Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/oyi77/1ai-skills/gemini-api-devnpx skills add oyi77/1ai-skills --skill gemini-api-devgit clone --depth 1 https://github.com/oyi77/1ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/oyi77/1ai-skills/gemini-api-dev)<a href="https://agentmods.dev/skills/oyi77/1ai-skills/gemini-api-dev"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/gemini-api-dev.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.02896 |
| Opus 5 | $0.00026 | $0.01448 |
| Sonnet 5 | $0.00010 | $0.00579 |
| Haiku 4.5 | $0.00005 | $0.00290 |
Grade A, and why
gemini-api-dev scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| "I will just use curl" | SDK handles retries, streaming, auth, and type safety | How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Api Dev
When to Use
Trigger phrases:
-
"gemini api dev"
-
"When building apps powered by Google Gemini models"
-
"When processing multimodal inputs (text + images + audio + video)"
-
"When implementing function calling or tool use with Gemini"
-
When building apps powered by Google Gemini models
-
When processing multimodal inputs (text + images + audio + video)
-
When implementing function calling or tool use with Gemini
-
When using Gemini for grounding with Google Search
When NOT to Use
- For OpenAI-compatible APIs (use OpenAI skills)
- For local model inference (use Ollama skills)
- For fine-tuning (use Vertex AI training skills)
Overview
The Google Gemini API provides access to Google's most capable AI models — Gemini 2.5 Pro, 2.5 Flash, and Gemini Nano — through a unified SDK. It supports text generation, multimodal understanding (images, audio, video, PDFs), function calling, and grounding with Google Search. The API is available via the google-genai Python SDK and @google/genai TypeScript SDK, both providing first-class async support, streaming generators, and type-safe response handling.
Gemini 2.5 Pro excels at complex reasoning, code generation, and multi-turn conversations with a 1-million-token context window. Gemini 2.5 Flash is optimized for speed and cost-efficiency while maintaining strong reasoning capabilities, making it suitable for high-volume production workloads. Nano models run on-device for Android and Chrome, handling summarization, smart reply, and text classification without network calls.
The API architecture follows a content-based message model: each request sends contents arrays with role (user or model) and parts — which can be text, inline_data (base64-encoded images/audio), file_data (PDFs, videos), function_call, or function_response. Configuration options include systemInstruction for persona setting, temperature (0.0–2.0), topP, topK, maxOutputTokens, stopSequences, and safetySettings for content filtering.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 283 lines · 52 tokens per session scan A e1b084f8c2bc
gemini-api-dev is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 2,896 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
LLM
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
using-llm
List available large language models and send chat completion requests programmatically. Use this skill when you need to call an LLM within a snippet, including model comparison, visual understanding, batch inference, and model performance testing.
dspy-react-agent-builder
Use for ReAct agents, tool-calling agents, dspy.ReAct, multi-step reasoning and acting, and GEPA agent optimization.
audio-prompting
Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering.
image-prompting
Use when crafting still-image prompts for any generative model — composition, identity sheets, edits, try-on, and photoreal personas.
video-prompting
Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining.