KovAPIKovAPI
Chat ● Operational Service status →

Claude Fable 5.2

Beta ⧉
claude-fable-5-2

Fable 5.2 is Anthropic’s most capable publicly available model today and the successor to 5.1. Input and output each cost 20% less per token than with 5.1. We recommend starting new projects with 5.2.

Long-document analysis and reasoning1M

Live Test · Playground

Try out Claude Fable 5.2 right here (available after login).

Input

Advanced
Web search
Memory · multi-turn
Thinking

Conversation

Start a conversationType a message below to begin

About Claude Fable 5.2

Use Claude Fable 5.2 to analyze long documents, reason through a problem or call tools. Send text and images through OpenAI Chat or Anthropic Messages. Billing is based on token usage.

Use cases

Long-document analysis and reasoning

Compare two versions of a contract and quote the clauses where payment terms changed.

Extract form fields

Extract dates, amounts and currencies from order notes. Use a JSON Schema to specify field names and types.

Look up an order

Provide an order lookup tool and send its result back to the conversation so the reply reflects the current order status.

How to choose

The default effort is high. Chat maps minimal and none to low. An explicit output limit of 4,096 or less also uses low when thinking settings are omitted. Native Messages keeps the model default.

FAQ

How is a request billed?
Fresh input, output, cache reads, 5-minute writes and 1-hour writes are metered separately.
Which parameter specifies a JSON Schema in each API?
Chat accepts json_object and replies normally. For strict JSON, use response_format.json_schema in Chat or output_config.format in native Messages.
How can I control thinking effort for short answers?
The default effort is high. Chat maps minimal and none to low. An explicit output limit of 4,096 or less also uses low when thinking settings are omitted. Native Messages keeps the model default.

Related Models

Explore other models you can integrate.

