Claude Fable 5Chat
Anthropic's highest-capability generally available model for long-running agents.
2 rails1M ctx$0.112typical$11.20 → $56.00 /MTok
Playground
Providers
| Provider | Role | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|---|
| ggmicloudNo trainingNo training on your data | Primary | 262K | $0.29 / $0.73/MToksame price, any rail | 2.4s | 3.0s | 100% |
| ddeepinfraNo trainingNo training on your data | Fallback | 262K | — | — | — |
Routing controls
Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.002/req
- Input
- $0.29/M tok
- Cached input
- $0.16/M tok
- Output
- $0.73/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
hy3
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hy3",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingresponse_format
FAQ
What is HY3?
Tencent's reasoning and coding model on two independently operated, live-tested rails.
How much does HY3 cost?
HY3 costs $0.29/M input tokens and $0.73/M output tokens.
What inputs and outputs does HY3 support?
HY3 accepts text and returns text.
How do I call HY3?
POST /api/v1/chat/completions with `"model": "hy3"`.