Claude Fable 5
TL;DR
PremiumAnthropic's most capable model for demanding reasoning and long-horizon agents.
Available on
Not on the Go plan ($1/mo, open-source models only).
Switch with
Pick Claude Fable 5 from the selector.
Intelligence Index
Claude Fable 5 vs the Anthropic lineup
Claude Fable 5
Claude Opus 4.8
Claude Opus 4.7
Claude Sonnet 5
Speed
~62
tokens / sec
Input
$10
per M tokens
Output
$50
per M tokens
Claude Fable 5 in Command Code
Claude Fable 5 is Anthropic's premium model — most capable for demanding reasoning & long-horizon agents. It runs in Command Code with a 1M-token context window, switchable any time with /model.
At 59.9 on the Intelligence Index, Claude Fable 5 is currently the highest-scoring model in Command Code.
Claude Fable 5 specs at a glance
What Claude Fable 5 accepts, how much it can hold in context, and what you need to run it.
| Spec | Claude Fable 5 |
|---|---|
| Context window | 1M tokens |
| Input modalities | text + images |
| Reasoning | Yes — efforts: low, medium, high, xhigh, max |
| Release date | 2026-06-09 |
| Minimum plan | Provider |
Claude Fable 5 vs the Command Code lineup
Claude Fable 5 alongside its nearest real alternatives in the lineup — every price straight from the billing tables.
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| Claude Fable 5 (this page) | 59.9 | 76.5 | ~62 tok/s | $10.00 | $50.00 | $20 | 1M |
| GPT-5.6 Sol | 58.9 | 77.4 | ~77 tok/s | $5.00 | $30.00 | $11.25 | 1.1M |
| Claude Opus 4.8 | 55.7 | 74.3 | ~55 tok/s | $5.00 | $25.00 | $10 | 1M |
| GPT-5.6 Terra | 55 | 76.7 | ~155 tok/s | $2.50 | $15.00 | $5.625 | 1.1M |
| GPT-5.5 | 54.8 | 74.9 | ~81 tok/s | $5.00 | $30.00 | $11.25 | 200K |
| Tencent Hy3 | 41.2 | 58.8 | ~58 tok/s | $0.00 | $0.00 | free | 262K |
What Claude Fable 5 is best for
Claude Fable 5 earns its slot in the lineup for the hardest reasoning problems, large multi-file refactors.
- The hardest reasoning problems — pick Claude Fable 5 from /model and it applies to the session.
- Large multi-file refactors — pick Claude Fable 5 from /model and it applies to the session.
When to switch away from Claude Fable 5
No single model wins every task. These are Claude Fable 5's computed nearest alternatives — one step up, one step down in cost, one for speed, one from the same family — each switchable mid-session with /model.
Switch to GPT-5.6 Sol
GPT-5.6 Sol runs about 44% cheaper blended ($11.25 versus $20 per million tokens) while scoring 58.9 on the Intelligence Index. Switch down for high-volume work where Claude Fable 5's edge isn't earning its rate.
Switch to GPT-5.5
GPT-5.5 streams ~81 tokens/sec to Claude Fable 5's ~62 at a comparable blended cost ($11.25 per million tokens). Use it when iteration speed matters more than squeezing out the last point of quality.
Switch to Claude Opus 4.8
Claude Opus 4.8 is the nearest Anthropic sibling — same house style, lower price point ($10 versus $20 blended per million tokens). The natural swap when you want to stay in the family.
What you pay for Claude Fable 5
Claude Fable 5 is billed per token at the rates below — the same billing tables the Usage page charges against, so this page cannot quote a different price than you pay.
Blended cost (3:1 input:output, the shape of a typical coding session) works out to $20 per million tokens.
| Per 1M tokens | Input | Output | Cache read |
|---|---|---|---|
| All requests | $10.00 | $50.00 | $1.00 |
In Command Code: caching and taste-1
Two things change the experience of using this model inside Command Code versus calling it directly through the upstream API.
First, prompt caching is on by default. In an agent loop the same context is read across many steps; cache reads are billed at $1.00 per million tokens versus $10.00 for fresh input.
Second, taste-1 sits between the model and the agent loop, rewriting and reranking candidate edits to match your codebase conventions.
