Claude Fable 5.2
Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision.
claude-fable-5-2Released 9 Nov 2026 (9 days ago)Pricing
List prices at Anthropic, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $8.00 | $40.00 | |
| Cached input 98% off input | $0.20 | 98% off input | |
| Cache write, 5 minutes | $10.00 | ||
| Cache write, 1 hour | $16.00 | ||
| Batch 50% off | $4.00 | $20.00 | 50% off |
| Web search $10.00 per 1,000 searches | $10.00 per 1,000 searches | ||
| Regional endpoints 10% more | 10% more |
What it costs a month
At Anthropic list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$4,698
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$3,408
- Coding agent1,000 requests a day, 40K in / 2K out, cached$5,448
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$14,400
Where to run it
7 hosts serve Claude Fable 5.2. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
AnthropicLab API claude-fable-5-2 | $8.00 / $40.00 | claude-fable-5-2 | |
Amazon BedrockCloud anthropic.claude-fable-5-2 | $8.00 / $40.00 | anthropic.claude-fable-5-2 | |
Azure AI FoundryCloud claude-fable-5-2 | $8.00 / $40.00 | claude-fable-5-2 | |
Vertex AICloud claude-fable-5-2 | $8.00 / $40.00 Retires 9 Nov 2027 | claude-fable-5-2 | Retires 9 Nov 2027 |
ReplicateInference claude-fable-5.2 | $8.00 / $40.00 | claude-fable-5.2 | |
PerplexityGateway claude-fable-5-2 | $8.00 / $40.00 | claude-fable-5-2 | |
DatabricksCloud databricks-claude-fable-5-2 | $8.00 / $40.00 | databricks-claude-fable-5-2 | |
GitHub CopilotSubscription claude-fable-5.2 | In the subscription | claude-fable-5.2 |
Show 9 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| Claude Platform claude-fable-5-2 | $8.00 / $40.00 | claude-fable-5-2 | |||||
| global global.anthropic.claude-fable-5-2 | $8.00 / $40.00 | global.anthropic.claude-fable-5-2 | |||||
| eu eu.anthropic.claude-fable-5-2 | $8.80 / $44.00 +10% vs headline | eu.anthropic.claude-fable-5-2 | |||||
| us us.anthropic.claude-fable-5-2 | $8.80 / $44.00 +10% vs headline | us.anthropic.claude-fable-5-2 | |||||
| us-gov-west-1 anthropic.claude-fable-5-2 | $9.60 / $48.00 +20% vs headline | anthropic.claude-fable-5-2 | |||||
| us-gov-east-1 anthropic.claude-fable-5-2 | $9.60 / $48.00 +20% vs headline | anthropic.claude-fable-5-2 | |||||
| us-gov us-gov.anthropic.claude-fable-5-2 | $9.60 / $48.00 +20% vs headline | us-gov.anthropic.claude-fable-5-2 | |||||
| Azure AI Foundry | |||||||
| fast mode claude-fable-5-2-fast | $16.00 / $80.00 +100% vs headline | claude-fable-5-2-fast | |||||
| Vertex AI | |||||||
| Alias claude-fable-5-2@default | $8.00 / $40.00 Retires 9 Nov 2027 | claude-fable-5-2@default | Retires 9 Nov 2027 | ||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImagesPDFs
- Produces
- Text
- Effort settings the source lists
- xhighmax
- Features
- Adaptive thinkingComputer useFast modeNative structured outputPDF inputPrompt cachingAlways reasonsBuilt-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Anthropic.
Smaller Anthropic models
- 50% less
- 75% less
- 99% less
Other frontier labs
- 70% less
- 75% less
- 81% less
- 75% less
Open-weight picks
- 75% less
- 87% less
- 89% less
- 97% less
Model line
Newer and older versions, at each lab's own price.
- Nov 2026Claude Fable 5.2Latest$8.00 / $40.00
- Sep 2026Claude Fable 5.1$10.00 / $50.00
- Jun 2026Claude Fable 5$10.00 / $50.00
Call it
Using Anthropic's API.
from anthropic import Anthropic
client = Anthropic() # reads ANTHROPIC_API_KEY
message = client.messages.create(
model="claude-fable-5-2",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)curl https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_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": "Hello"}]}'from litellm import completion
response = completion(
model="anthropic/claude-fable-5-2",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Claude Fable 5.2 cost?
On Anthropic, Claude Fable 5.2 costs $8.00 per million input tokens and $40.00 per million output tokens. Cached input costs $0.20 per million tokens.
Which APIs offer Claude Fable 5.2?
Claude Fable 5.2 runs on 7 APIs: Anthropic, Amazon Bedrock, Azure AI Foundry, Vertex AI, Replicate, Perplexity and Databricks.
What is Claude Fable 5.2's context window?
1M tokens, with up to 128K tokens in one reply.
Is Claude Fable 5.2 being retired?
Vertex AI retires it on 9 Nov 2027. 6 hosts keep serving it.
Is there a newer version of Claude Fable 5.2?
No. Claude Fable 5.2 is the newest model in its line.
What are cheaper alternatives to Claude Fable 5.2?
Models that cost less and keep most of what it can do: Claude Opus 5.5 on Anthropic (50% less), GPT-5.3 Codex on OpenAI (70% less), Gemini 4 Carbon on Google AI Studio (75% less) and Kimi K3.1 Pro on Databricks (75% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Claude Fable 5.2 released?
Anthropic released it on 9 Nov 2026.
What is Claude Fable 5.2's API model id?
Use claude-fable-5-2 with Anthropic. Other hosts use their own ids: anthropic.claude-fable-5-2 on Amazon Bedrock, claude-fable-5.2 on Replicate, databricks-claude-fable-5-2 on Databricks.
Sources
- Amazon Bedrock pricing
- Anthropic pricing
- Azure AI Foundry pricing
- Perplexity pricing
- Vertex AI pricing
- GitHub Copilot pricing
- Replicate pricing
- Databricks pricing
- LiteLLM model map
Raw catalog entry for claude-fable-5-2 on Anthropic
{
"cache_creation_input_token_cost": 0.00001,
"cache_creation_input_token_cost_above_1hr": 0.000016,
"cache_creation_input_token_cost_batches": 0.000005,
"cache_read_input_token_cost": 2e-7,
"cache_read_input_token_cost_batches": 1e-7,
"input_cost_per_token": 0.000008,
"input_cost_per_token_batches": 0.000004,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.00004,
"output_cost_per_token_batches": 0.00002,
"prompt_cache_min_tokens": 512,
"provider_specific_entry": {
"us": 1.1,
"fast": 2
},
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://platform.claude.com/docs/en/about-claude/pricing",
"supports_adaptive_thinking": true,
"supports_anthropic_compaction": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_fast_mode": true,
"supports_forced_tool_use": false,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_mid_conversation_system": true,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_speed": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true,
"thinking_always_on": true
}