Ways to buy 10
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 Anthropic APIThe 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 |
 Azure AI Foundryglobal · cached $0.1 | $1 | $5 | $1 / $5Same as list | $0.1 | Same as list |
 Databricks Mosaic AI Gateway + Foundation Model APIsFrom the platform pricing page | $1 | $5 | $1 / $5Same as list | n/a | Same as list |
 Google Vertex AIglobal · 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 |
| Google Vertex AI europe · cached $0.11 | $1.1 | $5.5 | $1.1 / $5.5+10% vs list | $0.11 | +10% vs list |
| Google Vertex AI us-east5 · cached $0.11 | $1.1 | $5.5 | $1.1 / $5.5+10% vs list | $0.11 | +10% vs list |
 Snowflake Cortex AI (AI_COMPLETE)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%
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 | ||||||
|---|---|---|---|---|---|---|---|
| Claude Opus 5.5 Anthropic · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · |
| Claude Fable 5.1 Anthropic · 1M | $10 | $50 | $10 / $50 | $20 | 1M | Lab list price | · |
| Claude Opus 5 Anthropic · 1M | $5 | $25 | $5 / $25 | $10 | 1M | Lab list price | · |
| Claude Sonnet 5 Anthropic · 1M | $2 | $10 | $2 / $10 | $4 | 1M | Lab list price | · |
 GPT-5.6 SolOpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
 Muse Spark 1.3Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
 Gemini 3.8 FlashGoogle · 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) | · |
| Muse Spark 1.1 Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
About Claude Haiku 4.5
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.
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. Overall score 3 on leadersboard.fru.dev (rank 40). 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.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.