Get started

Gemini 3.1 Flash Lite Preview

Sold by 3 sellers, timed at 172 tok/s, scored 6.2 on the Intelligence Index, and on 8 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Google/Gemini 3.1 Flash Lite PreviewUSD per 1M tokens · as OpenRouter routes it
google/gemini-3.1-flash-lite-previewGoogle · base listing · Gemini tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.25per 1M tokens
Output$1.50per 1M tokens
Cached input$0.025per 1M tokens
Context1.05M1,048,576 tokens
The other meters · every further rate the list publishes for this id, in the unit it states4 meters
Cache write$0.0833333333333333per 1M tokens
Reasoning tokens$1.50per 1M tokens
Audio input$0.50per 1M tokens
Web search$0.014per search
What the list says · the fields OpenRouter publishes for this id9 fields
AuthorGoogle
Listed
Canonical idgoogle/gemini-3.1-flash-lite-preview-20260303
Context1,048,576 tokens
Max output65,536 tokens
Modalitiestext, image, video, file, audio → text
TokenizerGemini
Reasoningoptional, on by default · effort high, medium, low, minimal, none, minimal by default
Moderationnot moderated by OpenRouter

What sellers charge

3 sellers · 3.6x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.125 at Google AI Studio to $0.45 at Google AI Studio. 1 seller undercuts the $0.25 listed; 1 is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

31,653 requests · 3 endpoints · 30-minute window
Throughput172 tok/sMedian output rate, weighted across the 3 endpoints serving it by the requests each answered.the speed board
First token597msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread135 to 179The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter'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

3 priced · 3 timed · cheapest first
  1. Google AI Studiogoogle-ai-studio/flex$0.125$0.75$0.0125not declared66knot matchednonenonenot matched100%
  2. Google AI Studiogoogle-ai-studio · listed$0.25$1.50$0.025not declared66knot matchednonenonenot matched100%
  3. Google AI Studiogoogle-ai-studio/priority$0.45$2.70$0.045not declared66knot matchednonenonenot matched99.83%
  4. Google AI Studionot matchednot matchednot matchednot matchedno offer135 tok/s91561ms4,587 reqno offer
  5. Google AI Studionot matchednot matchednot matchednot matchedno offer135 tok/s91.9466ms360 reqno offer
  6. Google AI Studionot matchednot matchednot matchednot matchedno offer179 tok/s91606ms26,706 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 3 timed routes are slower than it, and the middle route runs at 135 tok/s. The widest median-to-p90 gap is Google AI Studio's, 1.97x.

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 . Every one of the 3 sellers with a reading was at 99% or better on each of the 23 days held, 23 Oct 2026 to 21 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

11 parameters · 3 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. reasoning_effortevery seller
  5. response_formatevery seller
  6. seedevery seller
  7. structured_outputsevery seller
  8. temperatureevery seller
  9. tool_choiceevery seller
  10. toolsevery seller
  11. top_pevery seller

All 11 are accepted by every one of the 3 sellers that publish a list. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $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 board

Each 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.

Intelligence Index6.2Position 51 of 58, above 12% of the models scored.the intelligence leaderboard
Coding Index34.7Position 81 of 118, above 31% of the models scored.the coding leaderboard
Agentic Index1.6Position 74 of 94, above 21% of the models scored.the agentic leaderboard
  1. 3D scenes · Models1028 Elowin rate 38.7% · source rank 117the board, 113 ranked
  2. ASCII art · Models1150 Elowin rate 50.8% · source rank 39the board, 67 ranked
  3. Code · Models1060 Elowin rate 36.5% · source rank 119the board, 120 ranked
  4. Data visualisation · Models1041 Elowin rate 33.3% · source rank 113the board, 110 ranked
  5. Game development · Models1018 Elowin rate 33.7% · source rank 125the board, 120 ranked
  6. SVG · Models1041 Elowin rate 42.5% · source rank 83the board, 83 ranked
  7. UI components · Models1060 Elowin rate 37.7% · source rank 112the board, 116 ranked
  8. Websites · Models1073 Elowin rate 36.6% · source rank 120the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals

Epoch AI has not placed Gemini 3.1 Flash Lite Preview 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

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Gemini 3.1 Flash Lite Preview under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

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.