Gemini 3.8 Flash
Google's Gemini 3.8 Flash is a fast, cost-efficient workhorse model for agentic coding, multimodal understanding and long-horizon tool use, with a 1M-token context window.
Gemini 3.8 Flash is Google's Flash-series model released in September 2026, built on Gemini 3.7 Flash and positioned between the deep-reasoning Pro tier and the high-throughput Flash-Lite tier, which Google describes as its smartest workhorse. It accepts text, images, audio, video and PDFs as input and returns text, with a 1,048,576-token context window and up to 65,536 output tokens.
On software engineering it scores 90.8% on Terminal-bench 2.1, 61.6% on SWE-Bench Pro and 51.9% on SWE-Atlas; on agentic work it reaches 38.1% on τ³-bench Banking, and on multimodal understanding 86.2% on CharXiv and 35.0% on GDP.pdf. It supports function calling, structured outputs, code execution, context caching, file search, URL context, search grounding and computer use in preview, and exposes LOW, MEDIUM and HIGH thinking levels with MEDIUM as the default.
It is built for long-horizon software engineering such as vulnerability discovery and automated patch repair, for autonomous multi-step agents that iterate on tool calls, and for enterprise workflows that need multi-step reasoning. It also handles interactive video understanding, up to roughly 45 minutes of video with audio. Pricing is $0.75 per million input tokens and $3.75 per million output tokens.
Updated:
MODEL ID
gemini-3.8-flash- Context
- 1.049M
- Max output
- 65.536K
- Recommended API
- messages
- Input
- text / image / video / file / audio
- Output
- text
Providers
5 providersCompare API prices across providers. Select a provider to view all charges and conditions.
Reasoning
- Default effort
- medium
- Enabled by default
- Yes
- Always enabled
- Yes
- Available effort levels
- high / medium / low
Quick Start
Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.
Get your API key
Create a key from your Felo API Platform account and set it as an environment variable.
export FELO_API_KEY="YOUR_API_KEY"Make your first request
Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.
gemini-3.8-flashThis model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.
const response = await fetch("https://openapi.felo.ai/api/v1/messages", {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.FELO_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "gemini-3.8-flash",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());Using third-party SDKs
Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.
Enable streaming
Add stream: true to receive responses as server-sent events.
curl -N https://openapi.felo.ai/api/v1/messages \
-H "Authorization: Bearer $FELO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.8-flash",
"max_tokens": 1024,
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"stream": true
}'Endpoint
Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.
Messages
Anthropic-compatible messages for Claude-style clients.
POST
https://openapi.felo.ai/api/v1/messagesParameters
modelstringgemini-3.8-flashPublic model ID to call.max_tokensinteger—Maximum generated tokens.messagesarray—Conversation messages for Chat Completions.include_reasoning———reasoning———reasoning_effort———response_formatobject—Request structured output when supported.seed———stop———structured_outputs———temperaturenumber—Controls response variety when supported.tool_choicestring or object—Controls whether a tool should be called.toolsarray—Tool calling definitions following compatible schema.top_p———Frequently asked questions
What is Gemini 3.8 Flash?
Gemini 3.8 Flash is Google's Flash-series model released in September 2026, built on Gemini 3.7 Flash and positioned between the deep-reasoning Pro tier and the high-throughput Flash-Lite tier, which Google describes as its smartest workhorse. It accepts text, images, audio, video and PDFs as input and returns text, with a 1,048,576-token context window and up to 65,536 output tokens. On software engineering it scores 90.8% on Terminal-bench 2.1, 61.6% on SWE-Bench Pro and 51.9% on SWE-Atlas; on agentic work it reaches 38.1% on τ³-bench Banking, and on multimodal understanding 86.2% on CharXiv and 35.0% on GDP.pdf. It supports function calling, structured outputs, code execution, context caching, file search, URL context, search grounding and computer use in preview, and exposes LOW, MEDIUM and HIGH thinking levels with MEDIUM as the default. It is built for long-horizon software engineering such as vulnerability discovery and automated patch repair, for autonomous multi-step agents that iterate on tool calls, and for enterprise workflows that need multi-step reasoning. It also handles interactive video understanding, up to roughly 45 minutes of video with audio. Pricing is $0.75 per million input tokens and $3.75 per million output tokens.
How is usage billed?
Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.
