Gemini 3 Flash Preview (batch)
Sold by 6 sellers, timed at 85.7 tok/s, on 12 Design Arena boards, with results on 1 openly licensed board, and not scored by Artificial Analysis.
retrieved sha256 · 0bb53a77713f
What sellers charge
6 sellers · 3.6x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.25 at Google to $0.90 at Google AI Studio. The $0.25 listed is the cheapest on offer; 4 sellers are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
187,177 requests · 6 endpoints · 30-minute windowOpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.
Every endpoint
6 priced · 6 timed · cheapest first- Googlegoogle-vertex/global/flex · listed$0.25$1.50$0.025not declared66knot matchednonenonenot matched89.36%
- Google AI Studiogoogle-ai-studio/flex · listed$0.25$1.50$0.025not declared66knot matchednonenonenot matched98.88%
- Googlegoogle-vertex/global$0.50$3.00$0.05not declared66knot matchednonenonenot matched100%
- Google AI Studiogoogle-ai-studio$0.50$3.00$0.05not declared66knot matchednonenonenot matched99.86%
- Googlegoogle-vertex/global/priority$0.90$5.40$0.09not declared66knot matchednonenonenot matched100%
- Google AI Studiogoogle-ai-studio/priority$0.90$5.40$0.09not declared66knot matchednonenonenot matched100%
- Googlenot matchednot matchednot matchednot matchedno offer13 tok/s514s887 reqno offer
- Googlenot matchednot matchednot matchednot matchedno offer143 tok/s1131.6s2,929 reqno offer
- Googlenot matchednot matchednot matchednot matchedno offer81 tok/s431.24s135,084 reqno offer
- Google AI Studionot matchednot matchednot matchednot matchedno offer96 tok/s551.35s31,329 reqno offer
- Google AI Studionot matchednot matchednot matchednot matchedno offer135 tok/s711.07s117 reqno offer
- Google AI Studionot matchednot matchednot matchednot matchedno offer98 tok/s641.68s16,831 reqno offer
Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 2 of the 6 timed routes are slower than it, and the middle route runs at 97 tok/s. The widest median-to-p90 gap is Google's, 2.6x.
Google publishes 3 offers and had 3 routes timed; Google AI Studio publishes 3 offers and had 3 routes timed. The two documents share no route id, so those offers and routes are printed apart rather than paired.
Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 2 of the 6 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Google (google-vertex/global/flex) at 0.83% on 3 Nov 2026 and Google AI Studio (google-ai-studio/flex) at 96.59% on 17 Nov 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.
Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .
What each seller accepts
12 parameters · 6 sellers- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- reasoning_effortevery seller
- response_formatevery seller
- seedevery seller
- structured_outputsevery seller
- temperatureevery seller
- tool_choiceevery seller
- toolsevery seller
- top_pevery seller
- stop3 of 6not Google AI Studio (google-ai-studio), Google AI Studio (google-ai-studio/flex), and Google AI Studio (google-ai-studio/priority)
11 of these 12 are accepted by every one of the 6 sellers that publish a list; the other 1 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.
Price position
342 priced modelsBlended $0.563 per million tokens, 3 in to 1 out: cheaper than 200 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.
Measured quality
145 models with an index · 132 on a design arena boardEach mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.
- Agentic slides · Agents1073 Elowin rate 39.3% · source rank 8the board, 9 ranked
- Agentic slides, python-pptx · Agents1075 Elowin rate 39.3% · source rank 8the board, 9 ranked
- Android native · Agents1034 Elowin rate 47.7% · source rank 41the board, 41 ranked
- Full stack · Agents1037 Elowin rate 47.4% · source rank 36the board, 44 ranked
- Godot game development · Agents1161 Elowin rate 50.6% · source rank 16the board, 34 ranked
- Mobile apps · Agents1081 Elowin rate 46.6% · source rank 46the board, 49 ranked
- python-pptx slides · Agents1036 Elowin rate 38.3% · source rank 29the board, 29 ranked
- Web apps · Agents1091 Elowin rate 48.5% · source rank 40the board, 47 ranked
- 3D scenes · Models1164 Elowin rate 62.7% · source rank 65the board, 113 ranked
- Code · Models1178 Elowin rate 57.6% · source rank 69the board, 120 ranked
- Game development · Models1155 Elowin rate 58.3% · source rank 76the board, 120 ranked
- Websites · Models1187 Elowin rate 57.0% · source rank 70the board, 126 ranked
Epoch AI has not placed Gemini 3 Flash Preview (batch) on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.
Benchmark results
1 of 6 boards · 16 results| Task | All runs | Effort | Score |
|---|---|---|---|
| Chess Puzzles | 167 | high | 0.40 |
| FrontierMath-2025-02-28-Private | 101 | unstated | 0.36 |
| FrontierMath-2025-02-28-Public | 87 | unstated | 0.60 |
| FrontierMath-Tier-4-2025-07-01-Private | 72 | unstated | 0.04 |
| FrontierMath-Tier-4-2025-07-01-Public | 48 | unstated | 0 |
| FrontierMath-Tier-4-v2-Private | 84 | unstated | 0.17 |
| FrontierMath-Tiers-1-3-v2-Private | 128 | unstated | 0.51 |
| GPQA diamond | 342 | high | 0.89 |
| unstated | 0.83 | ||
| Mystery Game Puzzles | 149 | high | 0.20 |
| low | 0.26 | ||
| minimal | 0.25 | ||
| OTIS Mock AIME 2024-2025 | 319 | high | 0.96 |
| unstated | 0.93 | ||
| SimpleQA Verified | 106 | high | 0.67 |
| SWE-Bench verified | 33 | unstated | 0.75 |
Mean accuracy, 0 to 1, on the task the row names, as Epoch AI runs it and averaged over repeated runs. All eighteen of their tasks, including the held-out FrontierMath tiers, named as they name them. The model id carries the effort setting the run used. Epoch AI Benchmarking Hub names these runs gemini-3-flash-preview_high, gemini-3-flash-preview_low, gemini-3-flash-preview_minimal and gemini-3-flash-preview, and the effort beside each score says which run it is, unstated where the publisher wrote none. A run missing from a task's rows has no published result there, which is not a score of zero. All runs is how many runs the publisher scored on the task, every model's. Read from epoch.ai ↗, which dates its own data . Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
1 of the 6 openly licensed boards Vitna mirrors carries a result for Gemini 3 Flash Preview (batch), each printed as its publisher published it and none added to another. MTEB, LiveBench, HELM, Vectara hallucination leaderboard and Aider polyglot have not published one under a name that matches its listing, and names are matched to the catalog exactly and never guessed. A task that is a link opens its column on /capability, with every run scored on it; an effort that is a link opens its run's row there, where the run is ranked on Vitna's scale. Every board, with its licence and what its publisher measures, is on /benchmarks.
Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Vitna ran none of these evaluations and adjusted none of these figures.
