MODEL PROOF
Gemini 3.8 Flash
FRONTIER
Nothing is both better and cheaper under this workload.
Reasoning tokens are billed separately.
- Independent LMArena score
- 1,494.7 ± 8.53 · 5,076 votes
- Context window
- 1.05M
- Maximum output
- 65.54K
- Input modalities
- text, image, video, file, audio
- Output modalities
- text
- Published input price
- $0.750 / 1M tokens
- Published output price
- $3.75 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Every price dimension · USD per million tokens
| Input | $0.750/M |
|---|---|
| Output | $3.75/M |
| Cached input | $0.075/M |
| Cache write | $0.042/M |
| Cache write 1h | Unknown/M |
| Reasoning | $3.75/M |
| Web search | $0.014/call |
Reasoning tokens are billed separately at $3.75/M, on top of output. Its share of your bill depends on the reasoning tokens used.
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
6 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| Google AI Studiogoogle-ai-studio/flex Endpoint terms
| $0.375 | $1.88 | undeclared | 99.99% |
| Googlegoogle-vertex/global/flex Endpoint terms
| $0.375 | $1.88 | undeclared | 97.76% |
| Google AI Studiogoogle-ai-studio Endpoint terms
| $0.750 | $3.75 | undeclared | 99.93% |
| Googlegoogle-vertex/global Endpoint terms
| $0.750 | $3.75 | undeclared | 94.79% |
| Google AI Studiogoogle-ai-studio/priority Endpoint terms
| $1.35 | $6.75 | undeclared | 99.94% |
| Googlegoogle-vertex/global/priority Endpoint terms
| $1.35 | $6.75 | undeclared | 99.72% |
Independent scores
| LMArena Elo | 1494.7high |
|---|
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Best rankings by task
- mobileapps #6of 40 1257
- uicomponent #8of 104 1335
- website #9of 114 1309
- gamedev #9of 107 1333
- codecategories #10of 108 1316
- webapps #11of 40 1245
- fullstack #12of 41 1249
- 3d #13of 100 1324
Capability
| Context window | 1M |
|---|---|
| Max output | 66K |
| Input modes | text, image, video, file, audio |
| Tool use | yes |
| Reasoning | always on |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-09-23 |
| Quality data | verified |
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.
Questions this page answers
What does Gemini 3.8 Flash cost?
$0.750/M in, $3.75/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Gemini 3.8 Flash have an independent quality score?
Gemini 3.8 Flash has an LMArena score in this catalogue.
What beats Gemini 3.8 Flash?
Nothing is both better and cheaper than Gemini 3.8 Flash.
Does this page use Artificial Analysis scores for Gemini 3.8 Flash?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
MODEL MONUMENT
Save or share this proof
Badge
The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not.
[](https://undominated.ai/models/google__gemini-3.8-flash/)<a href="https://undominated.ai/models/google__gemini-3.8-flash/"><img src="https://undominated.ai/badge/google__gemini-3.8-flash.svg" alt="Gemini 3.8 Flash — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/google__gemini-3.8-flash.svg — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never
older than the last deploy.
