Claude API pricing (Anthropic)
As of October 28, 2026, the Claude API costs $0.1 to $10 per million input tokens and $0.5 to $50 per million output tokens, across 16 Claude models. Claude Haiku 5.5 costs $0.1 input and $0.5 output; Claude Sonnet 5.5 costs $2 input and $10 output; Claude Opus 5.5 costs $4 input and $20 output; Claude Fable 5.1 costs $10 input and $50 output; Claude Mythos 5.1 costs $10 input and $50 output. A typical request of 1,000 input and 500 output tokens costs $0.00035 on Claude Haiku 5.5 and $0.035 on Claude Mythos 5.1.
Claude API price per 1M tokens, every model
| Model | Input | Cached input | Cache write | Output | Batch input | Batch output | Context | Typical request |
|---|---|---|---|---|---|---|---|---|
Claude Haiku 5.5claude-haiku-5-5 | $0.1 | $0.01 | $0.125 | $0.5 | $0.05 | $0.25 | 1M | $0.00035 |
Claude Haiku 4.5claude-haiku-4-5 | $1 | $0.1 | $1.25 | $5 | $0.5 | $2.5 | 200K | $0.0035 |
Claude Sonnet 5claude-sonnet-5 | $2 | $0.2 | $2.5 | $10 | $1 | $5 | 1M | $0.007 |
Claude Sonnet 5.5claude-sonnet-5-5 | $2 | $0.1 | $2.5 | $10 | $1 | $5 | 1M | $0.007 |
Claude Sonnet 4.5claude-sonnet-4-5 | $3 | $0.3 | $3.75 | $15 | $1.5 | $7.5 | 200K | $0.0105 |
Claude Sonnet 4.6claude-sonnet-4-6 | $3 | $0.3 | $3.75 | $15 | $1.5 | $7.5 | 1M | $0.0105 |
Claude Opus 5.5claude-opus-5-5 | $4 | $0.2 | $5 | $20 | $2 | $10 | 1M | $0.014 |
Claude Opus 4.5claude-opus-4-5 | $5 | $0.5 | $6.25 | $25 | $2.5 | $12.5 | 200K | $0.0175 |
Claude Opus 4.6claude-opus-4-6 | $5 | $0.5 | $6.25 | $25 | $2.5 | $12.5 | 1M | $0.0175 |
Claude Opus 4.7claude-opus-4-7 | $5 | $0.5 | $6.25 | $25 | $2.5 | $12.5 | 1M | $0.0175 |
Claude Opus 4.8claude-opus-4-8 | $5 | $0.5 | $6.25 | $25 | $2.5 | $12.5 | 1M | $0.0175 |
Claude Opus 5claude-opus-5 | $5 | $0.5 | $6.25 | $25 | $2.5 | $12.5 | 1M | $0.0175 |
Claude Fable 5claude-fable-5 | $10 | $1 | $12.5 | $50 | $5 | $25 | 1M | $0.035 |
Claude Fable 5.1claude-fable-5-1 | $10 | $0.25 | $12.5 | $50 | $5 | $25 | 1M | $0.035 |
Claude Mythos 5claude-mythos-5 | $10 | $1 | $12.5 | $50 | $5 | $25 | 1M | $0.035 |
Claude Mythos 5.1claude-mythos-5-1 | $10 | $0.25 | $12.5 | $50 | $5 | $25 | 1M | $0.035 |
US dollars per million tokens, sorted by the cost of a typical request of 1,000 input and 500 output tokens. Cache write is the standard (5-minute) cache.
Calculate the cost of your own prompt →How much does a Claude API request cost?
A typical request of 1,000 input and 500 output tokens costs $0.00035 on Claude Haiku 5.5, $0.007 on Claude Sonnet 5.5, $0.014 on Claude Opus 5.5, $0.035 on Claude Fable 5.1 and $0.035 on Claude Mythos 5.1. A coding agent step with 50K tokens of context and 2K output tokens costs $0.60 on Claude Mythos 5.1.
| Model | Short chat message 300 in, 200 out | Typical request 1K in, 500 out | Long document summary 20K in, 1K out | Coding agent step 50K in, 2K out | 1,000 typical requests |
|---|---|---|---|---|---|
| Claude Haiku 5.5 | $0.00013 | $0.00035 | $0.0025 | $0.006 | $0.35 |
| Claude Sonnet 5.5 | $0.0026 | $0.007 | $0.05 | $0.12 | $7.00 |
| Claude Opus 5.5 | $0.0052 | $0.014 | $0.10 | $0.24 | $14.00 |
| Claude Fable 5.1 | $0.013 | $0.035 | $0.25 | $0.60 | $35.00 |
| Claude Mythos 5.1 | $0.013 | $0.035 | $0.25 | $0.60 | $35.00 |
At standard rates, for the newest model of each Claude family. 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 batch, prompt caching and long context change the price
Batch API. All 16 priced Claude models have a batch API price. Requests sent as a batch are processed within 24 hours and cost 50% less: Claude Mythos 5.1 drops from $10 input and $50 output to $5 and $25 per million tokens. See batch API pricing.
Prompt caching. All 16 priced Claude models charge less for cached input, the part of a prompt that repeats across requests: typically 90% less. Claude Mythos 5.1 charges $0.25 per million cached input tokens instead of $10. Writing a prompt to the cache costs extra: 1.25× the input price for the standard cache and 2× for the 1-hour cache (Claude Mythos 5.1: $12.5 and $20 per million tokens). The write pays for itself on the first request that reads the cache. See prompt caching pricing.
