Gemini 3.8 Flash
google/gemini-3.8-flashGemini 3.8 Flash is a Flash-tier reasoning model in Google's Gemini 3 series, released in September 2026 and described by Google as its most intelligent Flash model as of release. Google positions it for long-horizon software engineering, autonomous agents and complex enterprise workflows, with significant gains over 3.7 Flash in coding, agentic tasks and multi-step reasoning in specialized domains. It accepts text, image, video, audio and PDF input with text output, and suits demanding agentic and coding work.
- Input price
- $1.27
$1.50USD / 1M tokens - Output price
- $6.38
$7.50USD / 1M tokens - Context window
- 1M
- Max output
- 65.5K
Try the model
Playground
Try a prompt
Your response will appear here
Choose an example or write a prompt, then click Run.
Model card
Specifications
Pricing
- Input
- $1.27 / 1M tokens
- Output
- $6.38 / 1M tokens
- Cache read
- $0.13 / 1M tokens
Context & modalities
- Context window
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Input
- Text, image
- Output
- Text
Capabilities
- Chat
- Supported
- Vision
- Supported
- Reasoning
- Supported
- Structured output
- Supported
- Function calling
- Supported
- Audio input
- Supported
Access
- Provider
- Model ID
- google/gemini-3.8-flash
- Execution
- sync
- Base URL
- https://api.sandbase.ai
- API
- Chat Completions API
- Endpoint
- /v1/chat/completions
Independent evaluations
Benchmarks
Scores on standardized evaluations, compared with other models on SandBase.
Metrics sourced from Artificial Analysis · Intelligence Index v4.3
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/chat/completions" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "google/gemini-3.8-flash",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"Choose your model
Compare models
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
Gemini 3.8 FlashThis model Google | 1M | $1.27 | $6.38 | Sep 2, 2026 |
Google | 1M | $4.00 | $20.00 | Oct 13, 2026 |
Google | 64K | $1.50 | $7.50 | Oct 8, 2026 |
Google | 1M | $1.50 | $7.50 | Aug 13, 2026 |
Google | 1M | $0.30 | $2.50 | Jul 21, 2026 |
Google | 1M | $0.75 | $3.75 | Jul 21, 2026 |
Questions
FAQ
How do I call Google Gemini 3.8 Flash through SandBase?
Create a SandBase API key, then send requests with the model ID "google/gemini-3.8-flash" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.
How much does Google Gemini 3.8 Flash cost?
$1.27 per 1M input tokens and $6.38 per 1M output tokens with the current 15% discount (list price $1.50 / $7.50), billed per request from your SandBase balance.
What is the context window of Google Gemini 3.8 Flash?
1M tokens of context, with up to 65.5K output tokens per response.
How does Google Gemini 3.8 Flash score on benchmarks?
Google Gemini 3.8 Flash scores 40.9 on the Artificial Analysis Intelligence Index (v4.3), ranking #21 of 87 models on SandBase; Coding Index 76.3, Agentic Index 40.2. Source: Artificial Analysis, measured as Gemini 3.8 Flash (High).
Which features does Google Gemini 3.8 Flash support?
Google Gemini 3.8 Flash supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.
Do I need a separate Google account?
No. One SandBase API key and balance gives you access to Google Gemini 3.8 Flash and the other models in the catalog; you do not need to sign up with Google separately.