MedGemma vs text-curie
MedGemma (2024) and text-curie (2020) are compact production models from Google DeepMind and OpenAI. MedGemma ships a not-yet-sourced context window, while text-curie ships a 2K-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.
MedGemma is safer overall; choose text-curie when provider fit matters.
Decision scorecard
Local evidence first| Signal | MedGemma | text-curie |
|---|---|---|
| Best for | multimodal apps and tool-calling agents | general production evaluation |
| Decision fit | Agents, Vision, and JSON / Tool use | General |
| Context window | — | 2K |
| Cheapest output | - | - |
| Provider routes | 1 tracked | 0 tracked |
| Shared benchmarks | 0 rows | 0 rows |
Decision tradeoffs
- MedGemma has broader tracked provider coverage for fallback and procurement flexibility.
- MedGemma uniquely exposes Vision, Multimodal, and Function calling in local model data.
- Local decision data tags MedGemma for Agents, Vision, and JSON / Tool use.
- text-curie has the larger context window for long prompts, retrieval packs, or transcript analysis.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
MedGemma
Unavailable
No complete token price in local provider data
text-curie
Unavailable
No complete token price in local provider data
Cost delta unavailable until both models have sourced input and output token prices.
Switch friction
- No overlapping tracked provider route is sourced for MedGemma and text-curie; plan for SDK, billing, or endpoint changes.
- Check replacement coverage for Vision, Multimodal, and Function calling before moving production traffic.
- No overlapping tracked provider route is sourced for text-curie and MedGemma; plan for SDK, billing, or endpoint changes.
- MedGemma adds Vision, Multimodal, and Function calling in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2024-07-01 | 2020-06-01 |
| Context window | — | 2K |
| Parameters | — | 6.7B |
| Architecture | decoder only | decoder only |
| License | Proprietary | Unknown |
| Knowledge cutoff | - | 2019-10 |
Pricing and availability
| Pricing attribute | MedGemma | text-curie |
|---|---|---|
| Input price | - | - |
| Output price | - | - |
| Providers | - |
Pricing not yet sourced for either model.
Capabilities
| Capability | MedGemma | text-curie |
|---|---|---|
| Vision | Yes | No |
| Multimodal | Yes | No |
| Reasoning | No | No |
| Function calling | Yes | No |
| Tool use | Yes | No |
| Structured outputs | Yes | No |
| 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: MedGemma, multimodal input: MedGemma, function calling: MedGemma, tool use: MedGemma, and structured outputs: MedGemma. 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: MedGemma has no token price sourced yet and text-curie has no token price sourced yet. Provider availability is 1 tracked routes versus 0. Treat unknown pricing as an integration gap, then verify the route you will actually call before estimating production spend.
Choose MedGemma when vision-heavy evaluation and broader provider choice are central to the workload. Choose text-curie when provider fit 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 MedGemma or text-curie open source?
MedGemma is listed under Proprietary. text-curie is listed under Unknown. 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, MedGemma or text-curie?
MedGemma 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, MedGemma or text-curie?
MedGemma 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, MedGemma or text-curie?
MedGemma 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, MedGemma or text-curie?
MedGemma 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 MedGemma and text-curie?
MedGemma is available on GCP Vertex AI. text-curie is available on the tracked providers still being sourced. Provider coverage can affect latency, region availability, compliance posture, and fallback options. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Continue comparing
Last reviewed: 2026-05-19. Data sourced from public model cards and provider documentation.