# Claude Fable 5.2

LiveAnthropic

`claude-fable-5-2`

Claude Fable 5.2 by Anthropic: 1M context, 128K max output, with Vision, File input, Function calling, Structured output, Streaming, Reasoning, Code execution, Web search. On Hostlinku: Performance starts at $4.34/1M input · Economy starts at $1.38/1M input.

[Get started](https://hostlinku.com/register)[Try in Playground](https://hostlinku.com/dashboard/playground?model=claude-fable-5-2)

Input

4.34

/ 1M token

$8original

Output

21.7

/ 1M token

$40original

Cache read

per 1M token

$0.1085

$0.20

Cache write (5m)

per 1M token

$5.42

$10

Cache write (1h)

per 1M token

$8.68

$16

Web search

per 1K calls

$5.42

$10

[Get started](https://hostlinku.com/register)

Context window

1.0M

1,000,000 tokens

Max output

128.0K

128,000 tokens

7-day uptime

99.93%

4,287 requests · 3 failed

Measured throughput

229.8 tok/s

Real traffic, last 7 days · output side · 2.60s avg

## Capabilities

What this model can do through the Hostlinku gateway.

7 of 15 supported

Vision

Reads images, screenshots, and diagrams alongside text. Send image inputs directly in the messages payload.

Function calling

The model calls tools you define and folds their results into the reply. Required for agentic workflows and multi-step automation.

Reasoning

Spends extra thinking tokens on hard problems before answering. Best for math, code, and multi-step logic.

Prompt caching

Not supported

Response schema

Guarantees JSON output that matches a schema you provide. No brittle post-parsing on your side.

Streaming

Streams tokens as they are generated for real-time UX. Supported on every Hostlinku protocol.

Web search

Runs server-side web searches and folds the results into the answer. Billed per 1K calls.

Audio

Not supported

Video

Not supported

File input

Accepts documents such as PDFs and spreadsheets as context. Great for Q&A over long attachments.

Realtime

Not supported

Session

Not supported

Media

Not supported

Multipart form

Not supported

Binary response

Not supported

## Reliability & performance

Hostlinku measures this model from real request traffic: uptime and latency, not self-reported.

Last request: Nov 13, 2026, 10:27 AM

99.93%

4,287 requests in 7 days, 3 failed · automatic failover to backup channels

Uptime

Bar height = end-to-end latency.okfailed

Latest latency2.60s

Avg of last 602.60s

P95 of last 605.94s

Output throughput229.8 tok/s

ProtocolsAnthropic Messages (native) · OpenAI Responses (adapted) · Claude Code (tool)

Latency and uptime are measured from real request traffic over the last 7 days; throughput from user output.

## Protocols & code samples

Swap the base URL and everything else stays the same. Native protocols pass through; adapted protocols are translated by the Hostlinku gateway.

[Claude Code setup guide](https://docs.hostlinku.com/getting-started)

terminal

```
curl https://api.hostlinku.com/v1/messages \
  -H "x-api-key: $HOSTLINKU_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-fable-5-2",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Explain edge failover in one paragraph." }
    ]
  }'
```

## Full price list

Every billed dimension, with the vendor list price (struck through when higher) next to the $ price per Service Mode.

| Item | Unit | Original ($) | Performance$ | Economy$ |
| --- | --- | --- | --- | --- |
| Input (prompt) | per 1M tokens | $8 | $4.34 | $1.38 |
| Output (completion) | per 1M tokens | $40 | $21.7 | $6.9 |
| Cache read | per 1M tokens | $0.20 | $0.1085 | $0.0345 |
| Cache write (5m) | per 1M tokens | $10 | $5.42 | $1.73 |
| Cache write (1h) | per 1M tokens | $16 | $8.68 | $2.76 |
| Web search | per 1K calls | $10 | $5.42 | $11.5 |

Vendor list price is struck through when at least one Service Mode is cheaper. Dimensions without strikethrough (e.g. web search) are not discounted upstream.

## More from Anthropic

Other models from the same vendor, with prices and context for comparison.

[All models](https://hostlinku.com/en/models)

[Claude Haiku 5.5](https://hostlinku.com/en/models/claude-haiku-5-5)

Anthropic

$0.0542 / 1M token input · 1.0M ctx · 128K max out

[View model →](https://hostlinku.com/en/models/claude-haiku-5-5)[Compare](https://hostlinku.com/en/models?compare=claude-fable-5-2,claude-haiku-5-5)

[Claude Opus 5.5](https://hostlinku.com/en/models/claude-opus-5-5)

Anthropic

$2.17 / 1M token input · 1.0M ctx · 128K max out

[View model →](https://hostlinku.com/en/models/claude-opus-5-5)[Compare](https://hostlinku.com/en/models?compare=claude-fable-5-2,claude-opus-5-5)

[Claude Opus 5](https://hostlinku.com/en/models/claude-opus-5)

Anthropic

$2.71 / 1M token input · 1.0M ctx · 64K max out

[View model →](https://hostlinku.com/en/models/claude-opus-5)[Compare](https://hostlinku.com/en/models?compare=claude-fable-5-2,claude-opus-5)

[Claude Fable 5.2 vs Claude Haiku 5.5](https://hostlinku.com/en/models?compare=claude-fable-5-2,claude-haiku-5-5)[Claude Fable 5.2 vs Claude Opus 5.5](https://hostlinku.com/en/models?compare=claude-fable-5-2,claude-opus-5-5)[Claude Fable 5.2 vs Claude Opus 5](https://hostlinku.com/en/models?compare=claude-fable-5-2,claude-opus-5)[Claude Fable 5.2 vs Claude Sonnet 5](https://hostlinku.com/en/models?compare=claude-fable-5-2,claude-sonnet-5)

## FAQ

Common questions about Claude Fable 5.2: pricing, capabilities, and how they are measured.

Input

4.34

/ 1M token

$8original

Output

21.7

/ 1M token

$40original

Cache read

per 1M token

$0.1085

$0.20

Cache write (5m)

per 1M token

$5.42

$10

Cache write (1h)

per 1M token

$8.68

$16

Web search

per 1K calls

$5.42

$10

[Get started](https://hostlinku.com/register)

Anthropic

## Start using Claude Fable 5.2 today

Integrate Claude Fable 5.2 into your app with clear documentation, official SDKs, and transparent per-token USD pricing.

[Start for free](https://hostlinku.com/register)[Try in Playground](https://hostlinku.com/dashboard/playground?model=claude-fable-5-2)

## FAQ

### How much does Claude Fable 5.2 cost at Hostlinku?

Vendor list price is $8 input / $40 output per 1M tokens. At Hostlinku: Performance: $4.34 / $21.7; Economy: $1.38 / $6.9. Billing is in USD, charged per token with no subscription.

### What is Claude Fable 5.2's context window?

1,000,000 tokens in, up to 128,000 tokens out. Long prompts are metered per token, including cached prefixes.

### Does Claude Fable 5.2 support function calling?

Yes. Define tools in your request and the model calls them on every Hostlinku protocol.

### How do I use Claude Fable 5.2 with Claude Code?

Point Claude Code at Hostlinku: set ANTHROPIC_BASE_URL to https://api.hostlinku.com, use your Hostlinku API key as ANTHROPIC_AUTH_TOKEN, and set ANTHROPIC_MODEL to "claude-fable-5-2".

### How is the uptime on this page measured?

Hostlinku measures real request traffic through the supply chain. Every request is recorded, so the uptime, latency, and throughput you see are measured, not self-reported.