Claude Fable 5
Anthropic · released Jun 9, 2026
- Type
- Proprietary
- Input
- $10.00
- Output
- $50.00
- Cached
- $1.00
List price · per 1M tokens · Anthropic at 1M context · source ↗
Our take
Written Aug 3, 2026Claude Fable 5 is Anthropic's flagship text model that can handle up to one million tokens in a single request. It scores strongly across coding, mathematics and instruction-following tasks, though it is available only through hosted APIs rather than as a download.
Pick this for long-document work at one million tokens, coding and web development where it holds our highest arena score, or multi-step math and precise instruction-following. Skip it if you need local hosting, cannot afford premium rates, or need consistent throughput without provider shopping.
The case for it
- Top-tier coding performance, especially web development: its arena score for this task is the highest we hold in our entire catalogue.
- Strong across every measured arena category with no weak flank, from creative writing to mathematics.
- One-million-token request limit is nearly four times the next longest context length in our data.
- Pricing is consistent across most providers, with seven of eight offers at the identical rate.
The case against it
- No budget tier available: every tracked offer sits at the same premium price point with no discount provider.
- Throughput varies more than twofold depending on which host you choose, from 24 to 56 tokens per second.
- Parameter count and architecture are undisclosed, so there is no basis for efficiency claims against downloadable rivals.
How good is it?
IntelligencePuzzles, maths, exam questions
Arena Text (overall)1st of 143 · 1508.6
CodingWriting and fixing code on its own
Arena Coding1st of 143 · 1552.8
AgenticPlanning, calling tools, staying on task
Arena Agent (IPS)1st of 36 · 0.126via High
WritingWe do not rate this
Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage. So we show where Claude Fable 5 placed and give it no mark out of five.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Every published score for this model16 scoresEvery figure we hold, from 16 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Or rent it from someone else
Why this differs from the header. The strip above quotes Anthropic's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $10.00 in / $50.00 out
- Context served
- 1M
- Throughput
- ~39 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| Amazon Bedrock | $10.00 / $50.00 | 1M | 39 tok/s | No | No | Unknown |
| DeepInfra | $10.00 / $50.00 | 1M | not measured | Unknown | Unknown | Unknown |
| Microsoft Azure AI | $10.00 / $50.00 | 1M | 34 tok/s | No | No | Unknown |
| OpenRouter | $10.00 / $50.00 | 1M | not measured | Unknown | Unknown | Unknown |
| Google Vertex AIglobal | $10.00 / $50.00 | 1M | 31 tok/s | No | No | Unknown |
| Anthropic | $10.00 / $50.00 | 1M128K out | 34 tok/s | No | Yes30 days | Unknown |
| Amazon Bedrockclaude-on-aws | $10.00 / $50.00 | 1M | 15 tok/s | No | No | Unknown |
| Google Vertex AIeurope | $11.00 / $55.00 | 1M | 24 tok/s | No | No | Unknown |
DeepInfra
Microsoft Azure AI
OpenRouter
Google Vertex AIAcross the 8 listings we hold: 6 say they do not train on prompts, 0 say they do and 2 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| Amazon Bedrock | ✓ | ✓ | ✓ |
| DeepInfra | |||
| Microsoft Azure AI | ✓ | ✓ | ✓ |
| OpenRouter | ✓ | ✓ | ✓ |
| Google Vertex AIglobal | ✓ | ✓ | ✗ |
| Anthropic | ✓ | ✓ | ✓ |
| Amazon Bedrockclaude-on-aws | ✓ | ✓ | ✓ |
| Google Vertex AIeurope | ✓ | ✓ | ✗ |
Tool calling: 7 of 8 listings say yes, 1 publishes no parameter list. JSON output: 7 of 8 listings say yes, 1 publishes no parameter list. Strict schema: 5 of 8 listings say yes, 2 say no, 1 publishes no parameter list.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- 1 of 8 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 2 of 8 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text+image+file->text
- Catalogue slug
- anthropic-claude-fable-5