AI model comparison
Gemini 3 Flash Preview vs GPT-5.1-Codex
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Gemini 3 Flash Preview
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.
- Input / 1M
- $0.50
- Output / 1M
- $3
- Context
- 1.05M
OpenAI
GPT-5.1-Codex
GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.
- Input / 1M
- $1.25
- Output / 1M
- $10
- Context
- 400K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Gemini 3 Flash Preview
3x cheaper for a typical chat
Higher intelligence score
Gemini 3 Flash Preview
26.3 vs 23.7 on Artificial Analysis
Larger context window
Gemini 3 Flash Preview
1.05M vs 400K tokens
Newer release
Gemini 3 Flash Preview
Released December 17, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Gemini 3 Flash Preview26.3GPT-5.1-Codex23.7Coding index
Gemini 3 Flash PreviewNot availableGPT-5.1-CodexNot availableAgentic index
Gemini 3 Flash PreviewNot availableGPT-5.1-CodexNot availablePricing
Gemini 3 Flash Preview vs GPT-5.1-Codex API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Gemini 3 Flash Preview | GPT-5.1-Codex |
|---|---|---|
| Input tokensPer 1M tokens | $0.50 | $1.25 |
| Output tokensPer 1M tokens | $3 | $10 |
| Cached input (read)Per 1M tokens | $0.05 | $0.13 |
| Cache writePer 1M tokens | $0.08 | Not available |
| Web searchPer request | $0.014 | $0.01 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Gemini 3 Flash Preview$2.50GPT-5.1-Codex$7.50Coding task
30K in, 4K out
Gemini 3 Flash Preview$27$13.50 cachedGPT-5.1-Codex$77.50$43.90 cachedLong document summary
150K in, 2K out
Gemini 3 Flash Preview$81$13.50 cachedGPT-5.1-Codex$207.50$39.50 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Gemini 3 Flash Preview | GPT-5.1-Codex |
|---|---|---|
| Context window | 1.05M tokens | 400K tokens |
| Max output | 66K tokens | 128K tokens |
| Input types | Audio, File, Image, Text, Video | Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | High, Medium, Low, Minimal | High, Medium, Low |
| Default reasoning effort | Medium | Medium |
| Release date | December 17, 2025 | November 13, 2025 |
Features
Supported features
API features available for each model.
| Metric | Gemini 3 Flash Preview | GPT-5.1-Codex |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Not supported |
| Stop sequences | Supported | Not supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Gemini 3 Flash PreviewView full model details- Gemini 3 Flash Preview vs Hy4 preview
- Gemini 3 Flash Preview vs DeepSeek V4 Flash 0423
- Gemini 3 Flash Preview vs Step 5 Preview
- Gemini 3 Flash Preview vs MiniMax M3
- Gemini 3 Flash Preview vs Gemini 3.5 Flash Lite
- Gemini 3 Flash Preview vs Gemini 3.1 Pro Preview
- Gemini 3 Flash Preview vs MiMo-V2.5-Pro
- Gemini 3 Flash Preview vs Gemini 3.6 Flash
- Gemini 3 Flash Preview vs Kimi K2.6
- Gemini 3 Flash Preview vs GPT-5.4 Mini
- Gemini 3 Flash Preview vs Qwen3.7 Max
- Gemini 3 Flash Preview vs GLM 5
- Gemini 3 Flash Preview vs Grok Build 0.1
- Gemini 3 Flash Preview vs Qwen3.6 Plus
- Gemini 3 Flash Preview vs Qwen3.7 Plus
- Gemini 3 Flash Preview vs GLM 5 Turbo
- Gemini 3 Flash Preview vs GLM 5.1
- Gemini 3 Flash Preview vs Kimi K2.7 Code
- Gemini 3 Flash Preview vs Grok 4.20
- Gemini 3 Flash Preview vs Inkling Small
- Gemini 3 Flash Preview vs Inkling
- Gemini 3 Flash Preview vs Grok 4.3
- Gemini 3 Flash Preview vs GPT-5.1
- Gemini 3 Flash Preview vs Kimi K2.5
- Gemini 3 Flash Preview vs GLM 5V Turbo
- Gemini 3 Flash Preview vs GPT-5
- Gemini 3 Flash Preview vs Nemotron 3 Ultra
- Gemini 3 Flash Preview vs Qwen3.5 397B A17B
- Gemini 3 Flash Preview vs Qwen3.5-27B
- Gemini 3 Flash Preview vs Qwen3.6 27B
GPT-5.1-CodexView full model details- GPT-5.1-Codex vs GPT-5.2
- GPT-5.1-Codex vs GPT-5.2-Codex
- GPT-5.1-Codex vs GPT-5.1
- GPT-5.1-Codex vs DeepSeek V4 Flash 0423
- GPT-5.1-Codex vs GPT-5.4 Mini
- GPT-5.1-Codex vs GPT-5
- GPT-5.1-Codex vs Claude Opus 4.1
- GPT-5.1-Codex vs o3 Pro
- GPT-5.1-Codex vs Claude Sonnet 4.5
- GPT-5.1-Codex vs GPT-5 Mini
- GPT-5.1-Codex vs o3
- GPT-5.1-Codex vs Claude Sonnet 4
Our take
Gemini 3 Flash Preview is 3x cheaper for a typical chat. Gemini 3 Flash Preview scores higher on the Artificial Analysis Intelligence Index (26.3 vs 23.7). Gemini 3 Flash Preview has the larger context window (1.05M vs 400K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Gemini 3 Flash Preview or GPT-5.1-Codex cheaper?
Gemini 3 Flash Preview is cheaper for a typical chat (2K input tokens and 500 output tokens). Gemini 3 Flash Preview costs $0.50 per 1M input tokens and $3 per 1M output tokens, while GPT-5.1-Codex costs $1.25 per 1M input tokens and $10 per 1M output tokens.
Which has a bigger context window, Gemini 3 Flash Preview or GPT-5.1-Codex?
Gemini 3 Flash Preview supports up to 1.05M tokens of context, compared with 400K for GPT-5.1-Codex.
Is Gemini 3 Flash Preview smarter than GPT-5.1-Codex?
On the Artificial Analysis Intelligence Index, Gemini 3 Flash Preview scores 26.3 and GPT-5.1-Codex scores 23.7, putting Gemini 3 Flash Preview ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Gemini 3 Flash Preview and GPT-5.1-Codex at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Gemini 3 Flash Preview and GPT-5.1-Codex answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Gemini 3 Flash Preview and GPT-5.1-Codex at the same time. Compare the answers side by side and keep the best one.