Compare Gemini 3.1 Pro Preview (Google) and GPT-5.2 Codex (OpenAI) by price, context, capabilities, and latency.
Side by side
Compare price, provider, context, capabilities, latency, and source basis.
| Model | Provider | Input | Output | Context | Capabilities | Best for | Latency | Status | Source |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | Starting at $2 / 1M tokens | $12 / 1M tokens | 1M | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 2140-4141ms | Catalog | Platform curated | |
| GPT-5.2 Codexopenai/gpt-5.2-codex | OpenAI | $1.75 / 1M tokens | $14 / 1M tokens | 400k | StreamingTool callingJSON modeVision | image understanding, multimodal chat | 2227-3996ms | Catalog | Platform curated |
FAQ
Gemini 3.1 Pro Preview is cheaper ($2 / 1M tokens input / $12 / 1M tokens output) vs GPT-5.2 Codex ($1.75 / 1M tokens input / $14 / 1M tokens output). Actual cost depends on your input/output token mix — estimate it with the pricing calculator.
Gemini 3.1 Pro Preview is larger (1M tokens) vs 400k tokens.
Both target Vision. Pick Gemini 3.1 Pro Preview to optimize cost, or Gemini 3.1 Pro Preview for the longer context window. Test both on real prompts before committing production traffic.