Verified 2026-10-08 · sourced from Anthropic
Claude Haiku 5.5 Token Calculator, Pricing & 100K/1M Cost
Check Anthropic Claude Haiku 5.5 pricing, estimate 100K and 1M token cost, and size a real API budget before you send a single request. Standard pricing is $0.10 per million input tokens and $0.50 per million output tokens with a 1M token context window.
Quick answer: Claude Haiku 5.5 pricing per 1M tokens is $0.10 input and $0.50 output. Context window: 1,000,000 tokens · Cached input: $0.010 / 1M.
Best for searches like Claude Haiku 5.5 token calculator, Claude Haiku 5.5 pricing, Claude Haiku 5.5 100K tokens cost, Claude Haiku 5.5 1M token cost.
Reference rates: Standard · ≤100K input · global
USD per million text tokens. Verified 2026-10-08 · Official source
| Mode / prompt size | Input | Cache read | Cache write | Output |
|---|---|---|---|---|
| Standard ≤100,000 input | $0.1 | $0.01 | $0.125 (5m) / $0.2 (1h) | $0.5 |
| Standard >100,000 input | $0.5 | $0.05 | $0.625 (5m) / $1 (1h) | $2.5 |
| Batch ≤100,000 input | $0.05 | $0.005 | $0.0625 (5m) / $0.1 (1h) | $0.25 |
| Batch >100,000 input | $0.25 | $0.025 | $0.3125 (5m) / $0.5 (1h) | $1.25 |
1,000,000 context tokens · max output 128,000. Local token counts are estimates; use the provider’s usage counts for an invoice estimate.
Text-only estimate. Local token counts are approximate; use provider-reported usage for billing. Tool, image, audio and video charges are excluded.
Up to 100,000 input tokens uses the lower tier. Above 100,000, the full request uses higher input, cache and output rates, not just the excess tokens. The threshold is per request; daily call volume does not change it.
For prompt-size tier selection, total input includes uncached, cache-read and cache-creation tokens, using the provider’s total-input definition. This calculator applies one selected input billing operation to all input; it does not split mixed cache usage.
US-only inference adds 10% to token rates and is excluded from this global-endpoint estimate. Newer Claude tokenization differs from the local estimator; no fixed conversion factor is applied.
Billed output includes reasoning/thinking tokens that cannot be inferred from pasted final text; use API-reported output usage for accurate billing.
Batch: Batch halves token rates and stacks with cache read/write pricing. Cache hits in asynchronous batches are best effort, not guaranteed. Cache writes use separate 5-minute and 1-hour retention rates.
Pick the route that matches what you searched for
Some visitors want a fast Claude Haiku 5.5 API cost estimate, others want a direct 100K or 1M token budget, and some are already comparing alternatives. These shortcuts remove the extra click.
Estimate a single request or prompt budget right now.
Jump straight to the most common budgeting checkpoint.
Use this when you are sizing production traffic or a monthly plan.
Open the closest head-to-head comparison instead of researching from scratch.
Context window
1,000,000 tokens
Input price
$0.10 / 1M
Output price
$0.50 / 1M
Cached input
$0.010 / 1M
Pricing modes and thresholds
Long-context pricing starts above 100,000 input tokens.
Usage scenarios
Compare standard and cached pricing (where available) across common workloads.
| Scenario | Tokens in | Tokens out | Total tokens | Standard cost | Cached cost |
|---|---|---|---|---|---|
Quick chat reply Single user question with a short assistant answer | 650 | 220 | 870 | $0.0002 | $0.0001 |
Coding assistant session Multi-turn pair programming exchange (≈6 turns) | 2,600 | 1,400 | 4,000 | $0.0010 | $0.0007 |
Knowledge base response Retrieval-augmented answer referencing multiple passages | 12,000 | 3,000 | 15,000 | $0.0027 | $0.0016 |
Near-max context run Large document processing approaching the 1M token limit | 880,000 | 120,000 | 1,000,000 | $0.740 | $0.344 |
Daily & monthly budgeting
Translate usage into predictable operating expenses across popular deployment sizes.
| Profile | Requests/day | Tokens/day | Daily cost | Monthly cost | Cached daily | Cached monthly |
|---|---|---|---|---|---|---|
| Team pilot | 25 | 75,000 | $0.0175 | $0.525 | $0.0130 | $0.390 |
| Product launch | 100 | 500,000 | $0.550 | $16.50 | $0.393 | $11.78 |
| Enterprise scale | 500 | 3,000,000 | $3.50 | $105.00 | $2.60 | $78.00 |
Pricing notes
- Text-only estimate. Local token counts are approximate; use provider-reported usage for billing. Tool, image, audio and video charges are excluded.
- Up to 100,000 input tokens uses the lower tier. Above 100,000, the full request uses higher input, cache and output rates, not just the excess tokens. The threshold is per request; daily call volume does not change it.
- For prompt-size tier selection, total input includes uncached, cache-read and cache-creation tokens, using the provider’s total-input definition. This calculator applies one selected input billing operation to all input; it does not split mixed cache usage.
- US-only inference adds 10% to token rates and is excluded from this global-endpoint estimate. Newer Claude tokenization differs from the local estimator; no fixed conversion factor is applied.
- Billed output includes reasoning/thinking tokens that cannot be inferred from pasted final text; use API-reported output usage for accurate billing.
Frequently asked questions
How much does Claude Haiku 5.5 cost per 1,000 tokens?
At the published rates of $0.10 per million input tokens and $0.50 per million output tokens, a typical 1,000 token request (≈70% input, 30% output) costs about $0.0002.
Does Claude Haiku 5.5 offer cached input discounts?
Claude Haiku 5.5 drops input costs to $0.010 per million cached tokens. Using cached contexts, that same 1,000 token call totals $0.0002, a significant saving for chatbots and RAG systems.
What is the context window for Claude Haiku 5.5?
Claude Haiku 5.5 supports up to 1,000,000 tokens (1M), allowing large prompts and retrieval-augmented payloads in a single call.
How fresh is the Claude Haiku 5.5 pricing data?
Pricing is sourced from https://platform.claude.com/docs/en/about-claude/pricing and was last verified on 2026-10-08. The calculator updates automatically when models.json is refreshed.