Invoking Gemini

Delegate tasks to Google's Gemini models when they offer advantages over Claude.

When to Use Gemini

Image generation:

• Blog header images, illustrations, diagrams
• Style-guided image creation (risograph, editorial, etc.)
• Text rendering in images

Structured outputs:

• JSON Schema validation with property ordering guarantees
• Pydantic model compliance
• Strict schema adherence (enum values, required fields)

Cost optimization:

• Parallel batch processing (Gemini 3 Flash is lightweight)
• High-volume simple tasks

Multi-modal tasks:

• Image analysis with JSON output
• Video processing
• Audio transcription with structure

Setup

uv pip install requests pydantic

Credentials — Option A (recommended): Cloudflare AI Gateway

Source /mnt/project/proxy.env with CFACCOUNTID, CFGATEWAYID, CFAPITOKEN. Requests route through Cloudflare AI Gateway, bypassing IP blocks. Google API key stored in gateway via BYOK.

Credentials — Option B: Direct Google API

If no proxy.env, falls back to direct: GOOGLEAPIKEY.txt or API_CREDENTIALS.json.

Image Generation

Generate images using Gemini's native image models. This is the primary way to create illustrations, blog headers, diagrams, and visual content.

Quick Start

import sys
sys.path.append('/mnt/skills/user/invoking-gemini/scripts')
from gemini_client import generate_image

# One call — returns {"path": "...", "caption": "..."} or None
result = generate_image("A watercolor painting of a mountain lake at sunset")
print(result["path"])  # /mnt/user-data/outputs/gemini_image_1740000000.png

Function Signature

generate_image(
    prompt: str,                    # The image description
    output_path: str = None,        # Auto-generates if omitted
    model: str = "nano-banana-2",   # Default: fast. Use "image-pro" for quality
    temperature: float = 0.7,       # 0.5-0.7 for diagrams, 0.7-0.8 for illustrations
) -> dict | None
# Returns: {"path": "/mnt/user-data/outputs/gemini_image_*.png", "caption": str|None}
# Returns None on failure

Model Selection

Complete Blog Header Example

import sys
sys.path.append('/mnt/skills/user/invoking-gemini/scripts')
from gemini_client import generate_image

# 1. Compose prompt with style prefix + subject
style_prefix = (
    "Style: Risograph-inspired editorial illustration. "
    "Visible halftone dot texture and slight color misregistration between layers. "
    "Limited ink palette: deep indigo, warm coral, and sage green on off-white paper. "
    "Layered transparency where colors overlap creates rich secondary tones. "
    "Modern and professional — the aesthetic of an indie design studio, not a fantasy novel. "
    "Generous whitespace. No photorealism, no glow effects, no cyberpunk. No text or labels."
)
subject = "A raven perched on a stack of books, observing a network graph"
prompt = f"{style_prefix}\n\nSubject: {subject}. Wide landscape format, suitable as a blog header."

# 2. Generate (use image-pro for published content)
result = generate_image(prompt, model="image-pro", temperature=0.75)

if result:
    print(f"Saved: {result['path']}")
    # 3. Present to user
    # present_files([result["path"]])

Prompt Patterns

• Style prefix + subject: Prepend a style description, then describe the subject
• Be specific about style: "Risograph-inspired editorial illustration" not "a nice picture"
• Include composition: "Wide landscape format" / "centered, high contrast"
• Text rendering: "A poster with the text 'SALE' in bold red letters" (works well with image-pro)
• Negative constraints: "No photorealism, no glow effects" to avoid defaults

Custom Output Path

result = generate_image(
    "A logo for a coffee shop called 'Bean There'",
    output_path="/mnt/user-data/outputs/coffee_logo.png"
)

Basic Text Usage

import sys
sys.path.append('/mnt/skills/user/invoking-gemini/scripts')
from gemini_client import invoke_gemini

response = invoke_gemini(
    prompt="Explain quantum computing in 3 bullet points",
    model="flash",  # gemini-3.8-flash (default)
)
print(response)

Structured Output

Use Pydantic models for guaranteed JSON Schema compliance:

from gemini_client import invoke_with_structured_output
from pydantic import BaseModel, Field

class BookAnalysis(BaseModel):
    title: str
    genre: str = Field(description="Primary genre")
    key_themes: list[str] = Field(max_length=5)
    rating: int = Field(ge=1, le=5)

result = invoke_with_structured_output(
    prompt="Analyze the book '1984' by George Orwell",
    pydantic_model=BookAnalysis
)
print(result.title)  # "1984"

Nested models are supported. Gemini's responseSchema rejects $ref/$defs, which pydantic emits for every nested model, so the client inlines them before sending:

class Finding(BaseModel):
    claim: str
    confidence: Literal["high", "medium", "low"]
    note: str | None = None

class Analysis(BaseModel):
    findings: list[Finding]     # nested — inlined for you
    gaps: list[str]

Budget output generously. Thinking tokens count against maxoutputtokens (default 32768). Too low and the JSON truncates mid-object, which surfaces as a pydantic parse error rather than a length error — the client now detects finishReason=MAX_TOKENS and says so explicitly.

