How much does Claude Haiku 4.5 cost?

Claude Haiku 4.5 costs $1.00/M input tokens and $5.00/M output tokens, with separate rates for Cache Read at $0.10/M tokens, Cache Write at $1.25/M tokens, and Cache Write (1h) at $2.00/M tokens.

What is the context length of Claude Haiku 4.5?

Claude Haiku 4.5 has a 200,000 token context window. It supports up to 64,000 completion tokens.

Does Claude Haiku 4.5 support tool calling and structured outputs?

Yes. Claude Haiku 4.5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Claude Haiku 4.5 support?

Claude Haiku 4.5 accepts text, images, and files such as PDFs as input and returns text.

Which providers serve Claude Haiku 4.5?

Claude Haiku 4.5 is served by 4 providers on OpenRouter: Azure, Amazon Bedrock, Google Vertex, and Anthropic. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Claude Haiku 4.5 released?

Claude Haiku 4.5 was released on October 15, 2025.

Anthropic: Claude Haiku 4.5

anthropic/claude-haiku-4.5

Compare

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.

It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.

Modalities

In / out price

$1 / $5per 1M

Context

200K

Released

Oct 15, 2025

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$1.00	$5.00	$0.10	0.53s	79 tok/s	98.60%
	$1.00	$5.00	$0.10	0.64s	98 tok/s	100.00%
	$1.00	$5.00	$0.10	0.41s	77 tok/s	98.81%
	$1.00	$5.00	$0.10	0.55s	85 tok/s	100.00%
Not used in Standard routing:Why these endpoints are not used
	$1.10	$5.50	$0.11	0.55s	142 tok/s	100.00%
	$1.10	$5.50	$0.11	0.53s	59 tok/s	100.00%
	$1.10	$5.50	$0.11	0.47s	130 tok/s	100.00%
	$1.10	$5.50	$0.11	0.54s	83 tok/s	100.00%

Input $1.00Output $5.00
79 tok/s98.60% uptime
Input $1.00Output $5.00
98 tok/s100.00% uptime
Input $1.00Output $5.00
77 tok/s98.81% uptime
Input $1.00Output $5.00
85 tok/s100.00% uptime
Not used in Standard routing:Why these endpoints are not used
Input $1.10Output $5.50
142 tok/s100.00% uptime
Input $1.10Output $5.50
59 tok/s100.00% uptime
Input $1.10Output $5.50
130 tok/s100.00% uptime
Input $1.10Output $5.50
83 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.668/M tokens

Output

$5.008/M tokens

Claude Haiku 4.5 — Price history

Price history

No effective price data for this selection

	$0.450	$5.00	63.4%	0.9%
	$0.651	$5.00	44.8%	21.7%
	$0.678	$5.00	39.7%	2.4%
	$0.686	$5.00	37.6%	72.1%
Not used in Standard routing:Why these endpoints are not used
	$0.298	$5.50	83.3%	2.0%
	$0.444	$5.50	68.5%	0.6%
	$0.929	$5.50	24.5%	0.3%
	$1.100	$5.50	0.0%	0.1%

Effective in $0.450Effective out $5.00
Token share
0.9%
Effective in $0.651Effective out $5.00
Token share
21.7%
Effective in $0.678Effective out $5.00
Token share
2.4%
Effective in $0.686Effective out $5.00
Token share
72.1%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.298Effective out $5.50
Token share
2.0%
Effective in $0.444Effective out $5.50
Token share
0.6%
Effective in $0.929Effective out $5.50
Token share
0.3%
Effective in $1.100Effective out $5.50
Token share
0.1%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

142tok/s

P50, best across providers

Latency

0.41s

P50, best provider

Latency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchGoogle Vertex73.1%66.5%Amazon Bedrock (EU)72.8%66.7%auto-routing72.9%65.6%Amazon Bedrock (US)72.8%65.4%Azure73.1%65.0%Google Vertex (EU)70.7%66.7%Amazon Bedrock71.8%65.6%Google Vertex (US)72.0%64.4%Anthropic72.0%64.4%

