ANTHROPIC MODEL GUIDE
Claude Fable 5.2 API
Claude Fable 5.2 is built for long agent sessions, research across several sources, and analysis that ends in a finished deliverable.
Core specificationsModel Plaza checked November 10, 2026
Model IDclaude-fable-5-2
Context / max output1M / 128K
Input and outputText and image input; text output
ThinkingAdaptive thinking always on; default effort high
Vendor statusActive
LLMFly AI input / output per 1M$4 / $20 (50% OFF)
Selection verdictClaude Fable 5.2 bills at $4 input / $20 output per 1M tokens on LLMFly AI (0.5x standard tier).
Best fit
Start with Claude Opus 5.5 as a baseline. Try Fable when that baseline repeatedly misses a research requirement or fails to finish a long tool workflow.
Avoid when
Native Claude workflows that require zero data retention without an approved exception.
01
Claude API cost estimate
Enter token counts for one representative request; every usage item is multiplied by the request count.
Claude Code0.5xCurrent multiplier
Vendor reference cost$1.20Estimated savings$0.6050.0%
Cost breakdown
Rates are per 1M tokens- LLMFly AI
- $4
- Vendor reference
- $8
- Total tokens
- 100,000
- LLMFly AI
- $20
- Vendor reference
- $40
- Total tokens
- 10,000
- LLMFly AI
- $5
- Vendor reference
- $10
- Total tokens
- 0
- LLMFly AI
- $0.1
- Vendor reference
- $0.2
- Total tokens
- 0
02
Choosing and integrating
Claude Fable 5.2 API pricing breakdown
Claude Fable 5.2 (claude-fable-5-2) is billed by token usage. Prices below are USD per 1M tokens. LLMFly AI rates already include the 0.5x group multiplier; do not apply it again. Provider reference prices are separate. These rates come from the site's Model Plaza snapshot; confirm live catalog and account rates before calling.
Example: a request with 10,000 uncached input tokens and 1,000 output tokens costs approximately $0.06 in LLMFly AI token charges. This excludes cache writes, tools, retries, and other additional fees.
- Platform and provider prices use their own input-token tiers. Do not apply provider long-context multipliers to platform prices.
- Not listed does not mean free. Account for cache reads, cache writes, and uncached input in their respective billing categories.
- Token cost = tokens in each billing category × its price per million ÷ 1,000,000. Add tools and other charges separately.
| Price source | Input tokens per request | Input | Output | Cache write | Cache read | 1h cache write |
|---|---|---|---|---|---|---|
| LLMFly AI | Single rate | $4 | $20 | $5 | $0.1 | $8 |
| Provider reference | Single rate | $8 | $40 | $10 | $0.2 | $16 |
Pricing tiers and additional charges
The listed input and output rates are lower than Fable 5.1. For a long session, budget for reasoning output and repeated cache writes as well as the final answer.
Claude Fable 5.2 capabilities and workloads
- Adaptive thinking is always on in the Claude API. Control depth with effort and allow automatic tool choice. Forcing a particular tool can return HTTP 400.
Limits to check before migration
- Anthropic requires 30-day retention for its native API unless it expressly authorizes an exception. Verify the gateway's retention terms before routing sensitive data.
Comparing Claude Fable 5.2 with sibling models
Start with Claude Opus 5.5 as a baseline. Try Fable when that baseline repeatedly misses a research requirement or fails to finish a long tool workflow.
| Model ID | Context / max output | LLMFly AI in / out | Vendor reference in / out |
|---|---|---|---|
| claude-fable-5-2 | 1M / 128K | $4 / $20 | $8 / $40 |
| claude-opus-5-5 | 1M / 128K | $2 / $10 | $4 / $20 |
| claude-opus-5 | 1M / 128K | $2.5 / $12.5 | $5 / $25 |
| claude-fable-5-1 | 1M / 128K | $5 / $25 | $10 / $50 |
| claude-fable-5 | 1M / 128K | $5 / $25 | $10 / $50 |
Use the exact model ID when connecting
Copy the Claude Code setup from the console’s Use Key dialog, then run this command to test a text response.
- Send a minimal text request and inspect the response and usage.
- Test streaming, tool calls, and structured output separately if your application needs them.
- Check retry behavior and spending limits before increasing traffic.
claude -p "Reply with OK." --model claude-fable-5-2Vendor capability versus gateway access
Claude Fable 5.2 runs under the Claude Code group (0.5x multiplier) in Model Plaza. Configure Claude Code or Anthropic-compatible clients using the console's generated environment setup, and reconcile input, output, and cache line items in your usage log before scaling traffic.
Frequently asked questions
What should I put in the model field?
Use the exact ID claude-fable-5-2, not the display name.
How is the discount calculated?
The current 0.5x multiplier is applied to the base rate, giving 50% off the catalog's official reference. Amounts are shown per million tokens.
Do these prices include every possible fee?
Not necessarily. Check cache-write duration, tools, and other route charges separately. Use the full pricing table and actual usage records to reconcile a bill.
What are the context and output limits?
Vendor documentation lists 1M context and 128K maximum output; confirm gateway route limits separately.
Use the Claude Fable 5.2 API
LLMFly AI provides this model. Use the exact ID claude-fable-5-2 and confirm current account pricing in Model Plaza.