Both APIs bill per 1M tokens, but each counts tokens with its own tokenizer, so the same text is a different number of tokens at each. Equal rates don't mean an equal bill, and lower rates don't mean a lower one. To compare, count one of your own prompts with each vendor's token counter and multiply by the rates below.
Claude API
“Claude 4.7 and later models and Claude Mythos Preview use a newer tokenizer that produces approximately 30 percent more tokens for the same text than earlier models.”
Claude Haiku 5.5 (prompts up to 100K tokens) (Claude API) and gpt-6-luna (OpenAI API): $0.10 input, $0.50 output per 1M tokens.
Claude Sonnet 5.5 (Claude API) and gpt-6.1-sol (OpenAI API): $2.00 input, $10.00 output per 1M tokens.
Claude Fable 5.1 (Claude API) and gpt-6-astra (OpenAI API): $10.00 input, $50.00 output per 1M tokens.
Matched on input and output rates; cache rates are in the table below.
Every model, by input rate
Claude API and OpenAI API list prices per 1M tokens, by model
Model
API
Input
Cache read / Cached input
Cache write
Output
Claude Haiku 5.5Prompts up to 100K tokens
Claude API
$0.10
$0.01
$0.125 (5 min)$0.20 (1 h)
$0.50
gpt-6-luna
OpenAI API
$0.10
$0.01
$0.125 (30 min)$0.25 (12 h)
$0.50
Claude Haiku 5.5Prompts over 100K tokens
Claude API
$0.50
$0.05
$0.625 (5 min)$1.00 (1 h)
$2.50
Claude Sonnet 5.5
Claude API
$2.00
$0.10
$2.50 (5 min)$4.00 (1 h)
$10.00
gpt-6.1-sol
OpenAI API
$2.00
$0.10
$2.50 (30 min)$5.00 (12 h)
$10.00
Claude Opus 5.5
Claude API
$4.00
$0.20
$5.00 (5 min)$8.00 (1 h)
$20.00
Claude Fable 5.1
Claude API
$10.00
$0.25
$12.50 (5 min)$20.00 (1 h)
$50.00
gpt-6-astra
OpenAI API
$10.00
$1.00
$12.50 (30 min)$25.00 (12 h)
$50.00
USD per 1M tokens. Claude API: Standard processing. OpenAI API: Standard processing, prompts up to 272K input tokens. Cache write is the price of storing input in the prompt cache for the stated lifetime.
No subscription: you prepay credits, which expire 1 year after purchase and aren't refundable. Invoiced billing needs a sales agreement.
Usage tiers set monthly spend caps (Start $500, Build $1,000, Scale $200,000). Reaching the cap pauses the API until the 1st of the next month.
Extended thinking tokens bill as output tokens.
Batch processing costs 50% less than the rates shown. Opus fast mode costs $8 input / $40 output per 1M tokens, and US-only inference costs 1.1× the standard rates.
Once a Claude Haiku 5.5 prompt passes 100K tokens (cache reads and writes count), every token in that request bills at the higher long-prompt rates in the table.
Tool fees: web search $10 per 1k searches; web fetch costs only its tokens; code execution includes 1,550 free hours a month, then $0.05 per hour.
OpenAI API
No subscription: you prepay credits ($5 minimum, $10 by default). Auto-reload is on by default, and credits expire after 1 year with no refund.
Usage tiers are spend caps, not plans. They rise with the credits you have bought: $500/mo after $5, $5,000/mo after $100 and $200,000/mo after $500.
Reasoning tokens bill as output tokens.
Batch and Flex processing cost 50% less than the rates shown; Fast processing costs twice as much.
Regional data residency adds 10% for models released on or after March 5, 2026.
Prompts over 272K input tokens bill at higher long-context rates, which this page doesn't list.
Built-in tools bill on top of tokens: web search $10 per 1k calls; file search $2.50 per 1k calls, plus $0.10 per GB per day of storage after the first 1 GB.
Claude API vs OpenAI API pricing FAQ
Is the Claude API or the OpenAI API cheaper?
List prices alone can't tell you. Both APIs bill per 1M tokens, but each counts tokens with its own tokenizer, so the same text is a different number of tokens at each. These models charge the same list rates per token: Claude Haiku 5.5 (prompts up to 100K tokens) and gpt-6-luna ($0.10 input, $0.50 output per 1M tokens); Claude Sonnet 5.5 and gpt-6.1-sol ($2.00 input, $10.00 output per 1M tokens); Claude Fable 5.1 and gpt-6-astra ($10.00 input, $50.00 output per 1M tokens). To compare, count one of your own prompts with each vendor's token counter and multiply by its rates.
How much does the Claude API cost per token?
Claude API has no plan or monthly fee. It bills per 1M tokens, by model: Claude Fable 5.1: $10.00 input, $50.00 output; Claude Opus 5.5: $4.00 input, $20.00 output; Claude Sonnet 5.5: $2.00 input, $10.00 output; Claude Haiku 5.5 (prompts up to 100K tokens): $0.10 input, $0.50 output; Claude Haiku 5.5 (prompts over 100K tokens): $0.50 input, $2.50 output. Standard processing.
How much does the OpenAI API cost per token?
OpenAI API has no plan or monthly fee. It bills per 1M tokens, by model: gpt-6-astra: $10.00 input, $50.00 output; gpt-6.1-sol: $2.00 input, $10.00 output; gpt-6-luna: $0.10 input, $0.50 output. Standard processing, prompts up to 272K input tokens.
How do the Claude API and the OpenAI API count tokens?
Claude API: "Claude 4.7 and later models and Claude Mythos Preview use a newer tokenizer that produces approximately 30 percent more tokens for the same text than earlier models." OpenAI API: "The same text can produce different token counts depending on the model, its encoding, and the language." Each vendor's token counter shows how many tokens your own text uses.