AnthropicNot yet certifiedReleased 11/09/2026

Claude Fable 5.2

Claude Fable 5.2 supports agentic coding, knowledge work, and research with always-on adaptive thinking and adjustable reasoning effort from low through max.

View API reference ↓
Input / output priceFrom$8.00 / $40.00per 1M
24h uptime99.93%

Listed for reference. Inference Bureau dispatches only to certified routes, so requests for this model are refused until one is certified. See certified models.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "anthropic/claude-fable-5.2",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
Amazon Bedrock1M128K8.1 s118 tps$8.00$40.00Read $0.20Write $10.006 featuresNoYesUSListed
Anthropic1M128K2.3 s320 tps$8.00$40.00Read $0.20Write $10.007 featuresNoYesUSListed
Google Vertex AI1M128K1.3 s—$8.00$40.00Read $0.20Write $10.006 featuresNoYesGlobalListed

Uptime

24 hours

Request success rate per provider.

Amazon Bedrock99.80%
Anthropic99.99%
Google Vertex AI100.00%

Throughput

last hour

P50 output tokens per second.

Anthropic320 tps
Amazon Bedrock118 tps
Google Vertex AI—

Latency

last hour

P50 time to first token.

Google Vertex AI1.3 s
Anthropic2.3 s
Amazon Bedrock8.1 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "anthropic/claude-fable-5.2",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. anthropic/claude-fable-5.2. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. Claude Fable 5.2 supports up to 128,000 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokensstoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 1M-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens
PDFURL, base64Sent as file content parts; counts as input tokens

More models by Anthropic

ModelContextInputOutputCacheRelease
anthropic/claude-fable-5.2-batch1M$4.00$20.00Read $0.100Write $5.0011/09/2026
anthropic/claude-fable-5.2-fast1M$16.00$80.00Read $0.40Write $20.0011/09/2026
anthropic/claude-haiku-5.51M$0.100$0.50Read $0.010Write $0.1310/07/2026
anthropic/claude-haiku-5.5-batch1M$0.050$0.25Read $0.0050Write $0.06310/07/2026
anthropic/claude-sonnet-5.51M$2.00$10.00Read $0.100Write $2.5009/28/2026
anthropic/claude-sonnet-5.5-batch1M$1.00$5.00Read $0.050Write $1.2509/28/2026
anthropic/claude-opus-5.51M$4.00$20.00Read $0.20Write $5.0009/22/2026
anthropic/claude-opus-5.5-batch1M$2.00$10.00Read $0.100Write $2.5009/22/2026
anthropic/claude-opus-5.5-fast1M$8.00$40.00Read $0.40Write $10.0009/22/2026
anthropic/claude-fable-5.11M$10.00$50.00Read $0.25Write $12.5008/31/2026