兔子API 兔子API
中

provider-capability

Google Gemini Text, reasoning, and code

Direct answerUse this guide to understand the Google Gemini Text, reasoning, and code capability, then verify the exact callable model ID, endpoint, and price in the model marketplace before integration.

Updated · Reviewed

Capability boundary

The Google Gemini Text, reasoning, and code catalog describes the jobs this class of model is intended to solve. It does not mean that every listed model shares request fields, input limits, or output formats. Read each model card together with its lifecycle status, origin, and official source. A platform provider may host models from several original vendors, so both the displayed ID and origin matter.

Selection criteria

Evaluate text, reasoning, and code workloads separately. Factual answers need accuracy and grounded citations; difficult reasoning needs consistency and verifiable outcomes; coding needs repository-level edits and passing tests; structured output needs schema adherence. Agent workflows also need correct tool choice, argument construction, and recovery from failed calls. A larger context window alone does not guarantee a better production result, so compare time to first token, end-to-end latency, output limits, concurrency, and reasoning cost.

Integration and protocol boundary

Confirm the exact model ID, authentication method, endpoint, and request schema in the Google Gemini official documentation, then look for the same exact ID and supported endpoint in this site's model marketplace. Changing only the base URL does not guarantee an identical response contract. Streaming events, asynchronous jobs, file uploads, tool calls, and error payloads may require separate adapters.

Production checklist

Build a repeatable evaluation from representative inputs and record the model ID, parameters, input version, and result. Measure success rate, tail latency, throttling, timeout behavior, cost per completed task, and safety outcomes. Prepare a replacement path for preview or legacy models. The official catalog explains product boundaries; callable availability, channel status, and current pricing remain the responsibility of the model marketplace.

Reviewed provider catalog

Models in this capability

These are provider-catalog models, not a promise of availability on this site. Confirm callable IDs, endpoints, and pricing in the model marketplace.

Text, reasoning, and code

Check live availability in the model marketplace

Use cases

  • Complex Q&A, reasoning, and structured output
  • Code generation, tool use, and agent workflows

FAQ

How should I choose a Google Gemini Text, reasoning, and code model?

Start from the required input and output, then compare quality, latency, context or media limits, tool support, lifecycle status, and total request cost with representative production samples.

Does every model in the official catalog work on this site?

Not necessarily. The documentation records the provider catalog; callable IDs, channel support, endpoints, and current prices must be confirmed in the model marketplace.

What should be tested before production rollout?

Pin the exact model ID and endpoint, test success and error responses, measure quality and latency on real inputs, set timeouts and bounded retries, and monitor provider deprecations.

  • Google GeminiGoogle recommends Interactions API for new direct integrations. This gateway currently exposes Gemini-native GenerateContent and streamGenerateContent, not Interactions, and recommends Bearer while accepting x-goog-api-key compatibility.
  • General text, chat, and reasoning model guideGeneral text models cover Q&A, writing, extraction, and analysis, while reasoning models fit multi-step problems; production selection should balance task accuracy, latency, cost, and control.
  • AI API quickstart: from API key to first requestAn AI API call needs a matching base URL, API key, model ID, and endpoint; start with minimal curl, then add error handling, cost controls, and key security.
  • Common AI API error codes and troubleshootingHandle AI API failures by parsing the HTTP status, provider code, error type, message, retry hints, and request ID together. Fix request, authentication, billing, and hard-quota causes first; retry only transient throttling, network failures, and selected 5xx errors with strict bounds.

Official sources

  1. Gemini Models Official
  2. Gemini API Reference Official
  3. Gemini API Getting Started Official
  4. Gemini Interactions API Overview Official
  5. Migrate to the Interactions API Official
  6. Gemini API Streaming Official
  7. Gemini Function Calling Official
  8. Gemini API Key Best Practices Official
  9. Gemini API Errors Official