System AI Claude Fable 5.2
system.ai.claude-fable-5-2Pricing
List prices at Databricks, 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 |
What it costs a month
At Databricks 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$28,800
Where to run it
1 host serve System AI Claude Fable 5.2. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
DatabricksCloud system.ai.claude-fable-5-2 | $8.00 / $40.00 | system.ai.claude-fable-5-2 |
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
- TextImages
- Produces
- Text
- Features
- Adaptive thinkingPrompt cachingAlways reasons
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 Databricks.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 0% less
- 0% less
- 75% less
- 81% less
Open-weight picks
- 75% less
- 86% less
- 88% less
- 89% less
Call it
Using Databricks's API.
from litellm import completion
response = completion(
model="databricks/system.ai.claude-fable-5-2",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does System AI Claude Fable 5.2 cost?
On Databricks, System AI 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 System AI Claude Fable 5.2?
System AI Claude Fable 5.2 runs on 1 API: Databricks.
What is System AI Claude Fable 5.2's context window?
1M tokens, with up to 128K tokens in one reply.
Is System AI Claude Fable 5.2 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to System AI Claude Fable 5.2?
Models that cost less and keep most of what it can do: GPT-6.2 Astra on OpenAI (0% less), Claude Fable 5.2 on Anthropic (0% less) and Kimi K3.1 Pro on Databricks (75% less). Savings are on a mix of 3 input tokens to 1 output token.
What is System AI Claude Fable 5.2's API model id?
Use system.ai.claude-fable-5-2 with Databricks.
Sources
Raw catalog entry for system.ai.claude-fable-5-2 on Databricks
{
"cache_creation_input_token_cost": 0.00000999999,
"cache_creation_input_token_cost_above_1hr": 0.00001599997,
"cache_read_input_token_cost": 1.9999e-7,
"input_cost_per_token": 0.00000800002,
"input_dbu_cost_per_token": 0.000114286,
"litellm_provider": "databricks",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"metadata": {
"notes": "Claude Fable 5.2 on Databricks is served through Unity Gateway with the model service name system.ai.claude-fable-5-2, hosted through Amazon Bedrock. Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."
},
"mode": "chat",
"output_cost_per_token": 0.00004000003,
"output_dbu_cost_per_token": 0.000571429,
"prompt_cache_min_tokens": 512,
"source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
"supports_adaptive_thinking": true,
"supports_anthropic_thinking_payload": true,
"supports_assistant_prefill": false,
"supports_forced_tool_use": false,
"supports_function_calling": true,
"supports_mid_conversation_system": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"thinking_always_on": true
}