Pricingby GlyphClaude 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.
Ways to buy 10
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
The lab's own API · cached $0.1 | $1 | $5 | $1 / $5List price | $0.1 | List price |
 AWS Bedrockglobal · cached $0.1 | $1 | $5 | $1 / $5Same as list | $0.1 | Same as list |
global · cached $0.1 | $1 | $5 | $1 / $5Same as list | $0.1 | Same as list |
From the platform pricing page | $1 | $5 | $1 / $5Same as list | n/a | Same as list |
global · cached $0.1 | $1 | $5 | $1 / $5Same as list | $0.1 | Same as list |
| AWS Bedrock eu-west-1 · cached $0.11 | $1.1 | $5.5 | $1.1 / $5.5+10% vs list | $0.11 | +10% vs list |
| AWS Bedrock us · cached $0.11 | $1.1 | $5.5 | $1.1 / $5.5+10% vs list | $0.11 | +10% vs list |
europe · cached $0.11 | $1.1 | $5.5 | $1.1 / $5.5+10% vs list | $0.11 | +10% vs list |
us-east5 · cached $0.11 | $1.1 | $5.5 | $1.1 / $5.5+10% vs list | $0.11 | +10% vs list |
From the platform pricing page | $1.2 | $6 | $1.2 / $6+20% vs list | n/a | +20% vs list |
USD per 1M tokens; batch $0.5 in, $2.5 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $200.00 direct.
Helicone$200.00+0%
Kong AI Gateway$200.00+0%
LiteLLM$200.00+0%
Neon AI Gateway$200.00+0%
Vercel AI Gateway$200.00+0%
Cloudflare AI Gateway$210.00+5%
Requesty$210.00+5%
Eden AI$211.00+5.5%
OpenRouter$211.00+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. |
Anthropic · 1M | $2 | $10 | $2 / $10 | $4 | 1M | Lab list price | · | Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. |
Anthropic · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · | Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. |
Anthropic · 1M | $10 | $50 | $10 / $50 | $20 | 1M | Lab list price | · | 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... |
OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · | GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. |
Google · 1MCheapest: $2 on Google Gemini API (flex) | $2 | $10 | $2 / $10 | $4 | 1M | $2 on Google Gemini API (flex) | · | Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. |
OpenAI · 1.05MCheapest: $1 on OpenAI (flex) | $1 | $5 | $1 / $5 | $2 | 1.05M | $1 on OpenAI (flex) | · | GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. |
Google · 1MCheapest: $0.75 on Google Gemini API (flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Gemini API (flex) | · | Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. |
About Claude Haiku 4.5
Takes text, image, files in and returns text. First listed Oct 20, 2025. Up to 64K output tokens. Blended price $2 per 1M tokens at 3 input to 1 output. Model id claude-haiku-4-5.
Price history
List price since Oct 20, 2025, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
Questions
How much does Claude Haiku 4.5 cost?
$1 per million input tokens and $5 per million output tokens, with cached input at $0.1, or $0.5 and $2.5 through the Batch API.
What is the context window of Claude Haiku 4.5?
200K tokens, with up to 64K tokens of output.
Where is Claude Haiku 4.5 cheapest?
Of 10 routes tracked, AWS Bedrock is cheapest at $1 input and $5 output per million tokens.