LLM Comparison
Claude Haiku 5.5 vs Llama Guard 3 8B
Side-by-side specs, pricing & capabilities
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | ||
| Family | Claude | Llama |
| Status | Current | Current |
| Release Date | Oct 2026 | Feb 2025 |
| Context Window | 1.0M tokens | 131K tokens |
| Input Price | $0.10/M tokens | $0.48/M tokens |
| Output Price | $0.50/M tokens | $0.03/M tokens |
| Pricing Notes | Anthropic Claude API global standard tier, USD per million tokens. Prompts up to 100,000 tokens: $0.10 input, $0.50 output, $0.125 five-minute cache write, $0.20 one-hour cache write, and $0.01 cache read. Prompts above 100,000 tokens: $0.50 input, $2.50 output, $0.625 five-minute cache write, $1 one-hour cache write, and $0.05 cache read. Batch API requests receive a 50% discount. US-only data residency applies a 1.1x token-price multiplier. The Batch API beta supports up to 300,000 output tokens; 128,000 is the standard API cap recorded here. | — |
| Capabilities | reasoningvisiontool-uselong-contextcontext-caching | textcode |
| Max Output | 128K tokens | 100 tokens |
| API Identifier | claude-haiku-5-5 | meta-llama/llama-guard-3-8b |
| Benchmarks | ||
| Artificial Analysis Intelligence Index v4.3.2 | 43.4 indexartificial-analysis | — |
| LG3 code-interpreter safety F1 | — | 88.5%meta |
| LG3 English safety AUPRC | — | 98.5%meta |
| LG3 English safety F1 | — | 93.9%meta |
| LG3 tool-use safety F1 | — | 85.6%meta |
| View Claude Haiku 5.5 | View Llama Guard 3 8B | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| Claude Haiku 5.5Cheapest | $0.10 | $0.25 | $0.35 | — |
| Llama Guard 3 8B | $0.48 | $0.02 | $0.50 | +41% |
Anthropic
Claude Haiku 5.5
Claude Haiku 5.5 is Anthropic's fast proprietary model for high-volume classification, extraction, routing, and subagent workloads. It accepts text and images, returns text, uses adaptive thinking, and supports a 1,000,000-token context window with up to 128,000 output tokens on standard API calls.
Meta
Llama Guard 3 8B
Llama Guard 3 8B is a Meta safety-classification model for prompt and response moderation across English, multilingual, search, and code-interpreter use cases.
More Comparisons
Looking for more AI models?
Browse All LLMs