BroadRouter

Claude Haiku 4.5 API pricing

Updated

Among the 5 providers we checked (prices read 2026-11-14), 4 tie for the lowest blended standard price for Claude Haiku 4.5; Anthropic charges USD 1 per 1M input tokens and USD 5 per 1M output tokens. The median across 5 standard prices is USD 1 / USD 5. That is Anthropic's own API. Each price is read from the provider's own pricing page.

Anthropic · slug claude-haiku-4.5 · up to 200,000 tokens of context · 5 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-14. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2025-11-19 (13 archived price points, 0 list-price changes): LLM API price history.

What does Anthropic charge for Claude Haiku 4.5?

Input
USD 1
Cached input
USD 0.10
Output
USD 5
Blended 3:1
USD 2

USD per 1M tokens on Anthropic, model Claude Haiku 4.5, standard tier. Source, checked 2026-11-14.

Other Anthropic tiers: batch USD 0.50 / USD 2.50.

Is a host cheaper than Anthropic? They tie. DeepInfra and Anthropic's own API both work out at USD 2 per 1M tokens on the 3:1 blend.

Claude Haiku 4.5 price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 10% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Claude Haiku 4.5 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Anthropic tied cheapest maker
Claude Haiku 4.5
Notes and source quote
“| Claude Haiku 4.5 | $1 / MTok | $1.25 / MTok | $2 / MTok | $0.10 / MTok | $5 / MTok |”
USD 1USD 0.10USD 5USD 2not statednot statedAnthropic page
checked 2026-11-14
re-checked 2026-11-16
2DeepInfra tied cheapest
anthropic/claude-haiku-4-5
Notes and source quote
“$1.00 in $5.00 out / 1M tokens”
USD 1not publishedUSD 5USD 2200,000not statedDeepInfra page
checked 2026-11-14
re-checked 2026-11-16
3DigitalOcean tied cheapest
Notes and source quote
“Claude Haiku 4.5 — Processing modePrompt lengthInputOutputCache write (5m)Cache write (1h)Cache read: Standard All prompts$1.00$5.00$1.25$2.00$0.10”
USD 1USD 0.10USD 5USD 2not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
4Google Vertex AI tied cheapest
claude-haiku-4.5
Notes and source quote

Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately.

“Claude Haiku 4.5 Input $1.00 … Output $5.00 … Cache Hit $0.10”
USD 1USD 0.10USD 5USD 2not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
5Amazon Bedrock
Notes and source quote

Geo / in-region (US) on-demand price for us-east-1 from the "Geo and In-region Cross-region Inference" table. Global cross-region inference is cheaper: input $1.00, output $5.00 per 1M tokens. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1).

“Claude 4.5 Haiku $1.10 $5.50 $0.55 $2.75 $1.375 $2.20 $0.11”
USD 1.10USD 0.11USD 5.50USD 2.20not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16
—Anthropic maker batch
Claude Haiku 4.5
Notes and source quote

Message Batches API.

“| Claude Haiku 4.5 | $0.50 / MTok | $2.50 / MTok |”
USD 0.50not publishedUSD 2.50USD 1not statednot statedAnthropic page
checked 2026-11-14
re-checked 2026-11-16
—Google Vertex AI batch
claude-haiku-4.5
Notes and source quote

Global endpoint, prompts under 200K tokens; at 200K tokens or more, the whole request bills at long-context rates. Regional endpoints are priced separately.

“Claude Haiku 4.5 Batch Input $0.50 … Batch Output $2.50 … Batch Cache Hit $0.05”
USD 0.50USD 0.05USD 2.50USD 1not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
—Amazon Bedrock batch
Notes and source quote

Batch columns of the Geo/in-region table. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1).

