Claude Haiku 5.5 launches with 1M context and API pricing from $0.10 per million tokens

Verified October 7, 2026

Anthropic released Claude Haiku 5.5 on October 7, 2026. The new small Claude model is aimed at high-volume, latency-sensitive workloads including classification, extraction, routing, summarization and subagent tasks. ¹²

The headline specifications are a one-million-token context window, up to 128,000 standard output tokens, adaptive thinking, and API pricing starting at $0.10 per million input tokens and $0.50 per million output tokens. The Claude API model ID is claude-haiku-5-5. ²³⁴

Haiku 5.5 is materially cheaper than Haiku 4.5 while gaining a much larger context window and adaptive reasoning. The lowest $0.10/$0.50 prices only apply when the prompt is no larger than 100,000 tokens.

Claude Haiku 5.5 specifications

Specification	Claude Haiku 5.5
Release date	October 7, 2026
Claude API ID	claude-haiku-5-5
Context window	1,000,000 tokens
Standard max output	128,000 tokens
Batch max output	up to 300,000 tokens, beta
Thinking	Adaptive
Default effort	medium
Input, prompts up to 100K	$0.10 / MTok
Output, prompts up to 100K	$0.50 / MTok
Input, prompts over 100K	$0.50 / MTok
Output, prompts over 100K	$2.50 / MTok
Cache read, up to 100K	$0.01 / MTok
Batch API	50% discount on input and output
Knowledge cutoff	June 2026

The biggest change is the price

Claude Haiku 4.5 was listed at $1 per million input tokens and $5 per million output tokens. Haiku 5.5 cuts those list prices to $0.10 input and $0.50 output when prompts stay at or below 100,000 tokens. ⁴

On a pure price-per-token basis, that is a 90% reduction.

Example: 5 million input tokens + 1 million output tokens

For a workload consuming five million input tokens and one million output tokens, with every request remaining below the 100K prompt threshold:

• Haiku 4.5: 5 × $1 + 1 × $5 = $10
• Haiku 5.5: 5 × $0.10 + 1 × $0.50 = $1

That is a nominal 90% difference.

Anthropic says typical tasks cost roughly 75% less to run than Haiku 4.5. That lower real-world figure matters because Haiku 5.5 uses a newer tokenizer. Anthropic’s documentation says the same text can count as roughly 30% more tokens than it did on Haiku 4.5. ¹³

For production systems, cost per successful task is therefore a better metric than sticker price per million tokens.

Two pricing tiers

October 9, 2026 rate check: Anthropic’s API rate card lists $0.125 per million 5-minute cache writes, $0.20 for 1-hour writes, $0.01 for cache reads through 100K prompt tokens; above 100K those become $0.625 / $1.00 / $0.05. Applicable U.S. taxes and partner platform rates may vary.

The lowest rates only apply if the prompt contains 100,000 tokens or fewer.

Above that threshold, pricing rises to: ⁴

• $0.50 / MTok input
• $2.50 / MTok output
• $0.05 / MTok cache read

This distinction is important because Haiku 5.5 supports a one-million-token context window. A 500K-token prompt is not billed at the same rate as a 20K-token prompt.

The context window grows from 200K to 1M

Haiku 5.5 increases the context window from 200,000 to 1,000,000 tokens, a fivefold jump. Standard maximum output also doubles from 64K to 128K tokens. ²³

That makes the model particularly relevant for:

• large document sets,
• retrieval and RAG systems,
• code repositories,
• long agent histories,
• context compression,
• high-volume document processing.

Anthropic also documents a beta Batch API configuration that can support up to 300K output tokens.

Adaptive thinking reaches the Haiku tier

Haiku 5.5 supports Anthropic’s current adaptive thinking system, with medium as the default effort level. ³⁵

Instead of assigning every request a fixed reasoning budget, the model can spend different amounts of reasoning depending on the task. That is potentially valuable in agent pipelines: simple routing calls can remain cheap, while a more difficult tool-use or coding subtask can receive more reasoning without immediately escalating to a larger model.

This also affects migration. Integrations built around manual extended thinking or budget_tokens should be updated rather than assuming Haiku 5.5 behaves like Haiku 4.5.

Anthropic positions Haiku 5.5 as a high-volume worker

Anthropic explicitly describes Haiku 5.5 as a model for high-volume, latency-sensitive tasks such as: ¹

• classification,
• extraction,
• routing,
• summarization,
• database queries,
• live support,
• in-app assistants,
• voice agents,
• context compression,
• subagent work.

That positioning matters more than whether Haiku beats Sonnet on every benchmark. A low-cost worker model does not need to solve every open-ended problem. It needs to solve a very large number of narrow and medium-complexity tasks reliably, then escalate difficult cases to a stronger model.

Benchmarks: a large launch-day jump, with an evidence caveat

Anthropic reports large improvements over Haiku 4.5. Two of the most striking published results are: ¹

Benchmark	Haiku 5.5	Haiku 4.5
OSWorld 2.1, reported offline subset	72.4%	15.7%
Terminal-Bench 4.0	39.2%	0.0%

Those numbers point to substantial improvements in computer use and agentic coding.