View all →
GPT-5.6 Sol Chat

GPT-5.6 Sol

gpt-5.6-sol

Frontier flagship for agentic coding

$1.20/1M in · $6.00/1M out ↓70% View →
GPT-5.6 Luna Chat

GPT-5.6 Luna

gpt-5.6-luna

Fast, economical agentic coding model

$0.07/1M in · $0.40/1M out ↓66% View →
GPT-6 Astra Chat

GPT-6 Astra

gpt-6-astra

Next-generation OpenAI flagship - 1.05M context

$3.00/1M in · $15.00/1M out ↓70% View →
GPT-6.2 Astra Chat

GPT-6.2 Astra

gpt-6.2-astra

OpenAI's newest flagship - 20% below GPT-6 Astra's list

$2.40/1M in · $12.00/1M out ↓70% View →
GPT-6.2 Sol Chat

GPT-6.2 Sol

gpt-6.2-sol

The GPT-6.2 workhorse - a quarter of Astra's price

$0.60/1M in · $3.00/1M out ↓70% View →
GPT-6.1 Sol Chat

GPT-6.1 Sol

gpt-6.1-sol

The GPT-6 Sol upgrade - near-Astra coding and agents

$0.60/1M in · $3.00/1M out ↓70% View →
GPT-6 Sol Chat

GPT-6 Sol

gpt-6-sol

Built for complex coding and agentic workflows - 1.05M context

$0.60/1M in · $3.00/1M out ↓70% View →
GPT-6 Luna Chat

GPT-6 Luna

gpt-6-luna

The most efficient GPT-6, built for high-volume work

$0.07/1M in · $0.40/1M out ↓22% View →
GPT Image 2 Image

GPT Image 2

gpt-image-2

High-quality text-to-image / image-to-image model

$0.005/img and up View →
GPT Image 2.5 Flare Image

GPT Image 2.5 Flare

gpt-image-2.5-flare

Next-gen image model - clean and smooth

$0.005/img and up View →
GPT Image 2.5 Sunburst Image

GPT Image 2.5 Sunburst

gpt-image-2.5-sunburst

Next-gen image model - richer texture

$0.005/img and up View →
GPT Image 2.6 Flare Image

GPT Image 2.6 Flare

gpt-image-2.6-flare

OpenAI's November 2026 image model · clean and smooth

$0.015/img and up View →
GPT Image 2.6 Sunburst Image

GPT Image 2.6 Sunburst

gpt-image-2.6-sunburst

OpenAI's November 2026 image model · richer texture

$0.015/img and up View →
GPT Image 2.6 Flare · Token Image

GPT Image 2.6 Flare · Token

gpt-image-2.6-flare-token

GPT Image 2.6 Flare · billed by actual tokens · xhigh / max available

$21.6 /1M image output tokens View →
GPT Image 2.6 Sunburst · Token Image

GPT Image 2.6 Sunburst · Token

gpt-image-2.6-sunburst-token

GPT Image 2.6 Sunburst · billed by actual tokens · xhigh / max available

$21.6 /1M image output tokens View →
Nano Banana 2 Image

Nano Banana 2

nano-banana-2

High-quality text-to-image / image-to-image model

$0.015/img and up View →
Nano Banana Pro Image

Nano Banana Pro

nano-banana-pro

Flagship text-to-image / image-to-image model

$0.020/img and up View →
Nano Banana 2.1 Image

Nano Banana 2.1

nano-banana-2.1

The upgraded Nano Banana 2, with better images and text

$0.015/img and up View →
Nano Banana 2 Lite Image

Nano Banana 2 Lite

nano-banana-2-lite

The fastest, lowest-cost Nano Banana · 1K only

$0.010/img and up View →
Grok Imagine Image Image

Grok Imagine Image

grok-imagine-image

xAI's image model · renders in seconds

$0.005/img and up View →
Grok Imagine Image Quality Image

Grok Imagine Image Quality

grok-imagine-image-quality

xAI's higher-quality tier · finer detail and lettering

$0.015/img and up View →
Seedream 5.0 Pro Image

Seedream 5.0 Pro

seedream-5.0-pro

ByteDance's flagship Seedream 5.0 image model · text-to-image and multi-image editing

$0.025/img and up View →
Seedream 5.5 Image

Seedream 5.5

seedream-5.5

ByteDance's newest Seedream image model · text-to-image and multi-image editing

$0.020/img and up View →
Kling Image 4.0 Image

Kling Image 4.0

kling-image-4.0

Kuaishou's new Kling image model · 2K / 4K photoreal images and layouts

$0.060/img and up View →
Kling Image 4.0 Long Image

Kling Image 4.0 Long

kling-image-4.0-long

Kling long images · a whole e-commerce detail page or web page design in one image

$0.235/img and up View →
Midjourney Image

Midjourney

midjourney

The Midjourney image model · V8.2 by default, four originals a job

$0.045/job of 4+ View →
Claude Sonnet 4.6 Chat

Claude Sonnet 4.6

claude-sonnet-4-6

Balanced, efficient chat and coding model

$1.50/1M in · $7.50/1M out ↓50% View →
Claude Opus 5 Chat

Claude Opus 5

claude-opus-5

Next-generation flagship from Anthropic

$4.00/1M in · $20.00/1M out ↓20% View →
Claude Fable 5 Chat

Claude Fable 5

claude-fable-5

Anthropic Fable series · narrative and long-form writing

$8.00/1M in · $40.00/1M out ↓20% View →
Claude Opus 5.5 Chat

Claude Opus 5.5

claude-opus-5-5

Anthropic's next Opus · 1M context · adaptive thinking

$2.50/1M in · $12.50/1M out ↓38% View →
Claude Sonnet 5.5 Chat

Claude Sonnet 5.5

claude-sonnet-5-5

Anthropic's newest Sonnet · the best mix of speed and intelligence

$1.50/1M in · $7.50/1M out ↓25% View →
Gemini 4 Argon Chat

Gemini 4 Argon

gemini-4-argon

Gemini 4 Argon Beta: three thinking levels and a shared million-token context

$0.50/1M in · $3.00/1M out ↓71% View →
Gemini 4 Neon Chat

Gemini 4 Neon

gemini-4-neon

Gemini 4 Neon Beta: the mid-tier workhorse of the Gemini 4 family, between Hydrogen and Carbon