Parallel Invocation

from gemini_client import invoke_parallel

results = invoke_parallel(
    prompts=["Summarize Hamlet", "Summarize Macbeth", "Summarize Othello"],
    model="lite",  # gemini-3.5-flash-lite — cheap/fast tier for batch
)

Available Models

The current frontier Flash is gemini-3.8-flash (GA 2026-09-02), the default and the flash alias. Google shipped three Flash generations in six weeks: 3.6 (2026-07-21), 3.7 (2026-08-13), 3.8 (2026-09-02). Each stays callable under a pinned alias (flash-3.7, flash-3.6, flash-3.5, flash-3), and none has a shutdown date. gemini-3.1-flash-lite-preview from earlier docs is gone (shut down 2026-05-25).

The Pro tier is off routing. gemini-3.1-pro-preview costs 2.7× the input and 3.2× the output of 3.8 Flash at today's rates and loses to the 3.5+ Flash line on the coding and agentic benchmarks that matter here. Do not target it; the pro alias now resolves to gemini-3.8-flash, and "maximum reasoning" means thinking_level='high' on Flash.

Text / Reasoning Models

$0.75 → $1.50 means introductory pricing: Google's pricing page (fetched 2026-09-03) lists 3.6, 3.7 and 3.8 Flash at $0.75 in / $3.75 out through 2026-12-31 and $1.50 / $7.50 from 2027-01-01. Context caching is $0.075 → $0.15; Batch is half of standard. Output prices include thinking tokens.

Image Models

See [references/models.md](references/models.md) for full details.

Thinking Budget (Gemini 3.x)

Gemini 3.x models reason before responding. The parameter changed in 2026: integer thinkingbudget is gone; use string thinkinglevel ∈ {minimal, low, medium, high}. Default for 3.5–3.8 Flash is medium. For transcription / classification / extraction tasks, pass thinkinglevel='minimal' or the model will silently spend output tokens on reasoning (symptom: empty response with finishReason=MAXTOKENS).

3.7 and 3.8 Flash reject minimal with HTTP 400 (Thinking level MINIMAL is not supported for this model); low is their floor. The client downgrades minimal to low on those two models and prints a note to stderr, so existing callers keep working. Measured on 3.8 (2026-09-03): low spent 0 thinking tokens on a one-word reply, the default medium spent 79. On 3.7, low still spent 45–88, and a maxoutputtokens=50 call at low hit MAX_TOKENS and returned None, so budget output generously there. If a job needs a true no-thinking pass, pin flash-3.6 or lite, which still accept minimal.

response = invoke_gemini(
    prompt="Transcribe this image.",
    model="flash",
    image_path="/tmp/screenshot.png",
    max_output_tokens=4000,
    thinking_level="minimal",  # don't burn output budget on reasoning
)

Error Handling

response = invoke_gemini(prompt="...", model="flash")
if response is None:
    print("API call failed — check credentials")

result = generate_image("...")
if result is None:
    print("Image generation failed — check credentials or try again")

Common issues: Missing API key → see Setup. Rate limit → auto-retries with backoff. Network error → returns None.

Advanced Features

Custom Generation Config

response = invoke_gemini(
    prompt="Write a haiku",
    model="flash",                  # gemini-3.8-flash
    temperature=0.9,
    max_output_tokens=200,
    top_p=0.95,
    thinking_level="low",           # haiku is short; modest reasoning is fine
)

Multi-modal Input

from pydantic import BaseModel
from gemini_client import invoke_with_structured_output

class ImageDescription(BaseModel):
    objects: list[str]
    scene: str
    colors: list[str]

result = invoke_with_structured_output(
    prompt="Describe this image",
    pydantic_model=ImageDescription,
    image_path="/mnt/user-data/uploads/photo.jpg"
)

See [references/advanced.md](references/advanced.md) for more patterns.

Troubleshooting

"No credentials configured": Create /mnt/project/proxy.env with CF credentials, or add GOOGLEAPIKEY.txt.

CF Gateway 401/403: Verify CFAPITOKEN has AI Gateway permissions. If not using BYOK, add GOOGLEAPIKEY to proxy.env.

Import errors: uv pip install requests pydantic

Image generation returns None: Check credentials. If persistent, try model="nano-banana-2" (more reliable than image-pro). Check for content policy blocks in error output.