Best for budget
Low input/output cost for high-volume workloads.
Model · Anthropic
Claude Haiku 5.5
Claude Haiku 5.5 is served by Anthropic through OpenRouter. It provides 1M tokens of context and supports text, vision, files inputs.
Context window
1M tokens
Input / 1M tokens
$0.100
Output / 1M tokens
$0.500
Key facts
| Provider | Anthropic |
| OpenRouter ID | anthropic/claude-haiku-5.5 |
| Modalities | Text, Vision, Files |
| Best for | Budget, Agents |
Source
openrouter.ai/api/v1/models Verified 2026-10-10 Drift-checked daily 06:00 CST Best-fit workloads
Best for agents
Tool use, structured output and multi-step reasoning.
Cost estimates
These examples use the 2026-10-10 input and output prices. Cache discounts, provider surcharges and tool fees are excluded.
| Workload | Input | Output | Estimated cost |
|---|---|---|---|
| Quick test | 20,000 | 5,000 | $0.005 |
| Product chat month | 500,000 | 125,000 | $0.113 |
| Document batch | 5,000,000 | 1,000,000 | $1.00 |
Strengths
- ✓ $0.10 in / $0.50 out per million — the cheapest row here from a frontier vendor
- ✓ 1M-token window at that price, which is not normal for a small model
- ✓ Positioned for summarisation, subagents and browser use, with stronger coding and computer use than Haiku 4.5
Limitations
- ! Text output only
- ! It is the small model in a line whose small model is now cheap but not free: 20x under Sonnet 5.5, and priced per token either way
- ! Computer-use positioning is the vendor's; the hub carries the price and the window, not a task benchmark
OpenRouter API quickstart
Run these examples from your server or edge function. Keep the OpenRouter API key private and do not expose it in browser code.
cURL
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-haiku-5.5",
"messages": [{ "role": "user", "content": "Summarize this document in five bullet points." }],
"max_tokens": 500
}'JavaScript / TypeScript
const response = await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "anthropic/claude-haiku-5.5",
messages: [{ role: "user", content: "Summarize this document in five bullet points." }],
max_tokens: 500,
}),
});
const data = await response.json();
console.log(data.choices[0].message.content);How to evaluate Claude Haiku 5.5
- Run five real tasks from your product, not generic demo prompts.
- Record token usage, latency and output quality.
- Estimate cost using your real input/output mix.
- Compare it against one model with a similar price and one stronger model.
Compare models View on OpenRouter ↗
Claude Haiku 5.5 FAQ
What is Claude Haiku 5.5?
Claude Haiku 5.5 is a Anthropic model available through OpenRouter. It supports text, vision, files inputs and is suited for budget, agents workloads.
How much does Claude Haiku 5.5 cost on OpenRouter?
The 2026-10-10 snapshot lists $0.100 per 1M input tokens and $0.500 per 1M output tokens. Verify current pricing on OpenRouter before production.
How large is Claude Haiku 5.5's context window?
Claude Haiku 5.5 offers 1M tokens of context in the current snapshot. Provider-specific limits and surcharges may apply.
Head-to-head comparisons
Gemini 3.8 Flash vs Claude Haiku 5.5
If your input is words and pictures, Haiku 5.5 is the cheaper answer by a wide margin, and it is positioned for exactly the high-volume jobs (summarisation, subagents, browser use) that cheap tiers exist for. Reach for Gemini Flash when the input is a video, a recording, or a folder of mixed files — that is the capability worth 7.5x, not the model's badge.
Pricing and context data are based on a 2026-10-10 snapshot. Provider limits can change; always verify on OpenRouter before production.