---
title: "Gemini API Development: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/skills/google-gemini-gemini-api-dev/
description: "Gemini Interactions API patterns for Python and TypeScript, with a dated model list and deprecated-model rules."
---

# Gemini API Development: review, setup & limitations · Undominated.ai

> Gemini Interactions API patterns for Python and TypeScript, with a dated model list and deprecated-model rules.

[← Explore all skills](/skills/)

AI APPLICATION DEVELOPMENT / Google

# Gemini API Development

Gemini Interactions API patterns for Python and TypeScript, with a dated model list and deprecated-model rules.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/google-gemini/gemini-skills/tree/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/skills/gemini-api-dev)

SOURCE REVIEW

 Reviewed 2026-10-13
 Evidence 4 linked sources
 Publisher Google
 Licence [Apache-2.0 ↗](https://github.com/google-gemini/gemini-skills/blob/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/LICENSE)
 Revision ee9da5219575
 [Read what was—and wasn’t—checked ↓](#review)

“Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, speech generation (TTS), voice design, voice replication, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. Covers SDK usage and best practices for Gemini models and agents in Python and TypeScript.”

 [Google · upstream description ↗](https://github.com/google-gemini/gemini-skills/blob/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/skills/gemini-api-dev/SKILL.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - The file states that interactions are stored by default, retained 55 days on the paid tier and 1 day on the free tier, and that store=False also disables previous_interaction_id and background runs.
- It tells the agent to fetch the matching hosted documentation page before writing code, and marks the google-generativeai and @google/generative-ai SDKs as deprecated.

### A good fit for

 - Writing Gemini Interactions API calls in Python or TypeScript
- Checking whether a Gemini model or SDK in existing code is listed as deprecated
- Carry interaction-scoped settings forward explicitly when implementing a multi-turn client.

### Weigh up before choosing

 - If a user asks for a deprecated model, the file tells the agent to use gemini-3.8-flash instead and note the substitution. Check for that note when a specific model was required.
- Model IDs, SDK floors (google-genai >= 2.30.1, @google/genai >= 2.29.1) and retention periods are as written at this revision. The file says they override training data; they were not checked against the live API.
- The README states this is not an officially supported Google product. The README install command does not pin this revision.
- The pinned guide links storage opt-out to loss of previous_interaction_id and background execution; these API behavior claims were not exercised in this source review.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - skills/gemini-api-dev/SKILL.md (frontmatter, critical rules, quick start, Deep Research, managed agents, streaming, data model)
- README.md (skill table, installation, disclaimer)
- LICENSE Apache-2.0 text
- skills/gemini-api-dev/SKILL.md
- README.md
- LICENSE

### Our findings

 - The file lists current models, agents and SDK floors under the heading Critical Rules and says they override training data.
- tools, system_instruction and generation_config are interaction-scoped and must be re-specified each turn, per the file.
- The definition says tools, system instructions and generation configuration must be supplied again each interaction, and notes that opting out of storage disables previous-interaction chaining and background execution.

### Not established by this review

 - The installer was not run, and the skill was not executed against a project or service. No Gemini API call was made.
- references/migration.md and the linked hosted documentation pages were not opened.
- Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Add a skill to your workflow.

[Upstream setup instructions ↗](https://github.com/google-gemini/gemini-skills/blob/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/README.md)

DOCUMENTED COMMAND

 npx skills add google-gemini/gemini-skills --skill gemini-api-dev Copy command ↗

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

 - The README gives npx skills add google-gemini/gemini-skills --skill gemini-api-dev for this skill, plus plugin installs for Claude Code, Cursor, Codex and Antigravity.
- That command does not pin revision ee9da52195752ca83c2fca701d96bcb5a9c08d2d. Compare the installed SKILL.md and references/migration.md with that revision before use.
- The Python and TypeScript quick starts construct the client without an inline key; keep the Gemini API key in the environment.

### Before you start

 - Node.js and npm for the documented Skills installer
- A Gemini API key and google-genai or @google/genai only if you run the generated code

### Compatibility

Agent Skills-compatible hosts · Claude Code · Cursor · Codex · Antigravity · Gemini API (google-genai, @google/genai)

### Implementation

Python · TypeScript

### Host-mediated project files and Gemini API calls

 - Reads and writes application code in the working tree.
- Generated code calls the Gemini API with the user's key. Interactions are stored server-side unless store=False is set, per the file.
- Managed-agent examples provision a Google-hosted sandbox with environment="remote".

### Cost model

Source is Apache-2.0. Gemini API calls, Deep Research and managed agents are billed by Google to the user's account. Those charges were not measured.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Skill definition ↗](https://github.com/google-gemini/gemini-skills/blob/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/skills/gemini-api-dev/SKILL.md) Checked 2026-10-13 https://github.com/google-gemini/gemini-skills/blob/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/skills/gemini-api-dev/SKILL.md Supports: summary, upstreamDescription, whySelected, limitations, access, review
- [Install instructions and skill index ↗](https://github.com/google-gemini/gemini-skills/blob/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/README.md) Checked 2026-10-13 https://github.com/google-gemini/gemini-skills/blob/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/README.md Supports: install, compatibility
- [Repository licence ↗](https://github.com/google-gemini/gemini-skills/blob/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/LICENSE) Checked 2026-10-13 https://github.com/google-gemini/gemini-skills/blob/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/LICENSE Supports: license
- [Pinned continuation review W40 ↗](https://raw.githubusercontent.com/google-gemini/gemini-skills/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/skills/gemini-api-dev/SKILL.md) Checked 2026-10-15 https://raw.githubusercontent.com/google-gemini/gemini-skills/ee9da52195752ca83c2fca701d96bcb5a9c08d2d/skills/gemini-api-dev/SKILL.md Supports: review.findings, bestFor, limitations

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Gemini Live API Development ↗ Gemini Live API guidance for real-time audio, video and text over WebSockets, with stated session limits.](/skills/google-gemini-gemini-live-api-dev/)[### Agent Platform GenAI Inference ↗ Calls Gemini and third-party OpenMaaS models on Google Cloud Agent Platform, asking for model, project and region instead of defaulting.](/skills/google-agent-platform-inference/)[### Amazon Bedrock ↗ Bedrock model invocation, Knowledge Bases, Guardrails and AgentCore guidance, with quota, prompt-caching and cost-tracking workflows.](/skills/aws-amazon-bedrock/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Choose a toolkit](/tools/)
- [Inspect execution hosts](/agents/)
- [Check tool access](/mcp-servers/)
- [Check project dependencies](/check-repo/)
