Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
| Attribute | GPT-5.1 Codex (Mini)gpt-5.1-codex-mini | Gemini 3.7 Flashgemini-3.7-flash | DeepSeek V4.1 Flashdeepseek-v4.1-flash |
|---|---|---|---|
| Pricing | |||
| Input | $0.125 / 1M | $0.375 / 1M | $0.30 / 1M |
| Output | $1.00 / 1M | $1.88 / 1M | $1.20 / 1M |
| Cache Write (5m) | $0.125 / 1M | $0.375 / 1M | $0.30 / 1M |
| Cache Write (1h) | $0.125 / 1M | $0.375 / 1M | $0.30 / 1M |
| Cache Read | $0.125 / 1M | $0.375 / 1M | $0.30 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 400K | 1M | 1M |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | Yes | Yes | Yes |
| Function Calling | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes |
| Streaming | Yes | Yes | Yes |
| Catalogue | |||
| Provider | OpenAI | DeepSeek | |
| Category | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | GPT-5.1 Codex is a coding-focused version of GPT-5.1 designed for both interactive development and long autonomous engineering tasks. It can build projects, add features, debug, refactor, and review code with higher steerability and cleaner outputs than GPT-5.1. It integrates with developer tools (CLI, IDEs, GitHub, cloud), supports adjustable reasoning effort, handles images/screenshots for UI work, and uses tools for search and environment setup — making it purpose-built for agentic coding workflows. | Gemini 3.7 Flash is Google's fast multimodal model designed for agentic workflows, coding, and complex multi-step reasoning. It combines responsive inference with reliable problem-solving capabilities, making it well suited for interactive and production-scale applications. Optimized for speed and dependable multi-step execution, Gemini 3.7 Flash is a strong choice for coding assistants, autonomous agents, and high-throughput workflows that require both low latency and capable reasoning. | DeepSeek V4.1 Flash is a cost-efficient sparse Mixture-of-Experts (MoE) model in DeepSeek's V4.1 family, optimized for coding, reasoning, and agentic workflows. Despite its efficiency-focused positioning, DeepSeek reports that it surpasses the previous V4 Pro in performance, inference speed, and overall task completion time. The model is particularly strong at long-horizon, multi-step execution, making it well suited for coding agents, complex problem solving, and autonomous workflows that must reliably carry tasks through to completion. |