Claude Fable 5.1
Claude Fable 5.1 by Anthropic: $10 per 1M input and $50 per 1M output tokens, 1M context. Call it with one OpenAI-compatible API key, compare it with similar models, start free.
Claude Fable 5.1 is served by Anthropic and called through odnoga on /v1/chat/completions, in the same OpenAI-compatible shape every other model on that endpoint uses. It is a reasoning model, so it spends extra output tokens working through a problem before answering — budget for higher output cost on hard tasks. It accepts images alongside text. It supports tool and function calling. It can be forced to return structured JSON. Its 1M-token context window sets how much input you can send in one request. Cached input is billed at $0.25 per 1M tokens, so repeated prefixes cost less.
Specification and price
| Vendor | Anthropic |
|---|---|
| Model ID | claude-fable-5-1 |
| Context window | 1M tokens |
| Max output | 128K tokens |
| Served on | /v1/chat/completions |
| Capabilities | Reasoning, Reads images, Tool calling, JSON schema, Streaming, Web search, Prompt caching, Batch |
| Per 1M tokens | Vendor cost | Your price on Free+7% |
|---|---|---|
| Input | $10 | $10.75 |
| Output | $50 | $53.76 |
| Cached input | $0.25 | $0.269 |
Vendor cost is the list price per million tokens as recorded in the odnoga catalog; your price applies your plan margin with the same formula that bills every request — see pricing. Pricing
Call it through odnoga
const res = await fetch("https://api.odnoga.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.ODNOGA_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "claude-fable-5-1",
messages: [{ role: "user", content: "Hello" }],
}),
});
One endpoint, one key, one bill — /v1/chat/completions takes the same shape whichever vendor is behind it. Swap the model id and odnoga handles keys, routing, limits and cost accounting.
What Claude Fable 5.1 can do
Everything below is what the model itself supports. Ask for something it does not do and odnoga tells you before the request reaches the provider, instead of returning a worse answer.
Works through a problem step by step before answering, which costs more tokens and buys accuracy on hard tasks.
Send a screenshot, a photo or a scan in the same message as your text.
The model can call functions you define and use what they return.
Answers with valid JSON instead of prose you would have to parse.
Answers in the exact shape you specify, so the response fits your types without a fallback path.
Tokens arrive as they are produced, so your interface can answer immediately.
Can look something up rather than answer from training data alone. Billed per search.
A prompt you send repeatedly is charged at the cached rate, which is a fraction of the input price.
Work that can wait goes through at a lower price.
Beyond text
Send a document and ask about it, without extracting the text yourself first.
Finer control
- Structured outputs · The provider guarantees the schema rather than merely aiming for it.
- Parallel tools · Can call several of your functions in one turn instead of one after another.
How to use Claude Fable 5.1
Reviewed 2026-09-14
Best for
- Long-horizon agentic coding: multi-step refactors, migrations and tool-using coding agents that run for hours
- Multistep research workflows that gather, cross-check and synthesize many sources
- Demanding reasoning and knowledge work where Claude Opus 5 at higher effort still falls short
- Document, spreadsheet and slide work — creating and editing complex office artefacts
- Workloads with heavy prompt caching: cache reads are $0.25/MTok, 75% cheaper than Fable 5
Not the right pick when
- Simple chat, classification or extraction — Claude Sonnet 5 or Haiku 4.5 are far cheaper for that
- Most everyday workloads — Anthropic itself recommends starting with Claude Opus 5 first
- Latency-sensitive interactive features: this is a frontier reasoning model, not a speed pick
- Cost-sensitive high-volume traffic without caching or batch — at $10/$50 per MTok the bill grows fast
Practical tips through odnoga
- 01Pin claude-fable-5-1 in a managed prompt version so a future Fable upgrade never silently changes behaviour
- 02Turn on Anthropic prompt caching for repeated system prompts and tools — cache reads cost $0.25/MTok here
- 03Use the Batch API tier for offline evaluations: it supports batch and cuts cost on large test suites
- 04Run it in the evaluation lab against Opus 5 and Sonnet 5 on your own prompts before committing
- 05Set a per-tenant budget and a cheaper fallback model in odnoga before routing production traffic
- 06Use the effort parameter (low/medium/high/max/xhigh) to trade latency against reasoning depth per call
What a month costs
1,000 calls a month, 10,000 input tokens and 2,000 output tokens each, at your Free price (vendor cost +7%):
| Input (10M tokens) | $108 |
|---|---|
| Output (2M tokens) | $108 |
| Your cost per month on Free | $215 |
Vendor list cost $200 + odnoga margin $15.05 (+7%). Cached input or answer reuse lowers it; odnoga records both numbers per request.
If Claude Fable 5.1 is not the one
Models that take the same kind of input, are priced the same way, and do the closest thing to what this one does. Not a quality ranking — odnoga does not benchmark models.
| Model | Context | Input / 1M | Output / 1M | Capabilities |
|---|---|---|---|---|
| Claude Fable 5.1 | 1M | $10 | $50 | Reasoning, Reads images, Tool calling, JSON schema, Streaming, Web search, Prompt caching, Batch |
| Claude Fable 5 | 1M | $10 | $50 | Reasoning, Reads images, Tool calling, JSON schema, Streaming, Web search, Prompt caching, Batch |
| Claude Opus 4.6 | 1M | $5 | $25 | Reasoning, Reads images, Tool calling, JSON schema, Streaming, Web search, Prompt caching, Batch |
| Claude Opus 4.7 | 1M | $5 | $25 | Reasoning, Reads images, Tool calling, JSON schema, Streaming, Web search, Prompt caching, Batch |
Questions
- What does Claude Fable 5.1 cost?
- $10 per million input tokens and $50 per million output tokens — the same as Fable 5. Cache reads dropped 75% to $0.25 per million tokens; cache writes are $12.50 (5-minute) and $20 (1-hour).
- When should I pick Fable 5.1 over Claude Opus 5?
- Anthropic recommends starting with Opus 5 for most workloads. Pick Fable 5.1 for demanding reasoning and long-horizon agentic work, or when your evals on Opus 5 at higher effort still fall short.
- What is the difference between Fable 5.1 and Mythos 5.1?
- They are the same underlying model with different safeguard levels. Mythos 5.1 is in limited availability; Fable 5.1 is the generally available endpoint.
- Can I switch from Fable 5 to Fable 5.1 without code changes?
- Yes. Through odnoga you change the pinned model in the managed prompt version or pass claude-fable-5-1 as the model parameter — the API shape is unchanged.
All models · Pricing · Docs · Compare models in the evaluation lab
Sources: Anthropic — Introducing Claude Fable 5.1 and Mythos 5.1, Claude Platform Docs — Fable 5.1 overview, Claude Platform Docs — Pricing