impulse

Claude Haiku 5.5

Frontier lab

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.

API id claude-haiku-5-5Released 7 Oct 2026 (6 weeks ago)
Input / 1M
$0.10
at Anthropic
Output / 1M
$0.50
at Anthropic
Context window
1M
tokens
Max output
128K
tokens per reply
Hosts
9
24 listings
Released
6 weeks ago
7 Oct 2026

Pricing

List prices at Anthropic, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.10$0.50
Cached input
90% off input
$0.01
Cache write, 5 minutes$0.125
Cache write, 1 hour$0.20
Batch
50% off
$0.05$0.25
Prompts over 100K tokens$0.50$2.50
Web search
$10.00 per 1,000 searches
Regional endpoints
10% more

What it costs a month

At Anthropic list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$59.40
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$44.40
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$74.40
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$180
Use your own numbers

Where to run it

9 hosts serve Claude Haiku 5.5. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
AnthropicLab API
claude-haiku-5-5
$0.10 / $0.50
anthropic.claude-haiku-5-5
$0.10 / $0.50
claude-haiku-5-5
$0.10 / $0.50
Retires 29 Sep 2027
claude-haiku-5-5
$0.10 / $0.50
claude-haiku-5-5
$0.10 / $0.50
claude-haiku-5-5
$0.10 / $0.50
PerplexityGateway
claude-haiku-5-5
$0.10 / $0.50
databricks-claude-haiku-5-5
$0.10 / $0.50
claude-haiku-5.5
$0.135 / $0.675
+35% vs headline
GitHub CopilotSubscription
claude-haiku-5.5
In the subscription
Show 14 more listings: regions, snapshots and variants
Amazon Bedrock
Claude Platform
claude-haiku-5-5
$0.10 / $0.50
global
global.anthropic.claude-haiku-5-5
$0.10 / $0.50
Mantle
anthropic.claude-haiku-5-5
$0.11 / $0.55
+10% vs headline
au
au.anthropic.claude-haiku-5-5
$0.11 / $0.55
+10% vs headline
ca
ca.anthropic.claude-haiku-5-5
$0.11 / $0.55
+10% vs headline
eu
eu.anthropic.claude-haiku-5-5
$0.11 / $0.55
+10% vs headline
jp
jp.anthropic.claude-haiku-5-5
$0.11 / $0.55
+10% vs headline
us
us.anthropic.claude-haiku-5-5
$0.11 / $0.55
+10% vs headline
apac
apac.anthropic.claude-haiku-5-5
$0.11 / $0.55
+10% vs headline
us-gov-west-1 · Mantle
anthropic.claude-haiku-5-5
$0.12 / $0.60
+20% vs headline
us-gov-east-1
anthropic.claude-haiku-5-5
$0.12 / $0.60
+20% vs headline
us-gov-west-1
anthropic.claude-haiku-5-5
$0.12 / $0.60
+20% vs headline
us-gov
us-gov.anthropic.claude-haiku-5-5
$0.12 / $0.60
+20% vs headline
Vertex AI
Alias
claude-haiku-5-5@default
$0.10 / $0.50

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImagesPDFs
Produces
Text
Effort settings the source lists
xhighmax
Features
Adaptive thinkingComputer useNative structured outputPDF inputPrompt cachingBuilt-in web search

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Anthropic.

Smaller Anthropic models

No cheaper Anthropic model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Qwen3.8 Flash
    Alibaba Qwen · on AIHubMix
    $0.113 / $0.38
    Has every key capability
    10% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    11% less
  • DeepSeek V4.1 Flash
    DeepSeek · on Sail
    $0.09 / $0.30
    Has every key capability
    29% less
  • MiMo V2.6 Flash
    Xiaomi · on GMI Cloud
    $0.112 / $0.224
    Has every key capability
    30% less

Model line

Newer and older versions, at each lab's own price.