Plan availability
Claude Fable 5 is a premium model — it needs the Provider plan or higher. Not on the Go plan ($1/mo, open-source models only).
Command Code is a subscription with model usage at API rates. Each plan ships with monthly LLM credits; credits roll over and never expire, and auto top-up keeps you running if you go over.
| Plan | Price/mo | LLM credits | Models |
|---|---|---|---|
| Go | $1 | $10 | Open-source only |
| Pro | $15 | $30 | Open-source + premium |
| Provider | $15 | Pay as you go | Open-source + premium |
| Max 10× | $100 | $150 | Open-source + premium |
| Max 20× | $200 | $300 | Open-source + premium |
| Teams Pro | $40 / seat | $40 / seat | Open-source + premium |
| Enterprise | Custom | Custom | Custom pool, SSO, audit logs |
Switching models with /model
In an interactive Command Code session, run /model to open the model selector. Pick Claude Fable 5 and it applies to this session and to future sessions until you change it again. Premium models require Pro or higher; open-source models are available on every plan, including Go.
cmd # start an interactive session
/model # open the selector and pick Claude Fable 5All Command Code models, ranked by quality and speed
Quality is the Intelligence Index — an aggregate score across reasoning, math, coding, and knowledge evaluations. Speed is measured output tokens per second. Models without a published score are noted. This table is regenerated from the model registry, so it is always current.
| Model | Tier | Intelligence Index | Output speed |
|---|---|---|---|
| Claude Fable 5 (this page) | Premium | 59.9 | ~62 tok/s |
| GPT-5.6 Sol | Premium | 58.9 | ~77 tok/s |
| Claude Opus 4.8 | Premium | 55.7 | ~55 tok/s |
| GPT-5.6 Terra | Premium | 55 | ~155 tok/s |
| GPT-5.5 | Premium | 54.8 | ~81 tok/s |
| Grok 4.5 | Open-source | 53.8 | ~114 tok/s |
| Claude Opus 4.7 | Premium | 53.5 | ~52 tok/s |
| Claude Sonnet 5 | Premium | 53.4 | ~79 tok/s |
| GPT-5.4 | Premium | 51.4 | ~164 tok/s |
| GPT-5.6 Luna | Premium | 51.2 | ~234 tok/s |
| GLM-5.2 | Open-source | 51.1 | ~208 tok/s |
| Muse Spark 1.1 | Premium | 50.6 | ~130 tok/s |
| Gemini 3.5 Flash | Premium | 50.2 | ~236 tok/s |
| Claude Sonnet 4.6 | Premium | 47.2 | ~55 tok/s |
| Qwen 3.7 Max | Open-source | 46 | ~196 tok/s |
| MiniMax M3 | Open-source | 44.4 | ~113 tok/s |
| DeepSeek V4 Pro | Open-source | 44.3 | ~62 tok/s |
| GPT-5.3 Codex | Premium | 44.3 | ~106 tok/s |
| Kimi K2.6 | Open-source | 44.2 | ~43 tok/s |
| MiMo V2.5 Pro | Open-source | 42.2 | ~56 tok/s |
| Kimi K2.7 Code | Open-source | 41.9 | ~46 tok/s |
| Tencent Hy3 | Open-source | 41.2 | ~58 tok/s |
| DeepSeek V4 Flash | Open-source | 40.3 | ~106 tok/s |
| GLM-5.1 | Open-source | 40.2 | ~81 tok/s |
| Qwen 3.6 Max Preview | Open-source | 40 | ~46 tok/s |
| GPT-5.4 Mini | Premium | 40 | ~171 tok/s |
| Qwen 3.6 Plus | Open-source | 39.6 | ~53 tok/s |
| GLM-5 | Open-source | 39.5 | ~51 tok/s |
| Qwen 3.7 Plus | Open-source | 39 | ~52 tok/s |
| Kimi K2.5 | Open-source | 38.1 | ~51 tok/s |
| MiniMax M2.7 | Open-source | 38.1 | ~49 tok/s |
| Nemotron 3 Ultra | Open-source | 37.8 | ~204 tok/s |
| MiMo V2.5 | Open-source | 37.2 | ~88 tok/s |
| MiniMax M2.5 | Open-source | 33.7 | ~78 tok/s |
| Step 3.7 Flash | Open-source | 30.3 | ~407 tok/s |
| Step 3.5 Flash | Open-source | 26 | ~207 tok/s |
| Gemini 3.1 Flash Lite | Premium | 25 | ~300 tok/s |
| Claude Haiku 4.5 | Premium | 23.7 | ~103 tok/s |
| Kimi K3 | Open-source | Not yet scored | — |
| Kimi K2.7 Code HighSpeed | Open-source | Not yet scored | — |
| GLM-5.2 Fast | Open-source | Not yet scored | — |
| Inkling | Open-source | Not yet scored | — |
| Fugu Ultra | Premium | Not yet scored | — |
Frequently asked questions
Claude Fable 5 or GPT-5.6 Sol?
