is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Where can I run Code Cushman 001 and Perceptron Mk1?
Code Cushman 001 is available on the tracked providers still being sourced. Perceptron Mk1 is available on OpenRouter. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-05-18. Data sourced from public model cards and provider documentation.