Context budget
See how your prompts and reserved output fill a model's context window.
Context 1.0M, max output 128.0K.
100 to 128.0K tokens
Context used
0.4%4.0K of 1.0M tokens
- System prompt
- User input
- Reserved output
Remaining996.0Ktokens free
Est. cost$0.08per request
More turns100+before the limit
Pricing tierStandardno long-context tier
Cost across featured models
Same request, models that fit it.
- Anthropic
- OpenAI
Token breakdown
| Component | Tokens | Share |
|---|---|---|
| System prompt | 0 | 0.0% |
| User input | 0 | 0.0% |
| Reserved output | 4.0K | 0.4% |
| Free space | 996.0K | 99.6% |