# Claude Haiku 5.5 Usage, Cost & Rank | OpenCode Data

> Claude Haiku 5.5 ranked #43 by tokens across OpenCode last week, with 0% of tokens over the past two months. Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens.

Fast Claude model for responsive assistance, classification, and lightweight agents

- Page: https://opencode.ai/data/anthropic/claude-haiku-5-5
- JSON: https://opencode.ai/data/anthropic/claude-haiku-5-5.json
- Model ID: anthropic/claude-haiku-5-5
- Lab: Anthropic
- Updated: 2026-10-07T20:48:51.000Z

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 1M |
| Max output | 128K |
| Knowledge cutoff | 2026-06 |
| Release date | 2026-10-07 |
| Input modalities | text, image, pdf |
| Output modalities | text |
| Reasoning | Yes |
| Tool calling | Yes |
| Open weights | No |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $0.10 | $0.50 | $0.01 | $0.13 |

## OpenCode usage: past 2 months

| Metric | Value |
| --- | --- |
| Rank by tokens last week | #43 |
| Tokens | 352M |
| Share of all tokens | 0% |
| Change vs previous 2 months | +100% |
| Unique users | 176 |
| Completed sessions | 755 |
| Average tokens per session | 466K |
| Average cost per session | $0.0406 |
| Total spend | $31 |
| Input tokens served from cache | 98.8% |
| Weekly retention | - |

## Daily usage: past 2 months

| Date | Tokens | Unique users | Sessions |
| --- | --- | --- | --- |
| 2026-10-07 | 352M | 176 | 755 |

## Top countries: past 2 months

| Rank | Country | Tokens | Share |
| --- | --- | --- | --- |
| 1 | United States | 0 | 14.1% |
| 2 | Bangladesh | 0 | 10.6% |
| 3 | Germany | 0 | 9.8% |
| 4 | Poland | 0 | 8.2% |
| 5 | Brazil | 0 | 8.2% |
| 6 | Italy | 0 | 5.1% |
| 7 | Ukraine | 0 | 4% |
| 8 | Argentina | 0 | 3.7% |
| 9 | India | 0 | 3.6% |
| 10 | United Kingdom | 0 | 3.5% |
| 11 | France | 0 | 3.2% |
| 12 | Vietnam | 0 | 3.1% |
| 13 | Iraq | 0 | 2.7% |
| 14 | Spain | 0 | 2% |
| 15 | Finland | 0 | 2% |

## Nearby models by tokens last week

| Rank | Model | Lab | Tokens |
| --- | --- | --- | --- |
| 39 | [glm-5.1](https://opencode.ai/data/zhipuai/glm-5-1.md) | Zhipu | 1.1B |
| 40 | [minimax-m2.5](https://opencode.ai/data/minimax/minimax-m2-5.md) | MiniMax | 989M |
| 41 | [qwen3.6-plus](https://opencode.ai/data/alibaba/qwen3-6-plus.md) | Qwen | 900M |
| 42 | [qwen3.7-max](https://opencode.ai/data/alibaba/qwen3-7-max.md) | Qwen | 366M |
| 43 | [claude-haiku-5-5](https://opencode.ai/data/anthropic/claude-haiku-5-5.md) | Anthropic | 352M |
| 44 | [gpt-5-nano](https://opencode.ai/data/openai/gpt-5-nano.md) | OpenAI | 258M |
| 45 | [coding-glm-5.3](https://opencode.ai/data/zhipu/coding-glm-5-3.md) | Zhipu | 2.9M |
| 46 | [community/scriptsnsenses-sys/gemini-3.1-pro](https://opencode.ai/data/google/community-scriptsnsenses-sys-gemini-3-1-pro.md) | Google | 425K |
| 47 | [qwen3.8-27b](https://opencode.ai/data/alibaba/qwen3-8-27b.md) | Qwen | 30K |
| 48 | [ocz/muse-spark-1.3-contributor](https://opencode.ai/data/meta/ocz-muse-spark-1-3-contributor.md) | Meta | 13K |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| GDPval-AA | 1620 | Elo | https://www.anthropic.com/claude-haiku-5-5 |
| AA-Briefcase | 1578 | Elo | https://www.anthropic.com/claude-haiku-5-5 |
| OSWorld | 72.4 | partial score | https://www.anthropic.com/claude-haiku-5-5 |
| Humanity's Last Exam | 45.9 | score | https://www.anthropic.com/claude-haiku-5-5 |
| Humanity's Last Exam | 57.4 | score | https://www.anthropic.com/claude-haiku-5-5 |
| Terminal-Bench | 39.2 | score | https://www.anthropic.com/claude-haiku-5-5 |
| FrontierCode | 46.4 | score | https://www.anthropic.com/claude-haiku-5-5 |
| Chartography | 46.4 | score | https://www.anthropic.com/claude-haiku-5-5 |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.