How do I use Gemini 3.8 Flash in OpenCode or Cline?
Gemini 3.8 Flash runs on Standard Compute as google/gemini-3.8-flash on every plan from $19 a month, a fixed compute budget that stops new requests with HTTP 402 at 100%, with no Google Cloud project or AI Studio key. OpenCode, Cline, Kilo Code and Claude Code connect with one key; Gemini CLI does not, because it only speaks Google's Gemini API.
| Model | Google's September 2026 Flash model, which Google describes as engineered for long-horizon software engineering and autonomous agents. |
|---|---|
| Model ID | google/gemini-3.8-flashShort form gemini-3.8-flash also works |
| Base URL | https://api.stdcmpt.com/v1Claude Code uses https://api.stdcmpt.com |
| Context | 1,048,576 input and 65,536 output tokens at GoogleA request here takes up to about 850K input and 50K output tokens |
| Input | Text and imagesGoogle's API also takes video, audio and PDF; those are not offered here |
| Reasoning | Always on; low, medium or high |
Copy a working config
These four agents take any OpenAI- or Anthropic-compatible endpoint. Kilo Code also needs the context size so it knows when to compact. Select Gemini 3.8 Flash next to a stronger model and set the model to standardcompute if you want only the hard steps to go up.
{
"$schema": "https://opencode.ai/config.json",
"model": "standardcompute/google/gemini-3.8-flash",
"provider": {
"standardcompute": {
"npm": "@ai-sdk/openai-compatible",
"name": "Standard Compute",
"options": {
"baseURL": "https://api.stdcmpt.com/v1",
"apiKey": "{env:STANDARDCOMPUTE_API_KEY}"
},
"models": {
"google/gemini-3.8-flash": { "name": "Gemini 3.8 Flash" },
"standardcompute": { "name": "Smart routing" }
}
}
}
}
Replace YOUR_API_KEY with a key from the dashboard. This config reads your key from STANDARDCOMPUTE_API_KEY; export it with a key from the dashboard. Full setup: OpenCode, Cline, Aider and other tools, Kilo Code, Claude Code.
What it costs
| Per 1M tokens | Through Dec 31, 2026 | From Jan 1, 2027 |
|---|---|---|
| Input | $0.75 | $1.50 |
| Cached input | $0.075 | $0.15 |
| Output | $3.75 | $7.50 |
Gemini API paid tier, standard rates. Batch and Flex are half price; Priority costs 1.8 times standard. Source: Gemini API pricing, checked October 13, 2026.
Flash suits the bulk of an agent's steps: edits, tool calls and code search.
What works differently here
- Thinking cannot be switched off and Google rejects minimal; the lowest setting is low.
- There is no EU or US pin for Gemini 3.8 Flash yet. Gemini 3.5 Flash-Lite has both.
Other ways to run Gemini 3.8 Flash
| Gemini APIPay per token | First-party through Google AI Studio, with Batch and Flex at half price. |
|---|---|
| Vertex AIPay per token | Google Cloud billing and quotas for procurement teams. |
| Google AI plans with AntigravitySubscription | Antigravity and Antigravity CLI within weekly limits; Gemini models only. Since June 18, 2026 these plans no longer cover Gemini CLI. |
| Standard ComputeMonthly plan | Gemini 3.8 Flash on an Anthropic-compatible endpoint as well, so Claude Code can run it. |
FAQ
Gemini 3.8 Flash or Gemini 3.1 Pro for coding agents?
Gemini 3.8 Flash. Artificial Analysis scores it 41 on its Intelligence Index against 30 for 3.1 Pro, and Google lists it lower on input and output.
Gemini 3.8 Flash or Gemini 2.5 Flash?
Gemini 3.8 Flash. Gemini 2.5 Flash is being retired: it can no longer be added to a model selection, and it stops on October 20, 2026.
Sources: Gemini API pricing; Google: Gemini 3.8 Flash; Artificial Analysis: Gemini 3.8 Flash; Artificial Analysis: Gemini 3.1 Pro Preview
Create your key
Sign in, create a key in the dashboard and paste it into the config above.