Models
2 models approved for your teams; your usual model is Claude Sonnet 4.5.
Parezen API: every model works with your pz_ key (9 models).
Provider
Features
| Compare | ||||||||
|---|---|---|---|---|---|---|---|---|
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.15 | $0.6 | $0.015 | $0.075 | 1,000,000 | 680 ms | 97.4% | |
| DeepSeek V3 deepseek/deepseek-v3 | $0.27 | $1.1 | $0.027000000000000003 | $0.135 | 128,000 | 680 ms | Not measured | |
| Llama 3.3 70B meta/llama-3.3-70b | $0.28 | $0.28 | $0.028000000000000004 | $0.14 | 128,000 | 420 ms | 96.2% | |
| GPT-4.1 mini openai/gpt-4.1-mini | $0.4 | $1.6 | $0.04 | $0.2 | 1,000,000 | 680 ms | Not measured | |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $1 | $5 | $0.1 | $0.5 | 200,000 | 680 ms | Not measured | |
| Gemini 2.5 Pro google/gemini-2.5-pro | $1.25 | $10 | $0.125 | $0.625 | 1,000,000 | 680 ms | Not measured | |
| Mistral Large mistral/mistral-large | $2 | $6 | $0.2 | $1 | 128,000 | 680 ms | Not measured | |
| GPT-4.1 openai/gpt-4.1 | $2 | $8 | $0.2 | $1 | 1,000,000 | 680 ms | Not measured | |
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $3 | $15 | $0.3 | $1.5 | 200,000 | 680 ms | Not measured |
Sample prices per million tokens.