$0.90/1M in · $4.50/1M out ↓70% View →
Gemini 4 Hydrogen Chat

Gemini 4 Hydrogen

gemini-4-hydrogen

Gemini 4 Hydrogen Beta: the lowest-priced Gemini 4 model

$0.45/1M in · $2.25/1M out ↓70% View →
Gemini 3.8 Flash Chat

Gemini 3.8 Flash

gemini-3.8-flash

Latest Flash · adaptive thinking

$0.60/1M in · $3.60/1M out ↓7% View →
DeepSeek V4.1 Flash Chat

DeepSeek V4.1 Flash

deepseek-v4.1-flash

DeepSeek's current Flash model - thinking on or off

$0.11/1M in · $0.44/1M out ↓27% View →
GLM-5.3 Chat

GLM-5.3

glm-5.3

The new Z.ai flagship - coding and agents

$1.12/1M in · $3.52/1M out ↓20% View →
Qwen3.8 Max Chat

Qwen3.8 Max

qwen3.8-max

Alibaba's Qwen 3.8 flagship - reasoning, coding and agents

$1.40/1M in · $4.20/1M out ↓30% View →
Grok 4.7 Chat

Grok 4.7

grok-4.7

xAI's flagship reasoning model - long context

$0.30/1M in · $0.90/1M out ↓85% View →
Veo 3.1 Video

Veo 3.1

veo-3.1

Text / image / first-last frame / references · 8 s

$0.200/clip+ View →
Gemini Omni 1.2 Flash Video

Gemini Omni 1.2 Flash

gemini-omni-1.2-flash

Google Gemini Omni 1.2 Flash · 3-15 s · video editing · 4K

$0.035/s View →
Gemini Omni Flash Video

Gemini Omni Flash

gemini-omni-flash

Google's next-generation video model · 6 / 8 / 10 s

$0.035/s View →
Seedance 2.5 · Token Video

Seedance 2.5 · Token

seedance-2.5-token

Built for reliable delivery and fast creation

$7.50–13.75 /1M video tokens View →
Seedance 2.5 · Token Draft Video

Seedance 2.5 · Token Draft

seedance-2.5-token-draft

Draft to final

$7.50–12.50 /1M video tokens View →
Seedance 2.5 Video

Seedance 2.5

seedance-2.5

Text / image to video · up to 30 seconds

$0.158/s View →
Seedance 2.5 Flash Video

Seedance 2.5 Flash

seedance-2.5-flash

Seedance 2.5 Flash · 4-30 s · lower per-second price

$0.120/s View →
Seedance 2.0 Video

Seedance 2.0

seedance-2.0

Text / image to video · 5-15 seconds

$0.105/s View →
Seedance 2.0 Fast Video

Seedance 2.0 Fast

seedance-2.0-fast

Low latency · quick turnaround

$0.075/s View →
Seedance 2.0 Mini Video

Seedance 2.0 Mini

seedance-2.0-mini

Entry tier · lowest cost

$0.052/s View →
Seedance 2.0 · Clip Video

Seedance 2.0 · Clip

seedance-2.0-clip

Special price · per clip · 5 / 10 / 15 s at one price

$1.000/clip+ View →
Seedance 2.5 · Special Video

Seedance 2.5 · Special

seedance-2.5-30s

Temporary availability · per clip

$2.000/clip+ View →
Wan 3.0 Video

Wan 3.0

wan3.0-video

One endpoint, five modes · up to 30 seconds

$0.065/s View →
Wan 3.0 Prime Video

Wan 3.0 Prime

wan3.0-video-prime

Same capabilities · several times faster

$0.120/s View →
MiniMax H3 Video

MiniMax H3

minimax-h3

480P / 768P / 1080P · first & last frame · omni reference · native audio

$0.036/s View →
MiniMax H3 Lite Video

MiniMax H3 Lite

minimax-h3-lite

Faster, cheaper H3 · 480P / 768P

$0.013/s View →
Grok Imagine Video 1.5 Video

Grok Imagine Video 1.5

grok-imagine-video-1.5

Billed per second · up to 1080P

$0.040/s View →
Claude Fable 5.1 Chat

Claude Fable 5.1

claude-fable-5-1

The previous Fable generation

$6.00/1M in · $30.00/1M out ↓40% View →
Claude Haiku 5.5 Chat

Claude Haiku 5.5

claude-haiku-5-5

Classify tickets and extract fields

$0.06/1M in · $0.30/1M out ↓40% View →