  1. Oct 2026Claude Haiku 5.5Latest$0.10 / $0.50
  2. Oct 2025Claude Haiku 4.5$1.00 / $5.00
  3. Oct 2024Claude 3.5 Haiku$0.80 / $4.00
  4. Mar 2024Claude 3 Haiku$0.25 / $1.25

Call it

Using Anthropic's API.

Python
from anthropic import Anthropic

client = Anthropic()  # reads ANTHROPIC_API_KEY

message = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

Quick answers

How much does Claude Haiku 5.5 cost?

On Anthropic, Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens. Cached input costs $0.01 per million tokens.

Which APIs offer Claude Haiku 5.5?

Claude Haiku 5.5 runs on 9 APIs: Anthropic, Amazon Bedrock, Azure AI Foundry, OpenCode Go, Snowflake, Vertex AI, Perplexity, Databricks and Kyma API.

What is Claude Haiku 5.5's context window?

1M tokens, with up to 128K tokens in one reply.

Is Claude Haiku 5.5 being retired?

Azure AI Foundry retires it on 29 Sep 2027. 8 hosts keep serving it.

Is there a newer version of Claude Haiku 5.5?

No. Claude Haiku 5.5 is the newest model in its line.

What are cheaper alternatives to Claude Haiku 5.5?

Models that cost less and keep most of what it can do: Qwen3.8 Flash on AIHubMix (10% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Claude Haiku 5.5 released?

Anthropic released it on 7 Oct 2026.

What is Claude Haiku 5.5's API model id?

Use claude-haiku-5-5 with Anthropic. Other hosts use their own ids: anthropic.claude-haiku-5-5 on Amazon Bedrock, databricks-claude-haiku-5-5 on Databricks, claude-haiku-5.5 on Kyma API.

Sources

Raw catalog entry for claude-haiku-5-5 on Anthropic
{
  "input_cost_per_token_above_100k_tokens_batches": 2.5e-7,
  "output_cost_per_token_above_100k_tokens_batches": 0.00000125,
  "cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-7,
  "cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-8,
  "supports_anthropic_compaction": true,
  "cache_creation_input_token_cost": 1.25e-7,
  "cache_creation_input_token_cost_above_1hr": 2e-7,
  "cache_creation_input_token_cost_batches": 6.25e-8,
  "cache_read_input_token_cost": 1e-8,
  "cache_read_input_token_cost_batches": 5e-9,
  "input_cost_per_token": 1e-7,
  "input_cost_per_token_batches": 5e-8,
  "litellm_provider": "anthropic",
  "max_input_tokens": 1000000,
  "max_output_tokens": 128000,
  "mode": "chat",
  "output_cost_per_token": 5e-7,
  "output_cost_per_token_batches": 2.5e-7,
  "search_context_cost_per_query": {
    "search_context_size_high": 0.01,
    "search_context_size_low": 0.01,
    "search_context_size_medium": 0.01
  },
  "supports_adaptive_thinking": true,
  "thinking_on_by_default": true,
  "supports_mid_conversation_system": true,
  "supports_assistant_prefill": false,
  "supports_computer_use": true,
  "supports_function_calling": true,
  "supports_native_structured_output": true,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_sampling_params": false,
  "supports_tool_choice": true,
  "supports_vision": true,
  "supports_xhigh_reasoning_effort": true,
  "supports_max_reasoning_effort": true,
  "provider_specific_entry": {
    "us": 1.1
  },
  "supports_output_config": true,
  "supports_forced_tool_use": true,
  "thinking_always_on": false,
  "prompt_cache_min_tokens": 512,
  "source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview",
  "supports_web_search": true,
  "input_cost_per_token_above_100k_tokens": 5e-7,
  "output_cost_per_token_above_100k_tokens": 0.0000025,
  "cache_creation_input_token_cost_above_100k_tokens": 6.25e-7,
  "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 0.000001,
  "cache_read_input_token_cost_above_100k_tokens": 5e-8
}