“Claude 4.5 Haiku $1.10 $5.50 $0.55 $2.75 $1.375 $2.20 $0.11”
USD 0.55not publishedUSD 2.75USD 1.10not statednot statedAmazon Bedrock page
checked 2026-11-14
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Claude Haiku 4.5 cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Claude Haiku 4.5, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
Anthropic (maker)USD 131.40USD 250.20USD 873.00
DeepInfraUSD 180.00USD 315.00USD 2,250
DigitalOceanUSD 131.40USD 250.20USD 873.00
Google Vertex AIUSD 131.40USD 250.20USD 873.00
Amazon BedrockUSD 144.54USD 275.22USD 960.30

For the support chatbot, the cheapest price (Anthropic and 2 others, tied, USD 131.40 a month) saves USD 0 against the median (USD 131.40). For the coding agent the gap is USD 0 a month.

Which Claude Haiku 4.5 provider is cheapest for your traffic?

Anthropic, DeepInfra, DigitalOcean and Google Vertex AI share the lowest input price (USD 1) and the lowest output price (USD 5), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.

Claude Haiku 4.5: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
Anthropic (maker)USD 2 cheapestUSD 1.663 cheapestUSD 1.393 cheapest
DeepInfra (no cache price)USD 2 cheapestUSD 2USD 2
DigitalOceanUSD 2 cheapestUSD 1.663 cheapestUSD 1.393 cheapest
Google Vertex AIUSD 2 cheapestUSD 1.663 cheapestUSD 1.393 cheapest
Amazon BedrockUSD 2.20USD 1.829USD 1.532

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

4 of 5 providers publish a cached-input price below the input price: Anthropic (90% off), DigitalOcean (90% off), Google Vertex AI (90% off), Amazon Bedrock (90% off). DeepInfra publishes none, so cached tokens there bill at the input price.

DeepInfra states a context window of 200,000 tokens; Anthropic, DigitalOcean, Google Vertex AI and Amazon Bedrock do not state one.

Estimate your own bill

The Anthropic models whose cheapest standard price is closest to Claude Haiku 4.5's (USD 2 blended):

Anthropic models priced closest to Claude Haiku 4.5
ModelCheapest inputCheapest outputMax contextProviders
Claude Sonnet 5USD 2USD 101,000,0005
Claude Sonnet 5.5USD 2USD 101,000,0006
Claude Sonnet 4.5USD 3USD 15—4
Claude Sonnet 4.6USD 3USD 151,000,0005
Claude Opus 5.5USD 4USD 201,000,0006
Claude Opus 4.5USD 5USD 25—4

Priced closest from other makers: GPT-6.1 Terra (OpenAI, USD 2) · Muse Spark Open (Meta, USD 2) · Qwen3.7 Max (Qwen, USD 1.875).

Compare Claude Haiku 4.5 with

Also compared: vs Claude Haiku 5.5.

Every Claude Haiku 4.5 price comparison · All model-vs-model price comparisons

All 429 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Claude Haiku 4.5 API cost per token?

From USD 1 per 1M input tokens (USD 0.000001 per token) and USD 5 per 1M output tokens (USD 0.000005 per token) at the lowest standard prices we found. The median of 5 standard prices is USD 1 input and USD 5 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Claude Haiku 4.5?

Among the 5 providers we checked (prices read 2026-11-14), 4 are tied for the lowest price: Anthropic, DeepInfra, DigitalOcean and Google Vertex AI, each USD 2 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 1 (Anthropic and 3 others, tied); for output alone, USD 5 (Anthropic and 3 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is Claude Haiku 4.5 cheaper from a host than from Anthropic?

They tie. DeepInfra and Anthropic's own API both work out at USD 2 per 1M tokens on the 3:1 blend.

Does Claude Haiku 4.5 have cached input pricing?

4 of 5 standard prices include one. The lowest is USD 0.10 per 1M at Anthropic; the median is USD 0.10. Providers without one bill cached input at the input price. What cached input means.

What is the Claude Haiku 4.5 context window?

200,000 tokens on every provider that states it.

How much does a coding agent cost per month on Claude Haiku 4.5?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 873.00 a month at Anthropic, USD 873.00 at the median price and USD 2,250 at DeepInfra. Try your own numbers.

Is there a batch, flex or priority price for Claude Haiku 4.5?

Yes: batch from Anthropic at USD 0.50 / USD 2.50 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

Is Claude Haiku 4.5 free to use through an API?

No provider in our data lists a free price for Claude Haiku 4.5 as of 2026-11-14. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity