Documentation
Models
If unsure where to start, use claude-sonnet-5. For maximum power use claude-opus-5, and for creative work use claude-fable-5. All 9 models share one key and balance.
Current models
Full pricingPrices per 1M tokens.
NEW
Claude Fable 5
creative writing, storytelling, roleplay
Input price$5.00 / MTok
Output price$25.00 / MTok
SpeedThoughtfully
Context200K
NEW
Claude Opus 5
complex tasks, long context, agents
Input price$2.50 / MTok
Output price$12.50 / MTok
SpeedPowerful
Context1M
OPUS
Claude Opus 4.8
complex tasks, long context, agents
Input price$2.50 / MTok
Output price$12.50 / MTok
SpeedPowerful
Context200K
OPUS
Claude Opus 4.7
complex tasks, long context, agents
Input price$2.50 / MTok
Output price$12.50 / MTok
SpeedPowerful
Context200K
OPUS
Claude Opus 4.6
complex tasks, long context, agents
Input price$2.50 / MTok
Output price$12.50 / MTok
SpeedPowerful
Context200K
OPUS
Claude Opus 4.5
complex tasks, long context, agents
Input price$2.50 / MTok
Output price$12.50 / MTok
SpeedPowerful
Context200K
NEW
Claude Sonnet 5
daily coding and speed/quality balance
Input price$1.00 / MTok
Output price$5.00 / MTok
SpeedFast
Context200K
FAST
Claude Sonnet 4.6
daily coding and speed/quality balance
Input price$1.50 / MTok
Output price$7.50 / MTok
SpeedFast
Context200K
FAST
Claude Sonnet 4.5
daily coding and speed/quality balance
Input price$1.50 / MTok
Output price$7.50 / MTok
SpeedFast
Context200K
All available model IDs
claude-fable-5claude-opus-5claude-opus-4-8claude-opus-4-7claude-opus-4-6claude-opus-4-5claude-sonnet-5claude-sonnet-4-6claude-sonnet-4-5Which model to choose?
Choose by task, not benchmark. To switch, just change the model field.
| Task | Model | Why |
|---|---|---|
| Creative writing & storytelling | claude-fable-5 | Expressiveness and nuanced dialogue |
| Complex tasks & reasoning | claude-opus-5 | Maximum power for hard problems |
| Daily coding & vibe coding | claude-sonnet-4-6 | Best price/quality balance |
| Fast completions & autocomplete | claude-sonnet-4-5 | A stable Sonnet version for everyday work |
Model FAQ
Which model is best for coding?
Sonnet 5 is the best choice for most coding tasks. For complex architecture decisions and long-running agents, use Opus 5.
What is vibe coding and which model to use?
Vibe coding is development where you describe the task in natural language and the model writes the code. Use Sonnet 4.6 in Cursor, Claude Code, or Cline.
Which Claude models are available?
Claude Fable 5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Opus 4.5, Claude Sonnet 5, Claude Sonnet 4.6, and Claude Sonnet 4.5 are available.
How do I switch between models?
Just change the model field. The API key and balance are shared across all 9 models.