Long context. Claude models accept 200K to 1M input tokens. Long prompts cost more on one model: Claude Haiku 5.5 charges $0.5 input and $2.5 output per million tokens once a prompt is over 100K tokens, instead of $0.1 input and $0.5 output. A 200K-token prompt with 2K output tokens on Claude Haiku 5.5 costs $0.11, against $0.021 at the standard rate. The other 15 models list one price for their whole context window.
Claude API vs OpenAI and Gemini
It depends on the model. The cheapest Claude model, Claude Haiku 5.5, costs $0.00035 per typical request; the cheapest OpenAI model, GPT-5 nano, costs $0.00025. Claude Mythos 5.1 ($0.035) is closest in price to GPT-6 Astra ($0.035): about the same.
| Claude model | Input / output | Typical request | Closest OpenAI model | Closest Gemini model |
|---|---|---|---|---|
| Claude Haiku 5.5 | $0.1 / $0.5 | $0.00035 | GPT-6 Luna $0.1 / $0.5 · $0.00035 · about the same | Gemini 2.5 Flash Lite $0.1 / $0.4 · $0.0003 · 1.2× cheaper |
| Claude Sonnet 5.5 | $2 / $10 | $0.007 | GPT-6 Sol $2 / $10 · $0.007 · about the same | Gemini 4 Argon $2 / $10 · $0.007 · about the same |
| Claude Opus 5.5 | $4 / $20 | $0.014 | GPT-5.6 $4 / $20 · $0.014 · about the same | Gemini 3.1 Pro Preview $2 / $12 · $0.008 · 1.8× cheaper |
| Claude Fable 5.1 | $10 / $50 | $0.035 | GPT-6 Astra $10 / $50 · $0.035 · about the same | Gemini 3.1 Pro Preview $2 / $12 · $0.008 · 4.4× cheaper |
| Claude Mythos 5.1 | $10 / $50 | $0.035 | GPT-6 Astra $10 / $50 · $0.035 · about the same | Gemini 3.1 Pro Preview $2 / $12 · $0.008 · 4.4× cheaper |
For each Claude model, the model from the other provider whose typical request costs the nearest, with its input / output price per million tokens, its typical request, and how that compares with the Claude model.
Questions and answers
How much does the Claude API cost?
As of October 28, 2026, the Claude API costs $0.1 to $10 per million input tokens and $0.5 to $50 per million output tokens, across 16 Claude models. Claude Haiku 5.5 costs $0.1 input and $0.5 output; Claude Sonnet 5.5 costs $2 input and $10 output; Claude Opus 5.5 costs $4 input and $20 output; Claude Fable 5.1 costs $10 input and $50 output; Claude Mythos 5.1 costs $10 input and $50 output. A typical request of 1,000 input and 500 output tokens costs $0.00035 on Claude Haiku 5.5 and $0.035 on Claude Mythos 5.1.
What is the cheapest Claude model?
Claude Haiku 5.5 (claude-haiku-5-5), at $0.1 per million input tokens and $0.5 per million output tokens.
How much does a Claude API request cost?
A typical request of 1,000 input and 500 output tokens costs $0.00035 on Claude Haiku 5.5, $0.007 on Claude Sonnet 5.5, $0.014 on Claude Opus 5.5, $0.035 on Claude Fable 5.1 and $0.035 on Claude Mythos 5.1. A coding agent step with 50K tokens of context and 2K output tokens costs $0.60 on Claude Mythos 5.1.
Is the Claude batch API cheaper?
Yes. All 16 priced Claude models have a batch API price. Requests sent as a batch are processed within 24 hours and cost 50% less: Claude Mythos 5.1 drops from $10 input and $50 output to $5 and $25 per million tokens.
How much does prompt caching save on the Claude API?
All 16 priced Claude models charge less for cached input, the part of a prompt that repeats across requests: typically 90% less. Claude Mythos 5.1 charges $0.25 per million cached input tokens instead of $10. Writing a prompt to the cache costs extra: 1.25× the input price for the standard cache and 2× for the 1-hour cache (Claude Mythos 5.1: $12.5 and $20 per million tokens). The write pays for itself on the first request that reads the cache.
Does long context cost more on the Claude API?
Yes, on some models. Claude models accept 200K to 1M input tokens. Long prompts cost more on one model: Claude Haiku 5.5 charges $0.5 input and $2.5 output per million tokens once a prompt is over 100K tokens, instead of $0.1 input and $0.5 output. A 200K-token prompt with 2K output tokens on Claude Haiku 5.5 costs $0.11, against $0.021 at the standard rate. The other 15 models list one price for their whole context window.
Is the Claude API cheaper than OpenAI?
It depends on the model. The cheapest Claude model, Claude Haiku 5.5, costs $0.00035 per typical request; the cheapest OpenAI model, GPT-5 nano, costs $0.00025. Claude Mythos 5.1 ($0.035) is closest in price to GPT-6 Astra ($0.035): about the same.
Is the Claude API included in a Claude Pro or Max subscription?
No. Claude Pro and Max cover the Claude apps. The Claude API is billed separately, pay as you go per token, through the Claude Console at the prices on this page.
Source: Anthropic pricing, via the LiteLLM price list.