Models for roleplay
Editorial picks, not a benchmark ranking.
4Curated picks
4 models
- Context
- 1M
- Input / 1M
$1.575$0.788- Output price
$7.875$3.938 /1M- Max output
- 66K
- Accepts
- Context
- 1M
- Input / 1M
- $0.158
- Output price
- $0.525 /1M
- Max output
- 131K
- Accepts
- Context
- 1.1M
- Input / 1M
- $0.21
- Output price
- $1.26 /1M
- Max output
- 128K
- Accepts
- Context
- 1M
- Input / 1M
- $0.137
- Output price
- $0.273 /1M
- Max output
- 384K
- Accepts
Reliability
Reliability notes
No failover
Some of these have nowhere to fail over to.
GLM 5.3 Flash, GPT 5.6 Luna, DeepSeek V4 Flash 0731, Gemini 3.8 Flash are served by a single registered upstream. If it goes offline, they are unavailable until it recovers. How failover works.
Next