Gemini 3.8 Flash API Guide: Model ID, Pricing, Limits, and Migration

Google released Gemini 3.8 Flash to general availability on September 2, 2026. The exact Gemini Developer API model ID is gemini-3.8-flash. Google positions it as its most intelligent Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows.

That positioning makes 3.8 the new top stable Flash candidate, but it is not a universal migration command. Its standard introductory price matches 3.7 through the end of 2026, then doubles on January 1, 2027. Evaluate both quality and cost per accepted task before moving a working integration.

Gemini 3.8 Flash specifications

The official model page publishes the following contract:

The output type is important: Gemini 3.8 Flash can understand media, but it does not generate images or audio. It is also not a Live API model. Use a dedicated image, speech, or Live model when the result must be media or a real-time audio stream.

Supported tools and important exclusions

Gemini 3.8 Flash supports context caching, code execution, file search, function calling, structured outputs, Search grounding, Maps grounding, URL context, and computer use in Preview. These capabilities make it a plausible candidate for tool-heavy coding and agent workflows.

Three exclusions prevent common integration mistakes:

• minimal thinking is not supported and returns an error; use low, medium, or high.
• Image generation and audio generation are not supported.
• Live API is not supported.

Do not infer that every feature uses the same billing unit or availability. Grounding, cache storage, computer use, and consumption modes each have their own terms.

Gemini 3.8 Flash pricing

Google's current pricing page lists USD per 1 million tokens. Output prices include thinking tokens.

Standard and Priority currently show free-tier access, while Batch and Flex do not. Context-cache token charges and hourly storage also change in 2027. Search and Maps grounding have separate request-based pricing after their included monthly allowance.

The meaningful measure is not the input rate alone:

cost per accepted task = input + thinking/output + tools + grounding + cache + retries

If 3.8 reduces retries or solves a tool chain in one pass, it can beat a cheaper model operationally. If output becomes more verbose or a task did not need its capabilities, the same model can cost more without improving the result.

Make your first request

Google's text-generation guide uses the Interactions API for its current 3.8 examples. With the Google GenAI Python SDK:

python
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Explain the failure modes in this deployment plan.",
)

print(interaction.output_text)

The equivalent REST request is:

bash
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "input": "Explain the failure modes in this deployment plan."
  }'

Start with the default thinking behavior, then set thinking_level explicitly when latency and cost must be comparable across models. Inspect the complete response rather than relying only on a convenience text field when your workflow includes thoughts, tools, or interleaved content.

Should you migrate from Gemini 3.7 Flash?

Google calls 3.8 its most intelligent Flash model and now describes 3.7 as the previous generation. That is provider guidance, not proof for your private workload. A safe comparison keeps prompts, tools, thinking level, timeout, and acceptance criteria fixed.

Include ordinary requests, long context, structured output, tool failures, refusals, and multi-turn state. Record first-attempt success, tool-call correctness, P50/P95 latency, input and output tokens, retries, safety failures, and total cost per accepted task. Put both IDs behind configuration, canary 3.8 on a narrow workload, and keep 3.7 as an immediate rollback until the new path is stable.

For a broader comparison with Flash-Lite and Pro options, use the separate Gemini text-model guide. This page remains dedicated to the Gemini 3.8 Flash contract and migration decision.

Bottom line

gemini-3.8-flash is a stable, callable model today. Its strongest documented reasons to test are long-horizon software engineering, autonomous agents, complex tool use, and the full 1M-token input window. The introductory 2026 price is attractive, but plan for the published 2027 increase and adopt it only where measured results justify the switch.