Claude Haiku 4.5 vs Llama 4 Scout
Llama 4 Scout is cheaper than Claude Haiku 4.5 by about 94% on a blended (75% input / 25% output) basis. Claude Haiku 4.5 charges $1.00 / $5.00 per 1M input/output tokens; Llama 4 Scout charges $0.0800 / $0.24.
| Field | Claude Haiku 4.5 | Llama 4 Scout |
|---|---|---|
| Input $/Mtok | $1.00 | $0.0800 |
| Output $/Mtok | $5.00 | $0.24 |
| Cache read $/Mtok | $0.10 | – |
| Cache write $/Mtok | $1.25 | – |
| Input $/Mchar | n/a | 0.0241 |
| Output $/Mchar | n/a | 0.0722 |
| Context window | 200000 | 10000000 |
| Tokenizer | claude | llama3 |
| Confidence? | official | api |
| Source | official-anthropic | openrouter |
Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence
Price history
No price changes recorded yet for either model.
Same workload, monthly cost
Illustrative monthly cost at 10M tokens/month, split per workload preset. Not a substitute for the calculator, which uses your own volume, cache and batch assumptions.
| Workload | Claude Haiku 4.5 | Llama 4 Scout |
|---|---|---|
| Coding agent | $12.00 | $0.88 |
| RAG chat | $16.00 | $1.04 |
| Summarisation (batch) | $14.00 | $0.96 |
| Classification | $10.80 | $0.83 |
| Chat assistant | $26.00 | $1.44 |
| Content generation | $42.00 | $2.08 |
Batch pricing not published for Claude Haiku 4.5; standard rate used for the batch share of a workload.
Batch pricing not published for Llama 4 Scout; standard rate used for the batch share of a workload.
Cite this page
Claude Haiku 4.5 vs Llama 4 Scout: $1.00/$5.00 vs $0.0800/$0.24 per 1M tokens as of 2026-11-19. Token Barometer by Dejan Strbad, https://tokenbarometer.com, data CC BY 4.0. https://tokenbarometer.com/compare/anthropic_claude-haiku-4-5-vs-meta_llama-4-scout
Claude Haiku 4.5 page | Llama 4 Scout page | Open Claude Haiku 4.5 in calculator | Open Llama 4 Scout in calculator