Claude Haiku 4.5 vs Llama 4 Maverick
Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.
Cost at a Glance
Claude Haiku 4.5 is 1.9× more expensive than Llama 4 Maverick (46.7% savings if you switch).
At 5M input + 2M output tokens per month:
Choosing Llama 4 Maverick could save you $7.00/mo
Price Comparison (per 1M tokens)
| Metric | Claude Haiku 4.5 | Llama 4 Maverick |
|---|---|---|
| Input (per 1M tokens) | $1.00 | $0.80 |
| Output (per 1M tokens) | $5.00 | $2.00 |
| Cache Write (per 1M tokens) | $1.25 | — |
| Cache Read (per 1M tokens) | $0.10 | — |
| Batch Input (per 1M tokens) | $0.50 | — |
| Batch Output (per 1M tokens) | $2.50 | — |
Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →
Specifications
| Spec | Claude Haiku 4.5 | Llama 4 Maverick |
|---|---|---|
| Context Window | 1M | 1M |
| Max Output Tokens | 64K | 64K |
| Knowledge Cutoff | 2026-03 | 2026-03 |
| Modalities | Text, Image | Text, Image |
| Prompt Caching | Yes | No |
| Batch API | Yes | No |
| Thinking / Reasoning | No | No |
Benchmark Scores
| Benchmark | Claude Haiku 4.5 | Llama 4 Maverick |
|---|---|---|
| SWE-bench Verified | 55.3 | 72.0 |
| MMLU-Pro | 76.8 | 81.0 |
| HumanEval | 88.2 | 89.0 |
Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.
Use Cases
Claude Haiku 4.5
Llama 4 Maverick
About the Providers
Claude Haiku 4.5 is developed by Anthropic. Llama 4 Maverick is developed by Meta. This is a cross-provider comparison between Anthropic and Meta models. For the most up-to-date pricing, always check the official API documentation from each provider.