Claude API cost per request, October 2026: a chat turn and a long document
Input, cached and output prices for every Claude model, Anthropic's list price next to ours, and what a chat turn and a long-document request cost on Opus, Sonnet and Haiku.
How a Claude API request is billed
Claude API calls are billed per token, at three rates per million tokens: input, cached input and output. Output costs several times input on every Claude model, and cached input costs a fraction of it. There is no seat or plan price; a request costs its tokens times the rates of the model it named.
Claude per-token rates
12 Claude models, newest first. Each row shows our price and Anthropic's list price.
| Model | Input | Cached | Output | List input | List cached | List output |
|---|---|---|---|---|---|---|
| Claude Fable 5.1 | $6.00 | $0.15 | $30.00 | $10.00 | $0.25 | $50.00 |
| Claude Opus 5.5 | $2.10 | $0.12 | $6.00 | $4.00 | $0.20 | $20.00 |
| Claude Sonnet 5.5 | $1.20 | $0.075 | $3.00 | $2.00 | $0.10 | $10.00 |
| Claude Haiku 5.5 | $0.06 | $0.01 | $0.15 | $0.10 | $0.01 | $0.50 |
| Claude Fable 5 | $3.00 | $0.30 | $15.00 | $10.00 | $1.00 | $50.00 |
| Claude Opus 5 | $1.50 | $0.15 | $7.50 | $5.00 | $0.50 | $25.00 |
| Claude Sonnet 5 | $1.20 | $0.12 | $3.00 | $2.00 | $0.20 | $10.00 |
| Claude Opus 4.8 | $1.50 | $0.15 | $7.50 | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.7 | $1.50 | $0.15 | $7.50 | $5.00 | $0.50 | $25.00 |
| Claude Opus 4.6 | $1.50 | $0.15 | $7.50 | $5.00 | $0.50 | $25.00 |
| Claude Sonnet 4.6 | $1.80 | $0.09 | $9.00 | $3.00 | $0.30 | $15.00 |
| Claude Haiku 4.5 | $0.60 | $0.06 | $3.00 | $1.00 | $0.10 | $5.00 |
USD per million tokens. Ours from the live catalog; list is the price on Anthropic's pricing page, the read date on each model page.
The lowest price is Claude Haiku 5.5: $0.06 in and $0.15 out.
Claude API cost per request, worked
A chat turn of 2,000 input and 500 output tokens, and a long-document request of 50,000 input and 2,000 output. Both sizes are assumptions; nothing is counted at the cached rate.
| Model | Chat turn, list | Chat turn, here | Long document, list | Long document, here |
|---|---|---|---|---|
| Claude Opus 5.5 | $0.018 | $0.0072 | $0.24 | $0.117 |
| Claude Sonnet 5.5 | $0.009 | $0.0039 | $0.12 | $0.066 |
| Claude Haiku 5.5 | $0.0005 | $0.0002 | $0.006 | $0.0033 |
Input tokens times the input rate plus output tokens times the output rate, per million.
Claude Opus 5.5: $2.10 in and $6.00 out here, against $4.00 and $20.00 at list, 47% under on input and 70% on output.
Claude Sonnet 5.5: $1.20 in and $3.00 out here, against $2.00 and $10.00 at list, 40% under on input and 70% on output.
Claude Haiku 5.5: $0.06 in and $0.15 out here, against $0.10 and $0.50 at list, 40% under on input and 70% on output.
Claude API cost per month, worked
Two monthly workloads on the same models: 1,000 chat turns a day and 100 long documents a day, each for 30 days. Every request is the size above, so a month of chat is 60 million input and 15 million output tokens, and a month of documents is 150 million input and 6 million output. The volumes are assumptions; nothing is counted at the cached rate.
| Model | Chat month, list | Chat month, here | Document month, list | Document month, here |
|---|---|---|---|---|
| Claude Opus 5.5 | $540.00 | $216.00 | $720.00 | $351.00 |
| Claude Sonnet 5.5 | $270.00 | $117.00 | $360.00 | $198.00 |
| Claude Haiku 5.5 | $13.50 | $5.85 | $18.00 | $9.90 |
USD for 30 days: the per-request cost above times 30,000 chat turns or 3,000 documents.
Claude Opus 5.5: $567.00 a month here for both workloads, against $1,260.00 at list, $693.00 less.
Claude Sonnet 5.5: $315.00 a month here for both workloads, against $630.00 at list, $315.00 less.
Claude Haiku 5.5: $15.75 a month here for both workloads, against $31.50 at list, $15.75 less.
Cost scales with volume, so 10,000 chat turns a day is ten times the chat column.
What cached input does to the cost
When a request repeats a prefix the API has seen, such as a long system prompt or a document, the response reports those tokens as cached and they bill at the cached rate in the first table. A model with no cached rate bills them at its input rate.
Calling it
The Anthropic SDK takes a base URL and a key. Every Claude id in the table works with the same two values; the OpenAI SDKs work too.
from anthropic import Anthropic
client = Anthropic(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
message = client.messages.create(
model="claude-opus-5-5",
max_tokens=1024,
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(message.content[0].text)More in the SDK guide and the Claude Code guide.
Questions
Is there a subscription? No. Credit is prepaid from $10, and each top-up locks your prices for 30 days.
Which Claude model should I use? The cheapest one that does the task. Haiku for short, high-volume work and subagents, Sonnet for most coding and writing, Opus where the harder answer is worth the price. Run the same prompt on each and compare.
Where is the full price list? On the Claude API pricing page, and every other model on the Models page. To see what your own usage would cost, re-price an export on the savings page.