Intelligence Index
0150.2
> 96% OF MODELS
Google
Gemini 3.5 Flash
Updated: July 2026
Gemini 3.5 Flash delivers near-Pro coding and reasoning at flash-tier latency and cost. It supports text and image inputs with a 1M context window for fast, parallel agentic workflows.
Specifications
- Context
- 1M
- Input
- $1.5/M
- Output
- $9/M
Capabilities
VISIONWEBTHINKINGCODING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Mistral Medium 3.5 | MistralAI | 262K | $1.5/M | $7.5/M |
| GPT-3.5 Turbo Instruct | OpenAI | 4K | $1.5/M | $2/M |
| GLM 5.2 | Z-AI | 1M | $1.4/M | $4.4/M |
| Qwen3 Max | Qwen | 33K | $1.6/M | $6.4/M |
| Qwen3 Max | Qwen | 33K | $1.6/M | $6.4/M |
Performance Metrics
Coding Index
0270.1
> 94% OF MODELS
Agentic Index
0337.4
> 91% OF MODELS
Average Response Performance
- Output Speed
- 177.6 tok/s
- Time To First Token
- 23.02s
- Time To First Answer Token
- 23.02s
- End To End Response Time
- 25.84s
DATA SOURCE: Artificial Analysis