Anthropic · Claude · Flagship
Anthropic's model for long-running agent workflows, front-end code, analysis and knowledge work.
30% below the market rate.
Added here 18 Oct 2026 — read the changelog for what changed and why.
Output is 5× the input rate. $1 covers about 40 prompts of 1,000 input + 500 output tokens. 1 credit = $1 of usage. All rates
Set ONEAIAPIKEY_API_KEY to a key from your console, then run any example. Streaming is on so long answers are not cut off by idle-connection timeouts.
curl https://api.oneaiapikey.com/v1/chat/completions \
-H "Authorization: Bearer $ONEAIAPIKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-fable-5-1",
"stream": true,
"messages": [{"role": "user", "content": "Add rate limiting to the login route, update the tests and run them."}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.oneaiapikey.com/v1",
api_key=os.environ["ONEAIAPIKEY_API_KEY"],
)
stream = client.chat.completions.create(
model="claude-fable-5-1",
messages=[{"role": "user", "content": "Add rate limiting to the login route, update the tests and run them."}],
stream=True, # recommended for long outputs
)
for chunk in stream:
if chunk.choices and chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.oneaiapikey.com/v1",
apiKey: process.env.ONEAIAPIKEY_API_KEY,
});
const stream = await client.chat.completions.create({
model: "claude-fable-5-1",
messages: [{ role: "user", content: "Add rate limiting to the login route, update the tests and run them." }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}More: quickstart · API reference · try it in Chat first
Scores for Claude Fable 5.1 as its maker published them, with the setting they state. We have not re-run them. Versions and settings differ between vendors, so compare only identical benchmark names; compare models side by side.
Last 7 days, UTC days
Hover, tap or drag across any day, or focus the chart and use the arrow keys, to see how every model did that day.
Real tokens served through this gateway, updated every 5 minutes. Ranked by usage, not quality.
Full ranking insightsClaude line-up
Of the 9 Claude models on this site, Claude Fable 5.1 (free lane) is the step up from Claude Fable 5.1 and Claude Opus 5.5 (free lane) the step down. Each comparison lists the published rates and limits, then what favours each side.
| Per 1M tokens | Claude Fable 5.1 | Claude Fable 5.1 (free lane) |
|---|---|---|
| Input | $7the same | $7 |
| Output | $35the same | $35 |
| Context | 1Mthe same | 1M |
| Max output | 128kthe same | 128k |
Nothing in the published data puts it ahead of Claude Fable 5.1.
| Per 1M tokens | Claude Fable 5.1 | Claude Opus 5.5 (free lane) |
|---|---|---|
| Input | $72.5× as much | $2.80 |
| Output | $352.5× as much | $14 |
| Context | 1Mthe same | 1M |
| Max output | 128kthe same | 128k |
Use cases
The catalogue lists Claude Fable 5.1 for long agent runs, front-end code and analysis. Each row prices one typical request at the published rates, with the arithmetic shown. The market-rate figure shows the same request at the lowest public price elsewhere. Token counts are examples; your prompts will differ.
One turn of a long agent session: 60,000 tokens of context, 50,000 of them cached from the previous turn, and 3,000 tokens of edits and tool calls back.
“Add rate limiting to the login route, update the tests and run them.”
Same request on Claude Fable 5.1 (free lane) $0.525 and Claude Opus 5.5 (free lane) $0.21. Cheapest flagship-tier model in the family: Claude Opus 5.5 at $0.08, 57% less.
$0.1875
per agent turn, about 53 per $10
$0.2625 at the market rate
0.01 × $7 + 0.05 × $0.25 + 0.003 × $35
A UI component from a description: 6,000 tokens of existing components and styles in, 2,500 tokens of markup and code out.
“Build a responsive pricing table component in React with a monthly and yearly toggle.”
Same request on Claude Fable 5.1 (free lane) $0.1295 and Claude Opus 5.5 (free lane) $0.0518. Cheapest flagship-tier model in the family: Claude Opus 5.5 at $0.0518, 60% less.
$0.1295
per component, about 77 per $10
$0.185 at the market rate
0.006 × $7 + 0.0025 × $35
A hard question with its supporting material: 8,000 tokens in, 4,000 tokens out including the reasoning.
“Given these three incident timelines, find the shared root cause and the evidence for it.”
Same request on Claude Fable 5.1 (free lane) $0.196 and Claude Opus 5.5 (free lane) $0.0784. Cheapest flagship-tier model in the family: Claude Opus 5.5 at $0.0784, 60% less.
$0.196
per answer, about 51 per $10
$0.28 at the market rate
0.008 × $7 + 0.004 × $35
Overview
Claude Fable 5.1 is a flagship model from Anthropic, available here under the exact model id “claude-fable-5-1”. In the Claude line-up here it sits between Claude Fable 5.1 (free lane) and Claude Opus 5.5 (free lane). Anthropic has not published a release date we can cite; it has been available here since 18 Oct 2026.
Anthropic documents tools, vision, reasoning, structured output and prompt caching for it, and it reads images as well as text.
It costs $7 per million input tokens and $35 per million output tokens, so output is 5× the input rate. That is 30% below the market rate of $10 input and $50 output per million tokens, the lowest public price we found at other API gateways. On the use cases below, output makes up 56% of the bill for long agent runs, 68% for front-end code and 71% for analysis, so capping max tokens and asking for diffs saves more than trimming the prompt. With a 3:1 input-to-output mix it is the highest-priced of the 27 models on this site, so use it where it clearly earns that.
Cached input bills at $0.25 per million tokens, 96% below the standard input rate. In the long agent runs example, 50k of the 60k input tokens come from cache, which brings one agent turn from $0.525 down to $0.1875.
It is served through the OpenAI-compatible format at https://api.oneaiapikey.com/v1, so any SDK or tool that lets you set a custom base URL, for example Codex CLI, Cursor and Cline, can use it. It is not offered on the Anthropic Messages endpoint; pick an Anthropic-format model for Claude Code.
Similar models
Same key, same balance. Switching is a change to the model field.
Claude Fable 5.1 is a paid model: any balance above $0 pays for it, the $10.00 sign-up credit included. When it runs out, add $1 or more to your wallet. Every request is billed at the rates above, with a receipt in your usage log.
Claude Fable 5.1 is developed by Anthropic. Model names and trademarks belong to their owners. One AI API Key is an independent API gateway and is not affiliated with, endorsed by or sponsored by Anthropic.