Claude Fable 5.1
anthropic The API that serves this model and sets the prices shown here. claude-fable-5-1 The model identifier to send in API requests. LLM Generates text from a prompt, so it can be compared with other LLMs on price and capability. Extra Large A frontier flagship, above the large tier of its generation.Provider: Anthropic
Knowledge cutoff: June 2026
Nothing to act on today. The cost is the checking: someone has to remember to look again next month, and the month after. Coolhand watches this model for you and automatically updates your agents to the most compatible replacement the moment a retirement is announced — one less thing on your list, permanently.
Sticker prices & cost-per-token
List rates as published by Anthropic, before any volume or enterprise discounts.
$10.00
$50.00
1,000,000 tokens
128,000
tokens per response (includes reasoning tokens)
Closed weights
$0.25
$12.50
$12.50
Get this data free
Want to stay updated on price changes on this model? Pull this data free (no API key required) here:
curl "https://coolhandlabs.com/api/v2/inference_apis?q%5Bmodel_eq%5D=claude-fable-5-1&q%5Bsource_api_eq%5D=anthropic"Pricing History
| Effective | Price |
|---|---|
| Sep 7, 2026 – present |
Input cost: $10.00 / 1M, Output cost: $50.00 / 1M, Cached input cost: $0.25 / 1M, Cache creation cost: $12.50 / 1M, 5-minute cache write cost: $12.50 / 1M, 1-hour cache write cost: $0.00 / 1M, Reasoning output cost: $0.00 / 1M, Cache storage cost: $0.00 / 1M/hr
Added Fable 5.1 with rates from pricing page. Prompt cache read: $0.25, write: $12.50 per 1M tokens (5m TTL).
|
History
Last change detected September 28, 2026 (10 days ago) by an automated scan.
| Date | Changed by | What changed |
|---|---|---|
| Sep 7, 2026 | Automated scan | Initial record created |
Source
https://www.anthropic.com/pricingComparable models
| Claude Fable 5.1 This model | Claude Opus 5.5 cheaper alternative | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Input modalities | Image, Text | Image, Text |
| Output modalities | Text | Text |
| Input cost | $10.00/1M $0.0000100000 | $4.00/1M $0.0000040000 |
| Output cost | $50.00/1M $0.0000500000 | $20.00/1M $0.0000200000 |
| Knowledge cutoff | June 2026 | June 2026 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output tokens | 128,000 | 128,000 |
| Capabilities |
Tool calling
Structured output
Reasoning
Vision
Streaming
Prompt caching
|
Tool calling
Structured output
Reasoning
Vision
Streaming
Prompt caching
|
| Status | Active | Active |
Reliability
No reliability incidents recorded in the last 90 days.
Frequently asked questions
Claude Fable 5.1 (Anthropic) costs $10.00 per 1M input tokens and $50.00 per 1M output tokens, as last published by Anthropic.
Claude Fable 5.1 has a context window of 1,000,000 tokens (the maximum combined input and output it can handle in a single request).
Claude Fable 5.1 sits in the extra large size tier. Size tiers run from micro (small enough to run on a device) through small, medium and large to extra large (frontier flagships), and are assigned from the model's family, naming and limits rather than its price.
Claude Fable 5.1 can generate up to 128,000 tokens in a single response. Reasoning (thinking) tokens count toward this limit.
Claude Fable 5.1's training data runs through June 2026, so it may not know about later events. Coolhand records the cutoff at month precision, since providers often publish only the month.
Claude Fable 5.1 accepts image and text as input and produces text as output, as recorded in the Coolhand catalog.
No — the weights of Claude Fable 5.1 have not been released, so it is only available through hosted APIs.
No, Claude Fable 5.1 is currently active with no announced deprecation date.
Comparable options from Anthropic include the lower-cost Claude Opus 5.5.
Claude Opus 5.5 is from the same provider (Anthropic) and a comparable pricing tier, but we haven't verified parameter compatibility — compare context windows where listed and check Anthropic's migration guide before switching. Recorded capabilities: Claude Fable 5.1 supports tool calling, structured output, reasoning, vision, streaming, and prompt caching; Claude Opus 5.5 supports tool calling, structured output, reasoning, vision, streaming, and prompt caching. A capability we haven't recorded isn't necessarily unsupported.
Call GET https://coolhandlabs.com/api/v2/inference_apis?q[source_api_eq]=anthropic&q[model_eq]=claude-fable-5-1 — free, no API key required, and scoped to just this model since source_api and model together are unique. See https://coolhandlabs.com/docs for the full REST API reference.
Coolhand also tracks Claude Opus 4, Claude Sonnet 4, Claude Opus 4.1, Claude Fable 5, Claude Haiku 4.5, and Claude Opus 4.5 from Anthropic. Some may already be deprecated, so check each model's status alongside its current pricing.
| Model | Input cost | Output cost | Context window | Max output tokens | Status |
|---|---|---|---|---|---|
| Claude Opus 4 | $15.00/1M $0.0000150000 | $75.00/1M $0.0000750000 | — | — |
Deprecated Jul 13, 2026
|
| Claude Sonnet 4 | $3.00/1M $0.0000030000 | $15.00/1M $0.0000150000 | — | — |
Deprecated Jul 13, 2026
|
| Claude Opus 4.1 | $15.00/1M $0.0000150000 | $75.00/1M $0.0000750000 | — | — |
Deprecated Jul 13, 2026
|
| Claude Fable 5 | $10.00/1M $0.0000100000 | $50.00/1M $0.0000500000 | 1,000,000 | 128,000 | Active |
| Claude Haiku 4.5 | $1.00/1M $0.0000010000 | $5.00/1M $0.0000050000 | 200,000 | 64,000 | Active |
| Claude Opus 4.5 | $5.00/1M $0.0000050000 | $25.00/1M $0.0000250000 | 200,000 | 64,000 | Active |
Track LLM pricing and deprecations automatically.
Start free