How much does Claude Haiku 5.5 cost?

On the Respan gateway, Claude Haiku 5.5 costs from $0.05 per 1M input tokens and $0.25 per 1M output tokens on Anthropic and OpenRouter, after gateway discounts. Averaged across its 7 routes from 5 providers, it costs $0.09 per 1M input tokens and $0.44 per 1M output tokens.

Which providers serve Claude Haiku 5.5 on Respan?

Claude Haiku 5.5 is available through 7 routes from 5 providers: Anthropic, OpenRouter, Bedrock, Perplexity, and Google Vertex AI. Bedrock and Google Vertex AI require your own provider API key (BYOK).

What is Claude Haiku 5.5's context window?

Claude Haiku 5.5 accepts up to 1M tokens of context on its largest provider route.

How do I use Claude Haiku 5.5 with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "anthropic/claude-haiku-5-5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Claude Haiku 5.5?

Over the last 30 days of requests through the Respan gateway, the fastest provider was Anthropic at 194 tokens per second, and the lowest response latency was 0.9 seconds on Bedrock. Speed varies with request size and provider.

Where does Claude Haiku 5.5 rank on the Respan Index?

Claude Haiku 5.5 scores 54.4 out of 100 on the Respan Index v1.1, ranking #13 of 143 models. By category: Coding 50.0, Agents 69.3, Reasoning 55.8, Knowledge & language 23.6, and Human preference 54.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

How does Claude Haiku 5.5 score on benchmarks?

Claude Haiku 5.5 has 25 published benchmark scores, including LiveBench Coding 77.9%, OSWorld 2.1 (offline subset) 72.4%, and GPQA Diamond 89.6%. Each score links to where it was published; the data is collected by llmmetric.com.

Claude Haiku 5.5

Q: What is Claude Haiku 5.5?

Claude Haiku 5.5 is a model from Anthropic, released on Oct 7, 2026. Claude Haiku 5.5 is Anthropic's fast, low-cost model for high-volume, latency-sensitive work, with a 1M-token context window, 128K max output, and adaptive thinking.

Claude Haiku 5.5 is Anthropic's fast, low-cost model for high-volume, latency-sensitive work, with a 1M-token context window, 128K max output, and adaptive thinking.

Input / output, fromSave up to 50%: $0.05 / $0.25 per 1M
Weekly tokens / requests: 420.5K / 114
Context: 1M tokens
Released: Oct 7, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "anthropic/claude-haiku-5-5".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="anthropic/claude-haiku-5-5",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "anthropic/claude-haiku-5-5",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "anthropic/claude-haiku-5-5",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

7 routes from 5 providers, cheapest first, priced per 1M tokens after gateway discounts. BYOK routes use your own key.

Provider	Context	Input	Output	Cache read	Capabilities
AnthropicSave 50%`anthropic/claude-haiku-5-5`	1M	$0.05/M	$0.25/M	$0.0050/M	+2
OpenRouter`openrouter/anthropic/claude-haiku-5.5:batch`	1M	$0.05/M	$0.25/M	$0.0050/M	+2
BedrockBYOK only`bedrock/global.anthropic.claude-haiku-5-5`	1M	$0.10/M	$0.50/M	$0.01/M	+2
OpenRouter`openrouter/anthropic/claude-haiku-5.5`	1M	$0.10/M	$0.50/M	$0.01/M	+2
Perplexity`perplexity/anthropic/claude-haiku-5-5`	1M	$0.10/M	$0.50/M	$0.01/M
Google Vertex AIBYOK only`vertex_ai/claude-haiku-5-5@default`	1M	$0.10/M	$0.50/M	$0.01/M	+2
BedrockBYOK only`bedrock/us.anthropic.claude-haiku-5-5`	1M	$0.11/M	$0.55/M	$0.01/M	+2

Is a provider down? Anthropic status, OpenRouter status, AWS Bedrock status, Perplexity status, Google AI status

Pricing

Averaged across 7 routes from 5 providers, in USD per 1M tokens after gateway discounts.

Average input: $0.09 per 1M
Average output: $0.44 per 1M
Average cache read: $0.0087 per 1M
Average cache write: $0.11 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.11/MBedrockLowest$0.05/MAnthropic and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway, 4 of 7 routes had traffic in that window. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

194tokens/sbest, on Anthropic

Faster than 92% of the other 483 models on the gateway

Anthropic194 tok/s
OpenRouter64 tok/s
Bedrock4.3 tok/s

Time to first token

Lower is better

0.9son Anthropic

Faster than 85% of the other 57 models on the gateway

Response latency

Lower is better

0.9sbest, on Bedrock

Faster than 66% of the other 500 models on the gateway

Bedrock0.9 s
OpenRouter1.0 s
Perplexity1.6 s

No traffic in the last 30 days on OpenRouter, Bedrock, and Google Vertex AI.

Benchmarks

The Respan Index plus 25 published scores from 6 sources, each linked to where it was published.

54.4/ 100

Respan Index#13 of 143

143 ranked models. The shaded band is this model's 95% interval, 49.0 to 59.6. MiMo-V2.6-Pro and GPT-5.6 Terra fall inside it, so the gap is within the margin of error.

Published scores

Benchmark	Score	Source	Published
LiveBench CodingLiveBench	77.9%	LiveBench	Oct 13, 2026
FrontierCode v1.1 (Main)Anthropic	46.4%	Anthropic	Oct 7, 2026
FrontierSWE V2Proximal Labs	43.8%	Proximal Labs	Oct 13, 2026
Terminal-Bench 4.0Anthropic	39.2%	Anthropic	Oct 7, 2026
Terminal-Bench 4.0Vals AI	35.4%	Vals AI	Oct 13, 2026

Benchmark	Score	Source	Published
OSWorld 2.1 (offline subset)Anthropic	72.4%	Anthropic	Oct 7, 2026
LiveBench Agentic CodingLiveBench	57.2%	LiveBench	Oct 13, 2026

Benchmark	Score	Source	Published
GPQA DiamondEpoch AI	89.6%	Epoch AI	Oct 13, 2026
LiveBench ReasoningLiveBench	84.6%	LiveBench	Oct 13, 2026
LiveBench Data AnalysisLiveBench	72.8%	LiveBench	Oct 13, 2026
Humanity's Last Exam (with tools)Anthropic	57.4%	Anthropic	Oct 7, 2026
Humanity's Last Exam (no tools)Anthropic	45.9%	Anthropic	Oct 7, 2026
EBR-benchEpoch AI	43.8%	Epoch AI	Oct 13, 2026
Mystery Game PuzzlesEpoch AI	30%	Epoch AI	Oct 13, 2026

Benchmark	Score	Source	Published
OTIS Mock AIME 2024-2025Epoch AI	98.9%	Epoch AI	Oct 13, 2026
LiveBench MathematicsLiveBench	92.8%	LiveBench	Oct 13, 2026
FrontierMath Tiers 1-3 v2Epoch AI	75.1%	Epoch AI	Oct 13, 2026
FrontierMath Tier 4 v2Epoch AI	46.3%	Epoch AI	Oct 13, 2026

Benchmark	Score	Source	Published
LiveBench Instruction FollowingLiveBench	66.5%	LiveBench	Oct 13, 2026
LiveBench LanguageLiveBench	63.5%	LiveBench	Oct 13, 2026
SimpleQA VerifiedEpoch AI	23.8%	Epoch AI	Oct 13, 2026