Code Cushman 002 vs Gemini 3 Flash Preview
Code Cushman 002 (2021) and Gemini 3 Flash Preview (2025) are agentic coding models from OpenAI and Google DeepMind. Code Cushman 002 ships a not-yet-sourced context window, while Gemini 3 Flash Preview ships a 1M-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.
Gemini 3 Flash Preview is safer overall; choose Code Cushman 002 when coding workflow support matters.
Decision scorecard
Local evidence first| Signal | Code Cushman 002 | Gemini 3 Flash Preview |
|---|---|---|
| Decision fit | Coding | Coding, RAG, and Agents |
| Context window | — | 1M |
| Cheapest output | - | $3/1M tokens |
| Provider routes | 0 tracked | 3 tracked |
| Shared benchmarks | 0 rows | 0 rows |
Decision tradeoffs
- Local decision data tags Code Cushman 002 for Coding.
- Gemini 3 Flash Preview has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Gemini 3 Flash Preview has broader tracked provider coverage for fallback and procurement flexibility.
- Gemini 3 Flash Preview uniquely exposes Vision, Multimodal, and Function calling in local model data.
- Local decision data tags Gemini 3 Flash Preview for Coding, RAG, and Agents.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output prices on this page.
Code Cushman 002
Unavailable
No complete token price in local provider data
Gemini 3 Flash Preview
$1,150
Cheapest tracked route: GCP Vertex AI
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 Gemini 3 Flash Preview; plan for SDK, billing, or endpoint changes.
- Gemini 3 Flash Preview adds Vision, Multimodal, and Function calling in local capability data.
- No overlapping tracked provider route is sourced for Gemini 3 Flash Preview and Code Cushman 002; plan for SDK, billing, or endpoint changes.
- Check replacement coverage for Vision, Multimodal, and Function calling before moving production traffic.
Specs
| Specification | ||
|---|---|---|
| Released | 2021-11-15 | 2025-12-17 |
| Context window | — | 1M |
| Parameters | — | — |
| Architecture | decoder only | decoder only |
| License | Proprietary | Proprietary |
| Knowledge cutoff | - | 2025-01 |
Pricing and availability
| Pricing attribute | Code Cushman 002 | Gemini 3 Flash Preview |
|---|---|---|
| Input price | - | $0.5/1M tokens |
| Output price | - | $3/1M tokens |
| Providers | - |
Capabilities
| Capability | Code Cushman 002 | Gemini 3 Flash Preview |
|---|---|---|
| Vision | No | Yes |
| Multimodal | No | Yes |
| Reasoning | No | No |
| Function calling | No | Yes |
| Tool use | No | Yes |
| Structured outputs | No | Yes |
| Code execution | No | Yes |
Benchmarks
No shared benchmark rows are currently sourced for this pair.
Deep dive
The capability footprint differs most on vision: Gemini 3 Flash Preview, multimodal input: Gemini 3 Flash Preview, function calling: Gemini 3 Flash Preview, tool use: Gemini 3 Flash Preview, structured outputs: Gemini 3 Flash Preview, and code execution: Gemini 3 Flash Preview. 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 002 has no token price sourced yet and Gemini 3 Flash Preview has $0.5/1M input tokens. Provider availability is 0 tracked routes versus 3. Treat unknown pricing as an integration gap, then verify the route you will actually call before estimating production spend.
Choose Code Cushman 002 when coding workflow support are central to the workload. Choose Gemini 3 Flash Preview when coding workflow support 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.
FAQ
Is Code Cushman 002 or Gemini 3 Flash Preview open source?
Code Cushman 002 is listed under Proprietary. Gemini 3 Flash Preview 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 002 or Gemini 3 Flash Preview?
Gemini 3 Flash Preview 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.
Which is better for multimodal input, Code Cushman 002 or Gemini 3 Flash Preview?
Gemini 3 Flash Preview 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 function calling, Code Cushman 002 or Gemini 3 Flash Preview?
Gemini 3 Flash Preview has the clearer documented function calling signal in this comparison. If function calling is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Which is better for tool use, Code Cushman 002 or Gemini 3 Flash Preview?
Gemini 3 Flash Preview has the clearer documented tool use signal in this comparison. If tool use 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 002 and Gemini 3 Flash Preview?
Code Cushman 002 is available on the tracked providers still being sourced. Gemini 3 Flash Preview is available on GCP Vertex AI, OpenRouter, and Google AI Studio. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-05-11. Data sourced from public model cards and provider documentation.