Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions a…
Model details →Anthropic: Claude 3.5 Haiku vs OpenAI: GPT-5.1-Codex
Anthropic: Claude 3.5 Haiku and OpenAI: GPT-5.1-Codex are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supp…
Model details →Side-by-side comparison
| Capability | Anthropic: Claude 3.5 Haiku | OpenAI: GPT-5.1-Codex | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 200K | 400K | 🏆 OpenAI: GPT-5.1-Codex |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.80 | $1.25 | 🏆 Anthropic: Claude 3.5 Haiku |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $4.00 | $10.00 | 🏆 Anthropic: Claude 3.5 Haiku |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | Yes | Yes | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | Yes | 🏆 OpenAI: GPT-5.1-Codex |
Frequently asked questions
Is Anthropic: Claude 3.5 Haiku better than OpenAI: GPT-5.1-Codex?
Anthropic: Claude 3.5 Haiku and OpenAI: GPT-5.1-Codex are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
What's the price difference between Anthropic: Claude 3.5 Haiku and OpenAI: GPT-5.1-Codex?
Input: $0.80 vs $1.25 per 1M tokens. Output: $4.00 vs $10.00 per 1M tokens.
What context windows do Anthropic: Claude 3.5 Haiku and OpenAI: GPT-5.1-Codex support?
Anthropic: Claude 3.5 Haiku supports up to 200K tokens. OpenAI: GPT-5.1-Codex supports up to 400K tokens.
Do both Anthropic: Claude 3.5 Haiku and OpenAI: GPT-5.1-Codex support tool calling?
Anthropic: Claude 3.5 Haiku: yes. OpenAI: GPT-5.1-Codex: yes.