Models
One API, a model for every job.
Every Claudech model speaks the same API. Pick the one that fits the job and switch at any time by changing the model name.
- Same request format for every model
- Switch by changing the model name
- One shared token balance
- Models, one API
- 4
- Token context window
- 1M
- Max output tokens
- 131K
- Input per 1M tokens, from
- $0.50
Fast and capable
Claude Opus 5.5
Our balanced everyday model. Strong reasoning with quick responses, ideal for chat, coding and analysis.
- Streaming
- Reasoning
- Vision
- Tool use
- JSON mode
- Model ID
claude-opus-5-5- Context window
- 1M tokens
- Max output
- 66K tokens
- Input / 1M
- $0.50
- Cached input / 1M
- $0.010
- Output / 1M
- $1.90
- Availability
- All plans
- Released
- Sep 2026
Advanced reasoning
Claude Fable 5.2
Our most capable model for complex, multi-step work where quality matters most.
- Streaming
- Reasoning
- Vision
- Tool use
- JSON mode
- Model ID
claude-fable-5-2- Context window
- 1M tokens
- Max output
- 131K tokens
- Input / 1M
- $0.50
- Cached input / 1M
- $0.010
- Output / 1M
- $1.90
- Availability
- All plans
- Released
- Sep 2026
Deep reasoning
Claude Opus 5
Extended thinking for hard problems: mathematics, research synthesis and intricate debugging.
- Streaming
- Reasoning
- Vision
- Tool use
- JSON mode
- Model ID
claude-opus-5- Context window
- 1M tokens
- Max output
- 131K tokens
- Input / 1M
- $0.50
- Cached input / 1M
- $0.010
- Output / 1M
- $1.90
- Availability
- All plans
- Released
- Sep 2026
Fast responses
Claude Sonnet 5.5
Lowest latency for high-volume tasks: classification, extraction, summaries and simple chat.
- Streaming
- Reasoning
- Vision
- Tool use
- JSON mode
- Model ID
claude-sonnet-5-5- Context window
- 1M tokens
- Max output
- 33K tokens
- Input / 1M
- $0.50
- Cached input / 1M
- $0.010
- Output / 1M
- $1.90
- Availability
- All plans
- Released
- Sep 2026
Try every model with one balance
Create an account, add tokens and call any model from chat, the playground or the API.