Claude Haiku 4.5 API pricing
Anthropic charges $1 per million input tokens and $5 per million output tokens for Claude Haiku 4.5 (claude-haiku-4-5), and $0.1 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.0035, or $0.00175 through the batch API.
Claude Haiku 4.5 price per million tokens
| Token type | Standard | Batch API |
|---|---|---|
| Input | $1 | $0.5 |
| Cached input | $0.1 | $0.05 |
| Output | $5 | $2.5 |
API model id: claude-haiku-4-5. Claude Haiku 4.5 supports a 200K-token context window, up to 64K output tokens, image input, tool calling and reasoning.
What Claude Haiku 4.5 costs per request
| Request | 1 request | 1,000 requests | 1M requests |
|---|---|---|---|
| Short chat message (300 in, 200 out) | $0.0013 | $1.30 | $1,300.00 |
| Typical request (1K in, 500 out) | $0.0035 | $3.50 | $3,500.00 |
| Long document summary (20K in, 1K out) | $0.025 | $25.00 | $25,000.00 |
| Coding agent step (50K in, 2K out) | $0.06 | $60.00 | $60,000.00 |
At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. Anthropic counts tokens with its own tokenizer, so the same text can be a different number of tokens.
How Claude Haiku 4.5 compares
- For a typical request, Claude Haiku 4.5 is cheaper than 49% of the other models on apicost.app.
- GPT-6.1 Terra from OpenAI costs $1 input and $5 output per million tokens, so a typical request is $0.0035: about the same price as Claude Haiku 4.5.
- Gemini 3.6 Flash from Google Gemini costs $0.75 input and $3.75 output per million tokens, so a typical request is $0.00263: 1.3× cheaper than Claude Haiku 4.5.
- DeepSeek V4 Pro from DeepSeek costs $1.32 input and $3.96 output per million tokens, so a typical request is $0.0033: about the same price as Claude Haiku 4.5.
Claude Haiku 4.5 price history
Claude Haiku 4.5 has cost $1 per million input tokens and $5 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Every LLM API price increase, cut, new and retired model, dated: LLM API price changes.
Models with a similar price
| Model | Provider | Input / 1M | Cached input / 1M | Output / 1M | Typical request |
|---|---|---|---|---|---|
| Grok 4.3 | xAI | $1.25 | $0.2 | $2.5 | $0.0025 |
| Grok 4.20 | xAI | $1.25 | $0.2 | $2.5 | $0.0025 |
| Gemini 3.6 Flash | Google Gemini | $0.75 | $0.075 | $3.75 | $0.00263 |
| Gemini 3.7 Flash | Google Gemini | $0.75 | $0.075 | $3.75 | $0.00263 |
| Gemini 3.8 Flash | Google Gemini | $0.75 | $0.075 | $3.75 | $0.00263 |
| GPT-5.4 mini | OpenAI | $0.75 | $0.075 | $4.5 | $0.003 |
| DeepSeek V4 Pro | DeepSeek | $1.32 | $0.044 | $3.96 | $0.0033 |
| GPT-6.1 Terra | OpenAI | $1 | $0.05 | $5 | $0.0035 |
Other Anthropic models
- Claude Fable 5 $10 / $50
- Claude Fable 5.1 $10 / $50
- Claude Fable 5.2 $8 / $40
- Claude Haiku 5.5 $0.1 / $0.5
- Claude Mythos 5 $10 / $50
- Claude Mythos 5.1 $10 / $50
- Claude Mythos 5.2 $8 / $40
- Claude Opus 4.5 $5 / $25
- Claude Opus 4.6 $5 / $25
- Claude Opus 4.7 $5 / $25
- Claude Opus 4.8 $5 / $25
- Claude Opus 5 $5 / $25
- Claude Opus 5.5 $4 / $20
- Claude Sonnet 4.5 $3 / $15
- Claude Sonnet 4.6 $3 / $15
- Claude Sonnet 5 $2 / $10
- Claude Sonnet 5.5 $2 / $10
Every Anthropic model side by side, with batch, caching and long-context prices: Claude API pricing (Anthropic). Ways to pay less: batch API, prompt caching, the cheapest models.
Questions and answers
How much does the Claude Haiku 4.5 API cost?
Anthropic charges $1 per million input tokens and $5 per million output tokens for Claude Haiku 4.5 (claude-haiku-4-5), and $0.1 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.0035, or $0.00175 through the batch API.
Has the Claude Haiku 4.5 API price changed?
No. Claude Haiku 4.5 has cost $1 per million input tokens and $5 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Is there a cheaper way to use Claude Haiku 4.5?
Yes. The Anthropic batch API runs requests within 24 hours for $0.5 per million input tokens and $2.5 per million output tokens. Prompt caching lowers the price of repeated input to $0.1 per million tokens.
What is the context window of Claude Haiku 4.5?
Claude Haiku 4.5 accepts up to 200,000 input tokens, roughly 150,000 words of English, and writes up to 64,000 output tokens per response. Filling the whole context window once costs $0.20 in input tokens.
Is Claude Haiku 4.5 cheaper than GPT-6.1 Terra?
They cost about the same. GPT-6.1 Terra from OpenAI costs $1 input and $5 output per million tokens, so a typical request is $0.0035: about the same price as Claude Haiku 4.5.
Source: Anthropic pricing, via the LiteLLM price list.