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.83%

Availability over the last 3 days

Last 72 hours

Availability 99.83%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.78%

Without Routing

97.48%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Anthropic: Claude Haiku 4.5 (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	Claude 4.5 Haiku (Reasoning) Intelligence Index	7.4
Artificial Analysis	Claude 4.5 Haiku (Reasoning) Coding Index	43.9
Artificial Analysis	Claude 4.5 Haiku (Reasoning) Agentic Index	8.0
Artificial Analysis	Claude 4.5 Haiku (Reasoning) GPQA Diamond	67.2%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) HLE	10.4%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) IFBench	54.3%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) τ²-Bench Telecom	54.7%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) AA-LCR	74.3%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) τ-Bench Banking	9.3%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) GDPval-AA	12.0%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) CritPt	0.0%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) LiveCodeBench	61.5%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) SciCode	42.2%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) Terminal-Bench Hard	27.3%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) Terminal-Bench 4.0	0.0%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) Terminal-Bench 2.1	44.2%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) MMLU-Pro	76.0%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) AA-Omniscience Accuracy	17.5%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) AA-Omniscience Non-Hallucination Rate	76.6%
Artificial Analysis	Claude 4.5 Haiku (Reasoning) AIME 2025	83.7%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) GPQA Diamond	64.6%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) HLE	4.2%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) IFBench	42.0%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) τ²-Bench Telecom	32.5%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) AA-LCR	49.7%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) CritPt	0.0%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) LiveCodeBench	51.1%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) Terminal-Bench Hard	27.3%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) MMLU-Pro	80.0%
Artificial Analysis	Claude 4.5 Haiku (Non-reasoning) AIME 2025	39.0%
Design Arena	Claude Haiku 4.5 Models Arena 3D Elo	1051
Design Arena	Claude Haiku 4.5 Models Arena Asciiart Elo	1135
Design Arena	Claude Haiku 4.5 Models Arena Code Categories Elo	1104
Design Arena	Claude Haiku 4.5 Models Arena Data Visualization Elo	1121
Design Arena	Claude Haiku 4.5 Models Arena Game Development Elo	1086
Design Arena	Claude Haiku 4.5 Models Arena SVG Elo	1015
Design Arena	Claude Haiku 4.5 Models Arena UI Component Elo	1090
Design Arena	Claude Haiku 4.5 Models Arena Website Elo	1114
Vals AI	Claude Haiku 4.5 (Nonthinking) CorpFin v2	60.3%
Vals AI	Claude Haiku 4.5 (Nonthinking) Public Benefits Bench v1.1	54.3%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

37Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

22.7Btokens

RevRing Testing

new

11.6Btokens

OpenClaw

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

11.4Btokens

Barrion AI Pentest

new

7.85Btokens

Rest of OpenRouter

3.14B

Top 5 Apps

798M

Anthropic: Claude Haiku versions

Available through EU in-region routing

Anthropic: Claude Haiku 4.5 is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe

Amazon Bedrock, Google Vertex

Prices in Europe

Amazon Bedrock: $1.10/M tokens input, $5.50/M tokens output
Google Vertex: $1.10/M tokens input, $5.50/M tokens output

Base URL

https://eu.openrouter.ai/api/v1

Plan

Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

More models from Anthropic

Claude Fable 5.2

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible software migrations, designed working electronic devices from scratch, and made progress on open problems in physics and mathematics. It communicates more clearly than earlier Fable models and generates output up to 30% faster than Fable 5.1. Adaptive extended thinking is always on, with reasoning effort levels from low to max (default high) and preserved thinking across turns. Anthropic recommends Opus 5.5 as the daily driver for most coding and knowledge work, with Fable 5.2 for the most ambitious, open-ended problems.

Text1M context$8 / $40

Claude Fable 5.2 (batch)

Text1M context$4 / $20

Claude Haiku 5.5

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.

It is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.

Text1M context$0.10 / $0.50

Claude Haiku 5.5 (batch)

Text1M context$0.05 / $0.25

Claude Sonnet 5.5

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

Text1M context$2 / $10

Claude Sonnet 5.5 (batch)

Thinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.

Text1M context$1 / $5

Claude Opus 5.5

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.

The model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.

Text1M context$4 / $20

Claude Opus 5.5 (batch)

Text1M context$2 / $10

Claude Fable 5.1

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

Text1M context$10 / $50

Claude Fable 5.1 (batch)

Text1M context$5 / $25

Claude Opus 5

Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 5 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context

Claude Opus 5

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$5 / $25

Claude Opus 5 (batch)

The model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.

Text1M context$2.50 / $12.50

Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.

Text1M context$2 / $10

Claude Sonnet 5 (batch)

Text1M context$1 / $5

Claude Fable Latest

This model always redirects to the latest model in the Claude Fable family.

Text1M context

Claude Fable 5

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.

It is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.

Text1M context$10 / $50

Claude Fable 5 (batch)

Text1M context$5 / $25

Claude Opus 4.8

Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8.

Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Note: As of September 1, 2026, this dedicated fast model is deprecated. Fast mode is now served by the fast service tier endpoint on Claude Opus 4.8 — request it with service_tier: "fast" or speed: "fast". Requests to this model keep working and are served by the same fast tier capacity, so no action is required, but new integrations should target the regular model. Learn more in our service tier docs: https://openrouter.ai/docs/guides/features/service-tiers

Text1M context

Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.

It is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.

Text1M context$5 / $25

Anthropic: Claude Haiku 4.5

Providers