GPT-5.6 Sol is about 44% cheaper blended ($11.25 vs $20 per million tokens), scoring 58.9 on the Intelligence Index. Use GPT-5.6 Sol for volume work and Claude Fable 5 where its edge earns the difference.
How much does Claude Fable 5 cost in Command Code?
$10.00 per million input tokens and $50.00 per million output tokens, with cache reads at $1.00. In an agent loop, cached context brings effective input to roughly $3.70 per million tokens.
What plan do I need for Claude Fable 5?
Claude Fable 5 requires the Provider plan or higher. The Go plan ($1/mo) covers open-source models only.
How good is Claude Fable 5 at coding?
Claude Fable 5 scores 76.5 on the Coding Index — the Artificial Analysis sub-score most predictive of coding-agent performance — alongside 59.9 overall.
Does Claude Fable 5 support image input and reasoning?
Yes — Claude Fable 5 accepts image input alongside text. It supports reasoning with selectable effort (low, medium, high, xhigh, max).
Which Command Code model should I use?
Claude Fable 5 currently leads the lineup on the Intelligence Index (59.9). Grok 4.5 (53.8) leads the open-weights tier, available on every plan. For fast lookups, Step 3.7 Flash streams ~407 tok/s. There is no single right answer — switch per session with /model and let the task pick the model.
Can I mix Claude Fable 5 with other models in a workflow?
Yes. Switch per session using /model. Common pattern: keep a default model and switch up for hard problems or down for quick lookups as the task calls for it.
Should I use Fable 5 or Opus 4.8?
Opus 4.8 is the flagship for most hard agentic work, at half the price. Fable 5 is the most capable Claude, reserved for the very hardest reasoning where capability dominates cost. Switch with /model per task.
Why is Fable 5 not on the Intelligence Index?
Public aggregate benchmarks have not yet been re-run for Fable 5 in the current Intelligence Index format. The model is available and routed normally.
Why is Fable 5 priced above Opus?
Fable 5 sits above the Opus tier as Anthropic's most capable model, so it carries a premium $10/$50 rate. Prompt caching (cache reads at $1.00/M) and taste-1 reduce the effective cost in an agent loop.
Is Command Code free to try?
The Go plan starts at $1/mo with $10 in LLM credits. It covers open-source models only. Pro at $15/mo unlocks premium models with $30 in LLM credits.
Does Command Code train on my code?
No. Command Code does not train on your code or store your code snippets. taste-1 data is stored locally in your project directory.
Where can I track my usage?
The Usage page in Studio shows per-request cost, token counts, and which model ran. Settings > Billing lets you change plans, buy credits, or enable auto top-up.
Does Command Code replace my editor?
No. Command Code is editor-agnostic — it runs as a CLI and works alongside any editor (Cursor, VS Code, Zed, JetBrains, Neovim, etc.).
Related reading
- Claude Opus 4.8 in Command Codemost intelligent Opus for agents and coding
- Claude Opus 4.7 in Command Codeprev flagship, still strong for agents and coding
- Claude Sonnet 5 in Command Codebest combo of speed & intelligence (recommended)
- GPT-5.6 Sol in Command Codefrontier model for complex professional work
- Every model, one referenceThe docs list of all Command Code models with ids and context windows.
- Pricing, limits, and dealsThe canonical price table, running deals, and usage estimates.
Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.