GoogleFastReleased 2 September 2026
Gemini 3.8 Flash pricing, context and benchmark
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.
1.05M
Input context
66K
Output context
$0.75
Official input
$3.75
Official output
31
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Gemini 3.8 Flash |
| Model ID | google/gemini-3.8-flash |
| Provider | |
| Release date | 2 September 2026 |
| Status | Generally available |
| Input context | 1,048,576 tokens |
| Output context | 65,536 tokens |
| Official input pricing | $0.75 per 1M tokens |
| Official output pricing | $3.75 per 1M tokens |
| Cache read pricing | $0.075 per 1M tokens (90% off input) |
| Market input pricing | $0.375 per 1M (cheapest route) |
| Market output pricing | $1.875 per 1M (cheapest route) |
| Highest route pricing | $1.35 in, $6.75 out per 1M |
| Input modalities | text · image · video · file · audio |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Gemini |
| Provider routes | 7 endpoints |
| Artificial Analysis index | 31 (#51 of 74) |
| Speed | 112 tokens/s, 16.59s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.75 in |
| Image | ✓ yes | no | $0.75 in |
| Audio | ✓ yes | no | $0.75 in |
| Video | ✓ yes | no | $0.75 in |
| File (PDF) | ✓ yes | no | $0.75 in |
02 · Overview
What is Gemini 3.8 Flash?
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.
Gemini 3.8 Flash carries a 1.05M token window, uses the Gemini tokenizer and is served by Google. On Hoodgen it sits in the Fast tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released2 September 2026
| Property | Gemini 3.7 Flash | Gemini 3.8 Flash | Change |
|---|---|---|---|
| Released | 2026 | Sep 2026 | Newer release |
| Context | 1.05M | 1.05M | Unchanged |
| Max output | 66K | 66K | Unchanged |
| Input price | $0.75 | $0.75 | Unchanged |
| Output price | $3.75 | $3.75 | Unchanged |
| Input modalities | text, image, video, file, audio | text, image, video, file, audio | Unchanged |
| AA index | n/a | 31 | Newer benchmark run |
04 · Capabilities
Features and capabilities
◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
▤
Files and PDFs
Documents go in as files rather than pasted text, keeping layout and tables intact.
♪
Audio and video
Calls, meetings and screen recordings can be summarised in one pass.
⚡
Prompt caching
Cached input costs $0.075 per million instead of $0.75, so stable prefixes get cheaper.
06 · Benchmarks
Benchmark results and performance
Artificial Analysis Intelligence Index v5.0.1 blends nine evaluations. Gemini 3.8 Flash scores 31 , ranking #51 of 74.
Intelligence index
31
#51 of 74
Cost per task
$7.77
weighted average per index task
Time per task
14.7m
inference time
Output speed
112
tokens per second
Index score and cost per task
Scale: index 0 to 70, cost 0 to $20. Sub scores are not published per evaluation, so none are invented here.
07 · Use cases
What can you do with Gemini 3.8 Flash?
High volume drafts
Captions, titles, product blurbs and rewrite passes where cost per call dominates.
Inline assistants
Autocomplete, quick replies and menu helpers that must answer inside a second.
Batch classification
Tagging, routing and extraction across thousands of short inputs.
Cheap agent loops
Tool calling loops that do not need frontier grade reasoning.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.075 per million instead of $0.75, a 90% discount. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
Gemini 3.8 Flash pricing
Official pricing
List price
$0.75 / 1M in
$3.75 / 1M out
- $0.075 cached input
- 1.05M context
- text, image, video, file, audio input
Cheapest route
$0.375 / 1M in
$1.875 / 1M out
- 7 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Highest route
$1.35 / 1M in
$6.75 / 1M out
- Priority or premium tier
- Best under load
- Use for latency critical calls
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Google AI Studio | flex | $0.375 | $1.875 | $0.037 | 100.0% |
| flex | $0.375 | $1.875 | $0.037 | 80.4% | |
| Google AI Studio | standard | $0.75 | $3.75 | $0.075 | 100.0% |
| standard | $0.75 | $3.75 | $0.075 | 100.0% | |
| standard | $0.825 | $4.125 | $0.083 | 99.3% | |
| Google AI Studio | priority | $1.35 | $6.75 | $0.135 | 100.0% |
| priority | $1.35 | $6.75 | $0.135 | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0063 | $3.13 | 2975 |
| List price | $0.0125 | $6.26 | 5950 |
| Highest route | $0.0371 | $18.56 | 17635 |
10 · Developers
API and developer information
| Model ID | google/gemini-3.8-flash |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text+image+file+audio+video->text |
| Max prompt tokens | 1,048,576 |
| Max completion tokens | 65,536 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3.8-flash",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 65,536 tokens per request. Long deliverables have to be chunked. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
| Depth ceiling | Fast tier: strong on throughput, weaker than flagship tiers on long multi step reasoning. |
12 · Comparison
Gemini 3.8 Flash vs other Google models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Gemini 3.8 Flash | 1.05M | $0.75 | $3.75 | 31 | Sep 2026 |
| Gemini 3.1 Pro Preview | 1.05M | $2 | $12 | n/a | 2026 |
| Gemini 4 Argon | 1.05M | $2 | $10 | 50 | Oct 2026 |
| Gemini 4 Carbon | 1.05M | $2 | $10 | n/a | 2026 |
| Gemini 3.1 Pro Preview Custom Tools | 1.05M | $2 | $12 | n/a | 2026 |
| Nano Banana Pro (Gemini 3 Pro Image) | 131K | $2 | $12 | n/a | 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Google and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
Gemini 3.8 Flash questions, answered
Gemini 3.8 Flash is a fast model from Google, released 2 September 2026. 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.
✦
Start chatting with Gemini 3.8 Flash
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.