claude-haiku-4-5
Availability100.0%
Available
Samples: 16
Latency5.2 s
- Input / 1M tokens
- $1
- Output / 1M tokens
- $5
- Context window
- 200,000
- Route
- Default
Roleplay
6.1/10Aggregated from multiple sources and calculated with our in-house algorithm. For reference only.
Source: LiveBench · WritingBench (Apache-2.0) · LMArena (CC BY 4.0)
Rescaled to the models on this site.
Routes
Aggregated from multiple sources and calculated with our in-house algorithm. For reference only.
| Use this model | |||||||
|---|---|---|---|---|---|---|---|
| claude-haiku-4-5 | claude_special | $0.3 | $1.5 | $0.03 | 6.1/10 | 6.8/10 | Roleplay API pricing |
| claude-haiku-4-5 | nova_special | $0.3 | $1.5 | $0.03 | 6.1/10 | 6.8/10 | Roleplay API pricing |
| claude-haiku-4-5 | Default | $1 | $5 | $0.1 | 6.1/10 | 3.6/10 | Use this model |
| claude-haiku-4-5 | claude_official | $1.2 | $6 | $0.12 | 6.1/10 | 3.2/10 | Roleplay API pricing |
| claude-haiku-4-5-thinking | nova_special | $0.3 | $1.5 | $0.03 | 6.1/10 | 6.8/10 | Roleplay API plans |
| claude-haiku-4-5-thinking | Default | $1 | $5 | $0.1 | 6.1/10 | 3.6/10 | Use this model |
Quick start
Free and Plus roleplay modelscurl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
-H "Authorization: Bearer $TOKENREPLY_API_KEY" \
-H 'Content-Type: application/json' \
--data '{
"model": "claude-haiku-4-5",
"messages": [
{
"role": "user",
"content": "Reply with hello."
}
]
}'