Claude Haiku 5.5 vs Llama 4 Maverick
Claude Haiku 5.5 (Anthropic) and Llama 4 Maverick (Meta) are listed at different prices. Claude Haiku 5.5 costs less: $0.10 per 1M input tokens and $0.50 per 1M output tokens, against $0.35 and $1.00 for Llama 4 Maverick. Claude Haiku 5.5 has the larger context window, 1,000,000 tokens against 524,288 for Llama 4 Maverick. Claude Haiku 5.5 charges $0.50 and $2.50 per 1M once a prompt passes 100,000 tokens; Llama 4 Maverick keeps one price across its window. Claude Haiku 5.5 accepts text, images and files and produces text; Llama 4 Maverick accepts text and images and produces text.
Anthropic: Claude Haiku 5.5 accepts text, images, and files, while Meta: Llama 4 Maverick accepts text and images; both produce text and support tools, structured outputs, and response formats. Claude Haiku 5.5 has a 1,000,000-token context and 128,000-token output limit, compared with Maverick’s 524,288-token context and 32,768-token output limit.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Claude Haiku 5.5 | Llama 4 Maverick |
|---|---|---|
| Maker | Anthropic | Meta |
| Added to catalog | 7 Oct 2026 | 5 Apr 2025 |
| Input, per 1M tokens | $0.10 | $0.35 |
| Output, per 1M tokens | $0.50 | $1.00 |
| Input above 100K tokensPer 1M; long prompts | $0.50 | $0.35 |
| Output above 100K tokens | $2.50 | $1.00 |
| Cached input read, per 1M | $0.01 | $0.17 |
| Context windowTokens | 1,000,000 | 524,288 |
| Max outputTokens | 128,000 | 32,768 |
| Accepts | file, image, text | image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | Yes | No |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Claude Haiku 5.5 | Llama 4 Maverick |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0002 | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0029 | $0.0096 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0040 | $0.013 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.079 | $0.054 |
Which to choose
Choose Claude Haiku 5.5 if
- Input tokens cost less: $0.10 against $0.35 per 1M
- Output tokens cost less: $0.50 against $1.00 per 1M
- Cached input costs less: $0.01 against $0.17 per 1M
- You need the larger context window: 1,000,000 tokens against 524,288
- You need longer answers in one response: 128,000 tokens against 32,768
- It has to read files, which the other model does not
- You want to set how much it reasons before it answers
Choose Llama 4 Maverick if
- Your prompts often run past 100K tokens: $0.35 against $0.50 per 1M input tokens there
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.