Overall · Snapshot captured:
- Artificial Analysis Intelligence Index
- 40.9
- Coding Index
- 76.3
- Agentic Index
- 40.2
Back to models
Artificial Analysis Design Arena
Gemini 3.8 Flash
FeaturedGemini 3.8 Flash is Google's newest Gemini Flash model, featuring hybrid reasoning, 1M token context window, advanced multimodal capabilities, and sub-second execution. Available through the DOS.AI gateway with unified billing and OpenAI compatibility.
Capabilities:Hybrid reasoningVisionLong context (1M)Tool callingCode generationStreaming
Modalities
Text input tokens
Image input
Text generation tokens
Input / Output Price
$0.75/$3.75/ 1M
Context Length
1M tokens
Released
Sep 5, 2026
Providers
Different companies host the same model. DOS.AI routes your request to one of them based on the routing mode you pick - Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).
Reasoning effortⓘAll
| Provider | Input /1M | Output /1M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|
Google | $0.75 | $3.75 | $0.075 | 2.72 s | - | 95.5% |
Pricing
Rates from the DOS.AI catalog for the billing units shown. Caching and provider discounts mean the price actually paid is often below the listed one.
Weighted Averagei
Weighted Avg Input Price
$0.747/ 1M tokens
-$0.003 /M compared to average list price
Weighted Avg Output Price
$3.751/ 1M tokens
Equal to list price
Cache read
$0.075/ 1M tokens
Rate for cached input tokens
Price History1 verified endpoints
Weighted Average($0.75)
Provider↕ | Effective in /M↕ | Effective out /M↕ | Cache read /M↕ | Latency↕ | Throughput↕ | Uptime↕ | Savings↕ |
|---|---|---|---|---|---|---|---|
Google | $0.75 | $3.75 | $0.07 | 2.72 s | - | 95.5% | - |
Based on settled billing for the last 30d.Effective pricing represents the average price paid for requests to this endpoint, factoring in caching, discounts, and tiered pricing. Listed pricing shows the posted provider list prices.
Observed performance
Provider results (Last 7 days).
Updated Oct 22, 03:51 PM UTC
ProviderUptimeP50 responseP95 responseLatency spreadSamples
Google
246 samples
95.5%
2.72 s
44.01 s
246
Google
246 samples
- Uptime
- 95.5%
- P50 response
- 2.72 s
- P95 response
- 44.01 s
- Latency spread
Uptime is based on observed valid provider attempts. Not a contractual guarantee.
Latency is measured to provider response headers, not end-to-end completion.
Observed reliability
Success rate across observed provider requests. This is historical sample data, not live health or an uptime guarantee.
Request observations
Last 7 days
- Observed success rate
- 95.53%
- Observed requests
- 246
Benchmarks
Dated third-party measurements with source links.
Overall · Snapshot captured:
- Elo
- 1323
- Win rate
- 54%
- Rank
- #12
Observed gateway latency
Window: 7d
- Lowest provider median TTFT
- -
- Lowest provider median latency
- 2.72 s
- Lowest provider P95 latency
- 44.01 s
- Providers with latency samples
- 1
API Integration
Use the DOS API to integrate Gemini 3.8 Flash into your applications. Compatible with standard OpenAI SDKs for easy drop-in migration.
</>Run inference
curl https://api.dos.ai/v1/chat/completions \
-H "Authorization: Bearer $DOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.8-flash",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'