Code Cushman 002 vs o3 Deep Research
Code Cushman 002 (2021) and o3 Deep Research (2025) compare a coding-specialized model against a standalone API model. Code Cushman 002 ships a not-yet-sourced context window, while o3 Deep Research ships a 200k-token context window. This page treats the result as workflow and deployment fit, not a universal model winner.
Treat this as a product-type comparison: Code Cushman 002 is coding-specialized model, while o3 Deep Research is standalone API model. Choose based on workflow fit before reading any benchmark or price row as decisive.
Decision scorecard
Local evidence first| Signal | Code Cushman 002 | o3 Deep Research |
|---|---|---|
| Product type | Coding-specialized model | Standalone API model |
| Best for | custom coding agents and code generation | reasoning-heavy apps, multimodal apps, and tool-calling agents |
| Decision fit | Coding | RAG, Agents, and Long context |
| Context window | — | 200k |
| Cheapest output | - | $40/1M tokens |
| Provider routes | 0 tracked | 2 tracked |
| Shared benchmarks | 0 shared | 0 shared |
Decision tradeoffs
- Local decision data tags Code Cushman 002 for Coding.
- o3 Deep Research has the larger context window for long prompts, retrieval packs, or transcript analysis.
- o3 Deep Research has broader tracked provider coverage for fallback and route flexibility.
- o3 Deep Research uniquely exposes Vision, Multimodal, and Reasoning in local model data.
- Local decision data tags o3 Deep Research for RAG, Agents, and Long context.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Code Cushman 002
Unavailable
No complete token price in local provider data
o3 Deep Research
$18,000
Cheapest tracked route/tier: Vercel AI Gateway
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 002 and o3 Deep Research; plan for SDK, billing, or endpoint changes.
- o3 Deep Research adds Vision, Multimodal, and Reasoning in local capability data.
- No overlapping tracked provider route is sourced for o3 Deep Research and Code Cushman 002; plan for SDK, billing, or endpoint changes.
- Check replacement coverage for Vision, Multimodal, and Reasoning before moving production traffic.
Specs
| Specification | ||
|---|---|---|
| Released | 2021-11-15 | 2025-10-10 |
| Context window | — | 200k |
| Parameters | — | — |
| Architecture | Decoder Only | Decoder Only |
| License | Proprietary | Proprietary |
| Openness | Proprietary | Proprietary |
| Weights | Not released | Not released |
| Code | Unknown | Unknown |
| Commercial use | Commercial use: conditional | Commercial use: conditional |
| Knowledge cutoff | - | 2024-06 |
Pricing and availability
| Pricing attribute | Code Cushman 002 | o3 Deep Research |
|---|---|---|
| Input price | - | $10/1M tokens |
| Output price | - | $40/1M tokens |
| Providers | - |
Capabilities
| Capability | Code Cushman 002 | o3 Deep Research |
|---|---|---|
| Vision | No | Yes |
| Multimodal | No | Yes |
| Reasoning | No | Yes |
| JSON / Tool use | No | Yes |
| Structured outputs | No | Yes |
| Code execution | No | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
No shared benchmark scores are currently available for this pair.
Continue comparing
Popular comparisons for Code Cushman 002
Popular comparisons for o3 Deep Research
Last reviewed: 2026-06-29. Data sourced from public model cards and provider documentation.