Claude Haiku 5.5 vs Gemini 4 Carbon
Claude Haiku 5.5 (Anthropic) and Gemini 4 Carbon (Google) 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 $2.00 and $10.00 for Gemini 4 Carbon. Gemini 4 Carbon has the larger context window, 1,048,576 tokens against 1,000,000 for Claude Haiku 5.5. Claude Haiku 5.5 charges $0.50 and $2.50 per 1M once a prompt passes 100,000 tokens; Gemini 4 Carbon keeps one price across its window. Claude Haiku 5.5 accepts text, images and files and produces text; Gemini 4 Carbon accepts text, images, files, audio and video and produces text.
Anthropic: Claude Haiku 5.5 accepts text, images, and files, while Google: Gemini 4 Carbon also accepts audio and video. Both produce text and support tools, structured outputs, response formats, and reasoning; Gemini 4 Carbon has a larger context window and maximum output allowance.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Claude Haiku 5.5 | Gemini 4 Carbon |
|---|---|---|
| Maker | Anthropic | |
| Added to catalog | 7 Oct 2026 | 10 Nov 2026 |
| Input, per 1M tokens | $0.10 | $2.00 |
| Output, per 1M tokens | $0.50 | $10.00 |
| Input above 100K tokensPer 1M; long prompts | $0.50 | $2.00 |
| Output above 100K tokens | $2.50 | $10.00 |
| Cached input read, per 1M | $0.01 | $0.10 |
| Context windowTokens | 1,000,000 | 1,048,576 |
| Max outputTokens | 128,000 | 943,718 |
| Accepts | file, image, text | audio, file, image, text, video |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | Yes | Yes |
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 | Gemini 4 Carbon |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0002 | $0.0040 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0029 | $0.058 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0040 | $0.080 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.079 | $0.315 |
Which to choose
Choose Claude Haiku 5.5 if
- Input tokens cost less: $0.10 against $2.00 per 1M
- Output tokens cost less: $0.50 against $10.00 per 1M
- Your prompts often run past 100K tokens: $0.50 against $2.00 per 1M input tokens there
- Cached input costs less: $0.01 against $0.10 per 1M
Choose Gemini 4 Carbon if
- You need the larger context window: 1,048,576 tokens against 1,000,000
- You need longer answers in one response: 943,718 tokens against 128,000
- It has to read audio and video, which the other model does not
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.