Add to ChromeCompare models
Put models side by side on price, context, capabilities, and benchmarks.
Llama Guard 4 12B is Meta's open-weight safety classifier model used to moderate and filter both prompts and model outputs across text and image content. It is designed to be deployed alongside other Llama models to detect unsafe or policy-violating content rather than for general chat.
Cost rate
0.1x
Context
1M
Input
Output
Reasoning
Tool calling
Structured outputs
Pricing/M tokens
Input$0.18
Cached input$0.00
Output$0.18
Context
Context length1,048,576
Max output tokens16,384
Knowledge cutoff2024-08-31
Performance
Throughput-
Latency-
Claude Haiku 4.5 is Anthropic's fast, affordable small model in the Claude 4 generation, balancing strong instruction-following and coding ability with low latency. It is designed for high-throughput agentic and chat applications where speed and cost efficiency are priorities.
Document analysis#31Software & IT Services#100Mathematical#101Writing, Literature, & Language#109
Cost rate
1x
Context
200K
Input
Output
Reasoning
Tool calling
Structured outputs
Pricing/M tokens
Input$1.00
Cached input$0.10
Output$5.00
Context
Context length200,000
Max output tokens64,000
Knowledge cutoff-
Performance
Throughput90 tok/s
Latency1.04s
Benchmarks
Head-to-head scores across reasoning, coding, and agentic indices, plus per-domain rankings.
Intelligence
62.5
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)62.5Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)62.1Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)60.9
