Gemini 3.5 Flash (high)
AI model by Google. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Gemini 3.5 Flash (high) is positioned in the mid-tier at $9.00/M output tokens. The benchmark profile is balanced — strongest on Coding Index (70.1) — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.
Latency. On latency, Gemini 3.5 Flash (high) reports 171 tok/s output speed and 27290ms 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 3.5 Flash (high) costs $2.40 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 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Gemini 3.5 Flash (high)Current | $1.50 | $9.00 | 171 tok/s |
| Qwen3 235B A22B (Reasoning) | $0.70 | $8.40 | 61 tok/s |
| GPT-5.1 Codex (high) | $1.25 | $10.00 | — |
| Nova 2.0 Pro Preview (medium) | $1.25 | $10.00 | 115 tok/s |
| o3 | $2.00 | $8.00 | 112 tok/s |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | $2.00 | $10.00 | 76 tok/s |