Code Cushman 002 vs Kimi K2.5
Code Cushman 002 (2021) and Kimi K2.5 (2026) are agentic coding models from OpenAI and Moonshot AI. Code Cushman 002 ships a not-yet-sourced context window, while Kimi K2.5 ships a 256k-token context window. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads. It focuses on practical selection signals rather than broad model-family marketing.
Kimi K2.5 is safer overall; choose Code Cushman 002 when coding workflow support matters.
Decision scorecard
Local evidence first| Signal | Code Cushman 002 | Kimi K2.5 |
|---|---|---|
| Best for | custom coding agents and code generation | custom coding agents, code generation, and tool loops |
| Decision fit | Coding | Coding, RAG, and Agents |
| Context window | — | 256k |
| Cheapest output | - | $2/1M tokens |
| Provider routes | 0 tracked | 10 tracked |
| Shared benchmarks | 0 rows | 0 rows |
Decision tradeoffs
- Local decision data tags Code Cushman 002 for Coding.
- Kimi K2.5 has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Kimi K2.5 has broader tracked provider coverage for fallback and procurement flexibility.
- Kimi K2.5 uniquely exposes Vision, Multimodal, and Function calling in local model data.
- Local decision data tags Kimi K2.5 for Coding, RAG, and Agents.
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
Kimi K2.5
$852
Cheapest tracked route/tier: 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 002 and Kimi K2.5; plan for SDK, billing, or endpoint changes.
- Kimi K2.5 adds Vision, Multimodal, and Function calling in local capability data.
- No overlapping tracked provider route is sourced for Kimi K2.5 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 | 2026-03-15 |
| Context window | — | 256k |
| Parameters | — | 1T (MoE, 384 experts) |
| Architecture | decoder only | mixture of experts |
| License | Proprietary | Proprietary |
| Openness | Proprietary | Proprietary |
| Commercial use | Commercial use with conditions | Commercial use with conditions |
| Knowledge cutoff | - | - |
Pricing and availability
| Pricing attribute | Code Cushman 002 | Kimi K2.5 |
|---|---|---|
| Input price | - | $0.44/1M tokens |
| Output price | - | $2/1M tokens |
| Providers | - |
Capabilities
| Capability | Code Cushman 002 | Kimi K2.5 |
|---|---|---|
| Vision | No | Yes |
| Multimodal | No | Yes |
| Reasoning | No | No |
| Function calling | No | Yes |
| Tool use | No | No |
| Structured outputs | No | Yes |
| Code execution | No | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
No shared benchmark rows are currently sourced for this pair.
Deep dive
The capability footprint differs most on vision: Kimi K2.5, multimodal input: Kimi K2.5, function calling: Kimi K2.5, and structured outputs: Kimi K2.5. 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 Kimi K2.5 has $0.44/1M input tokens. Provider availability is 0 tracked routes versus 10. 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 Kimi K2.5 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. It also helps separate model capability from provider packaging, which can change cost and latency.
FAQ
Is Code Cushman 002 or Kimi K2.5 open source?
Code Cushman 002 is listed under Proprietary. Kimi K2.5 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 Kimi K2.5?
Kimi K2.5 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 002 or Kimi K2.5?
Kimi K2.5 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 Kimi K2.5?
Kimi K2.5 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 structured outputs, Code Cushman 002 or Kimi K2.5?
Kimi K2.5 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 002 and Kimi K2.5?
Code Cushman 002 is available on the tracked providers still being sourced. Kimi K2.5 is available on Cloudflare Workers AI, Fireworks AI, OpenRouter, Together AI, and NVIDIA NIM. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-06-04. Data sourced from public model cards and provider documentation.