About

Drafted from the provider's own page.

If you're unsure which model to use, start with Claude Opus 5 for most workloads. Use Claude Fable 5.1 for demanding reasoning and long-horizon agentic work, or when your evals on Claude Opus 5 at higher effort still fall short.

open weights: no
best for: computeextractioncoding

Capabilities

What the model accepts and returns, where a probe through our own gateway proved it.

streaming
tools
json mode
vision
audio

Providers

What you pay through us for each provider, and its own list price where that differs.

Sort by

1 shown

Anthropic
anthropic/claude-fable-5
input /M
$10.00
output /M
$50.00
Cache read $1.00/M · Cache write $20.00/M (1 hour), $12.50/M (5 min)
cache read list price /M
$1.00
Web search
$0.01 per request
The provider's list price. We do not charge for searches yet.
1.0M context128K max out

Speed

24 hours7 days30 days

fastest over 24 hours: 36.0 t/s

Anthropic2,123 ms to first token36.0 t/smedian of 24

Served

24 hours7 days30 days

served in the last 24 hours: 100.00%

Anthropic100.00% · 24 of 24

Rebuilt once a day from the requests we sent, so it is a daily figure and not a live one.

not yet

Not yet. These figures come from Artificial Analysis, which the publish pipeline reads once a day.

Integrations

What the model holds, rather than a compatibility grade: nothing here measures how well a particular tool gets on with it, so nothing here scores one.

answers on: chat completions
accepts: textimagepdf
returns: text

request parameters it takes

reasoning
response_format
tool_choice
tools

Use this model

Works with the OpenAI SDK. Point it at our base URL and use this id.

curl https://api.hopscotchlabs.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-fable-5",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 256
  }'