Model comparison
Claude Fable 5 vs Kimi K3
Provider-published facts for Claude Fable 5 and Kimi K3, side by side: price, limits, inputs, access and data policy. No mystery scores and no invented benchmark rankings.
Model comparison
Provider-published facts for Claude Fable 5 and Kimi K3, side by side: price, limits, inputs, access and data policy. No mystery scores and no invented benchmark rankings.
Set your usage. Your estimate updates as you type.
Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.
One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
| Model | Access | Estimated total (USD) |
|---|---|---|
| Claude Fable 5Anthropic | Anthropic | $0.085 |
| Kimi K3Moonshot AI | Moonshot AI | No reviewed rate |
Quick take
The original Fable model for complex coding and multi-step work, retained for existing integrations.
Check the newer Fable 5.2 and the mandatory retention requirements before starting a new project.
Moonshot AI's frontier multimodal model for million-token coding, reasoning, knowledge work, and tool-driven agents.
Moonshot's public terms permit broad service-improvement uses of submitted content. Treat the provider route and enterprise agreement as a core requirement for confidential work.
Compare the published facts
Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.
| Text & reasoning | Claude Fable 5 | Kimi K3 |
|---|---|---|
| Context windowMaximum combined prompt and working context documented by the provider. | 1M tokens | 1M tokens |
| Maximum outputProvider-published response limit, where available. | 128K tokens | Not separately published for the direct API |
| Knowledge cutoffLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff. | January 2026 | Not published |
| Input priceCurrent standard list price per million input tokens unless noted. | $10 / 1M | $3 / 1M uncached; $0.30 cached |
| Output priceCurrent standard list price per million output tokens unless noted. | $50 / 1M | $15 / 1M |
| InputsMedia types accepted by the listed model endpoint. | Text, image | Text, image |
| Tools & agentsSelected native tools and agent-building capabilities, not an exhaustive list. | Tool use, agents, vision, coding workflows | Tools, agent workflows, reasoning levels, dynamic tool loading on supported routes |
How to choose
Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.
Claude Fable 5 requires 30-day retention unless Anthropic authorizes an exception. API data is not used for training without express permission.
Provider and API links
Moonshot's API privacy and model-use terms allow submitted content to be stored and used to provide, maintain, develop, and improve the service. Obtain appropriate enterprise terms before sending sensitive material.
Frequently asked questions
Claude Fable 5: The original Fable model for complex coding and multi-step work, retained for existing integrations. Kimi K3: Moonshot AI's frontier multimodal model for million-token coding, reasoning, knowledge work, and tool-driven agents.
Best fit for Claude Fable 5: Complex coding. Best fit for Kimi K3: Large codebase and document work. Test both with your own data and provider route before committing.
No. Anthropic's models overview lists Claude Fable 5.2, released November 9, 2026, as the current Fable model, with Fable 5.1 and Fable 5 as legacy models. The 5.5 versions are Claude Opus 5.5, Claude Sonnet 5.5 and Claude Haiku 5.5.
From each provider's own documentation, pricing and policy pages for the Text & reasoning category. Cody does not add its own benchmark scores or name a universal winner.