Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Context
1Mtokens
About 1,498 pages of text at once
Max output
66Ktokens
About 94 pages in one answer
Intelligence
30.5/ 100
Above 53% of the catalogue
Output speed
74tokens/s
A 500-word answer in about 9.5 s
From public market statistics for this model
First token
2.8s
Reasoning models start later
From public market statistics for this model
Health, 30 days
68.14%
0 of 30 days without a fault
IranRouter’s measurements
Price & cost
Every rate in Rial. A request pays only for the tokens it actually uses.
| Input | 2,055,745 | IRR / 1M tokens |
|---|---|---|
| Output | 10,278,724 | IRR / 1M tokens |
| Reasoning tokens | 10,278,724 | IRR / 1M tokens |
| Cache read | 205,574 | IRR / 1M tokens |
| Cache write, 5 minutes | 114,208 | IRR / 1M tokens |
| Image input tokens | 2,055,745 | IRR / 1M tokens |
| Audio input | 2,055,745 | IRR / 1M tokens |
| Cached audio input | 205,574 | IRR / 1M tokens |
| Per web search | 38,374 | IRR |
With prompt caching, the fixed part of your prompt is billed at the cache-read rate on later requests.
What would this model cost you a month?
Monthly cost
370.03MIRR
12.33M IRR a day, 6,167 IRR each request
The same work on peer models
30 days at today’s rate.
Rial price over 90 days
It moves with the exchange rate; the steps are the maker’s own price changes. Built at today’s margin, so approximate if the margin changed in the window.
Performance, 30 days
Health is measured by IranRouter itself: a day counts as healthy unless requests to this model failed on our side or it could not be served. First token and speed come from IranRouter’s traffic, and from public market statistics for this model on days without enough of it.
Daily health68.14%
Time to first token2.65 s
Output speed86 tokens/s
Place in the market
By usage across the global model market.
Daily rank#26
Share of the day’s tokens0.7%
Among its peers
Cost of one message against intelligence; this model is highlighted.
Cost of one message, IRR (log scale)
Capabilities
- Input
- TextImageVideoFileAudio
- Output
- Text
Parameters it accepts
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_pOther benchmarks
Design contests
- UI componentsElo: 1,315Win rate: 54%
- Game devElo: 1,304Win rate: 51%
- Code (overall)Elo: 1,302Win rate: 51%
- WebsitesElo: 1,299Win rate: 50%
4 moreShow less
- SVGElo: 1,295Win rate: 55%
- 3DElo: 1,293Win rate: 50%
- Data vizElo: 1,276Win rate: 52%
- ASCII artElo: 1,271Win rate: 52%
Standard tests
- GPQA DiamondScore: 96%Tasks: 191
- τ-bench Verified AirlineScore: 71%Tasks: 47
Start in a minute
The official OpenAI and Anthropic SDKs; only the address and the key change.
# pip install openai from openai import OpenAI client = OpenAI( base_url="https://iranrouter.com/v1", api_key="ir-...", ) r = client.chat.completions.create( model="google/gemini-3.8-flash", messages=[{"role": "user", "content": "Hello, introduce yourself"}], ) print(r.choices[0].message.content)
Peer models
Its family and models with a close score; the last column compares one message’s cost with this model.
| Model | Against this model | ||||
|---|---|---|---|---|---|
| Z.ai: GLM 5.3Z.ai | 2,302 | 31.7 | 82 | 1M | 75% cheaper |
| Qwen: Qwen3.6 Max PreviewQwen | 14,075 | 28.4 | — | 262K | 52% dearer |
| Z.ai: GLM 5.3 FlashZ.ai | 292 | 27.8 | 77 | 1M | 97% cheaper |
| SpaceXAI: Grok 4.7xAI | 19,187 | 35 | 71 | 500K | 107% dearer |
| Anthropic: Claude Haiku 5.5Anthropic | 1,233 | 36.2 | 153 | 1M | 87% cheaper |
1–5 of 6
Technical specs
- ID
google/gemini-3.8-flash- Maker
- Tokenizer
- Gemini
- Released
- Sep 2, 2026
- Added to IranRouter
- Sep 4, 2026
- Context
- 1,048,576 tokens
- Max output
- 65,536 tokens
Scores by Artificial Analysis, Design Arena, as of Oct 31, 2026