Context
1M
Input
text, file, image, audio, video
Output
text
Tool calling
Supported
About this model
Gemini 3.5 Flash is Google's high-efficiency multimodal model offering near-Pro-level coding and reasoning at Flash-tier speed and cost. It is optimized for coding, parallel agentic execution, multimodal understanding, and scalable production workloads.
Input modalities
text
Accepted as model input
file
Accepted as model input
image
Accepted as model input
audio
Accepted as model input
video
Accepted as model input
Providers
Available routing options for this model through OneInfer.
Available
Input tokens
$1.500 / 1M tokens
Output tokens
$9.000 / 1M tokens
Routing
OneInfer optimized
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Input tokens | $1.500 / 1M tokens |
| Output tokens | $9.000 / 1M tokens |
| Cached input tokens | $0.150 / 1M tokens |
Performance
Published evaluation results associated with this model.
Coding
Terminal-bench 2.176.2
SWE-Bench Pro (Public)55.1
Agentic
MCP Atlas83.6
Toolathlon56.5
UI Control
OSWorld-Verified78.4
Expert Tasks
Finance Agent v257.9
GDPval-AA (Elo)1656
Multimodal
CharXiv Reasoning84.2
MMMU-Pro83.6
Blueprint-Bench 233.6
Long Context
MRCR v2 (8-needle) 128K77.3
MRCR v2 (8-needle) 1M26.6
Reasoning
Humanity's Last Exam40.2
ARC-AGI-272.1
API example
curl https://api.oneinfer.ai/v1/ula/chat/completions \
-H "Authorization: Bearer $JWT_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3.5-flash",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'