Gemini 3.8 Flash
The best cheap model for long-running agent loops: rank 8 on Arena, 128 tok/s, and the only sub-$1 model on Scale's SWE-Bench Pro V2 board. Hallucinates more than Claude-class models and the price doubles in January.
Key facts
- Score
- 77 / 100, rank #12Evals79Price52People72Fit100
- Price
- $0.75 in · $3.75 out per 1M tokens (Gemini API Pricing)
- Blended price
- $1.50 per 1M tokens (3 input : 1 output)
- Context window
- 1M
- Open weights
- No
- Released
- Sep 2, 2026
- Best for
- Agentic coding on a budget, Frontend generation, High-volume multimodal pipelines
Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens on Google's list price (Gemini API Pricing, read Oct 11, 2026).
Independent evals
| Benchmark | Result | Who ran it | Read |
|---|---|---|---|
| Artificial Analysis Intelligence Index | 41 | Gemini 3.8 Flash (High) - Artificial Analysis | Oct 10, 2026 |
| Arena Text score | 1497 (rank 8) | Text Arena Leaderboard | Oct 10, 2026 |
| Scale SWE-Bench Pro V2 (mini-swe-agent) | 58.80% | SWE-Bench Pro V2 Leaderboard - Scale Labs | Oct 10, 2026 |
- Artificial Analysis output speed (tokens/s): 127.9 (Gemini 3.8 Flash (High) - Artificial Analysis)
What practitioners say
Huge HN thread (1,160 points, 669 comments). simonw built an HTML visualisation in '13 seconds' for '1.8 cents'; colechristensen calls it 'competitive with opus/fable and also FAST'; several use it as the workhorse model with a stronger planner. The pushback is about reliability: one user says it 'gives me the most hallucinations' of the major models, others complain it ignores context between consecutive messages, and the uneven knowledge cutoff (some domains stuck at early 2025) bites in research tasks.
Caveats
- $0.75/$3.75 is introductory; Google's pricing page says it goes to $1.50/$7.50 on 2027-01-01.
- HN users report more hallucination and dropped context between turns than rival models; verify outputs.
- Third Flash release in six weeks (3.6, 3.7, 3.8). Expect short model lifecycles and deprecation churn.
Questions people ask
How much does Gemini 3.8 Flash cost?
Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens on Google's list price (Gemini API Pricing, read Oct 11, 2026).
How good is Gemini 3.8 Flash?
Gemini 3.8 Flash ranks #12 of 26 on the Models at Work leaderboard with a score of 77 out of 100 (October 2026 edition). The best cheap model for long-running agent loops: rank 8 on Arena, 128 tok/s, and the only sub-$1 model on Scale's SWE-Bench Pro V2 board. Hallucinates more than Claude-class models and the price doubles in January.
What is Gemini 3.8 Flash best for?
Gemini 3.8 Flash is best for agentic coding on a budget, frontend generation, high-volume multimodal pipelines.
What are Gemini 3.8 Flash's benchmark scores?
Artificial Analysis Intelligence Index: 41 (Gemini 3.8 Flash (High) - Artificial Analysis); Arena Text score: 1497 (rank 8) (Text Arena Leaderboard); Scale SWE-Bench Pro V2 (mini-swe-agent): 58.80% (SWE-Bench Pro V2 Leaderboard - Scale Labs).
What is Gemini 3.8 Flash's context window?
Gemini 3.8 Flash has a 1M token context window according to Google.
Is Gemini 3.8 Flash open weights?
No. Gemini 3.8 Flash is a proprietary model available through Google's API and partner clouds.
Compare Gemini 3.8 Flash
Methodology: Score is 0 to 100 and computed, not typed: 55% independent evals (Artificial Analysis, Arena, Scale SEAL, Epoch, each scaled against its natural floor and the best score in this table, then averaged), 15% blended price on a fixed log scale ($0.05 per million is 100, $60 is 0), 15% practitioner sentiment from Signals and community threads, 15% operational fit (context window, open weights). A missing component drops out and the rest are reweighted. A model with no independent eval yet is provisional and ranks below every measured one. Within three points is a tie. Vendor-published figures are labelled and never counted.