Gemini 3 Flash Preview (Reasoning)
AI model by Google. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Gemini 3 Flash Preview (Reasoning) is a budget-tier option from Google at $3.00/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Gemini 3 Flash Preview (Reasoning) reports 190 tok/s output speed and 6330ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Gemini 3 Flash Preview (Reasoning) costs $0.80 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Gemini 3 Flash Preview (Reasoning)Current | $0.50 | $3.00 | 190 tok/s |
| Apodex 1.1 | $0.30 | $3.00 | — |
| Qwen3.8 27B (Non-reasoning) | $0.50 | $3.00 | 48 tok/s |
| Qwen3.8 27B (medium) | $0.50 | $3.00 | 49 tok/s |
| Qwen3.8 27B (low) | $0.50 | $3.00 | 49 tok/s |
| Hermes 4 - Llama-3.1 405B (Reasoning) | $1.00 | $3.00 | 43 tok/s |