They should still be framed correctly. The benchmark projects themselves are externally developed, but the Haiku 5.5 scores shown at launch are primarily being communicated by Anthropic. Broad independent reruns using matched settings are naturally limited on release day.

What these scores do not tell you

A synthetic benchmark does not directly measure:

• number of tool calls per successful task,
• retry loops,
• stability over long agent runs,
• real tokens-per-second throughput,
• cache effectiveness in your own prompts,
• fallback frequency to a larger model,
• final cost per successfully completed task.

For an agent platform, cost per successful task is usually the more useful business metric.

Prompt caching can be extremely cheap

For prompts in the lower pricing tier, a cache read costs only $0.01 per million tokens. ⁴

That can matter substantially for repeated context such as:

• large system prompts,
• project rules,
• static documentation,
• reusable repository context,
• stable agent background instructions.

A system with a high cache-hit ratio may therefore achieve an effective input cost well below the normal uncached input rate.

Migrating from Haiku 4.5 requires more than changing the model ID

Existing integrations should be tested.

Anthropic highlights changes including: ⁵

1. Switch the model ID to claude-haiku-5-5.
2. Move from manual extended thinking to adaptive thinking.
3. Remove unsupported non-default sampling parameters.
4. Do not rely on assistant prefill.
5. Parse response blocks defensively.
6. Review updated computer-use toolsets.
7. Re-measure token counts and costs because of the newer tokenizer.

That last point matters for observability. A cost dashboard calibrated to Haiku 4.5 token ratios can systematically misestimate Haiku 5.5 usage.

Availability

Anthropic lists Haiku 5.5 across: ²

• Claude Platform
• Amazon Bedrock
• Google Cloud
• Microsoft Foundry
• Claude Platform on AWS

Platform-specific model identifiers can differ. In the Claude API, the model ID is claude-haiku-5-5.

Because the model launched on October 7, 2026, cloud-provider documentation and SDK registries may temporarily lag behind Anthropic’s own model documentation.

Claude Haiku 5.5 vs Haiku 4.5

Category	Haiku 4.5	Haiku 5.5
Context	200K	1M
Max output	64K	128K
Thinking	Extended	Adaptive
Small-prompt input	$1/MTok	$0.10/MTok
Small-prompt output	$5/MTok	$0.50/MTok
Cache read	$0.10/MTok	from $0.01/MTok
Positioning	fast small Claude	high-volume routing and subagents
Tokenizer	older generation	newer; about 30% more tokens for identical text according to Anthropic

Haiku 5.5 is therefore more than a routine version bump. Anthropic changes the pricing model, context size, reasoning system, tokenizer and intended agent role at the same time.

Where Haiku 5.5 fits in a real pipeline

Haiku is a sensible first choice for bounded, repeatable steps: extracting fields from documents, classifying requests, summarizing retrieved passages or handling a narrow coding subtask. For open-ended, multi-stage software engineering, Sonnet or Opus is often the safer starting point. That is also consistent with Anthropic’s model positioning; launch benchmark scores are not proof of better results on your own tasks. ¹

A useful routing evaluation starts with a fixed set of real requests. Run the same tasks through Haiku 4.5, Haiku 5.5 and a stronger baseline. Check correctness and output-schema validity first; then record latency, input and output tokens, cache hits, retries and escalations.

Example escalation rule: let Haiku extract data into a specified JSON schema. If validation fails, retry once with the error. Escalate to Sonnet if the second output still fails. This measures cost per accepted result, not just the cost of individual tokens. Remember that prompts exceeding 100,000 tokens incur the higher Haiku 5.5 price tier. ⁴

Claude Max and Team: monthly API credits and actual eligibility

According to Anthropic’s subscriber credit guide, the monthly Claude Console credits are $100 for Max 5x, $200 for Max 20x, $20 per Team Standard seat, and $100 per Team Premium seat, pooled up to $500 for the whole Team per month. Claude Free, Pro and Enterprise are ineligible for this particular credit.

How to claim: Link a Claude Console organization using Settings → Billing (Max) or Organization settings → Billing (Team). New subscribers can claim after seven days; rollout may vary. Unused credits expire every billing cycle and do not roll over.

Covers: Claude API, Claude Managed Agents, Claude Agent SDK and Console playground. Not Claude Code, extra Claude app usage, Bedrock, Google Cloud or third-party routers. This is not an unlimited-token plan. Official rules

Assessment

Haiku 5.5’s short-prompt tier can make high-volume agent calls inexpensive. Long prompts, the updated tokenizer and retries narrow that advantage. Before putting it in production, evaluate a labeled set of real tasks and compare the total cost of outcomes your application actually accepts.

Source notes

Footnotes

1. Anthropic 1 ↩ ↩² ↩³ ↩⁴ ↩⁵

2. Anthropic 2 ↩ ↩² ↩³ ↩⁴

3. Anthropic 3 ↩ ↩² ↩³ ↩⁴

4. Anthropic 5 ↩ ↩² ↩³ ↩⁴ ↩⁵

5. Anthropic 4 ↩ ↩²