Price book 2026-10-22
AI model pricing
1,982 models from 39 providers: the labs' text and embedding models, open-weight models on every major host and cloud, and image, video, speech and transcription models, each priced the way its provider bills. The same price book powers the open-source SDKs. Download it as prices.json or follow every change.
22 models. Clear
| Model | Provider | Type | Price | Status |
|---|---|---|---|---|
| amazon.nova-2-5-sonic | Amazon Bedrock | Realtime voice | $0.33 in · $2.75 out per 1M | |
| amazon.nova-2-sonic-v1:0 | Amazon Bedrock | Realtime voice | $0.33 in · $2.75 out per 1M | |
| gemini-2.5-flash-native-audio-latest | Google Gemini | Realtime voice | $0.50 in · $2.00 out per 1M | |
| gemini-2.5-flash-native-audio-preview-09-2025 | Google Gemini | Realtime voice | $0.50 in · $2.00 out per 1M | |
| gemini-3.5-live-translate-preview | Google Gemini | Realtime voice | $3.50 in · $21.00 out per 1M | |
| gemini-3.8-live | Google Gemini | Realtime voice | $0.75 in · $4.50 out per 1M | |
| gemini-3.8-live-extended-thinking | Google Gemini | Realtime voice | $0.75 in · $4.50 out per 1M | |
| gemini-live-2.5-flash-preview-native-audio-09-2025 | Google Gemini | Realtime voice | $0.50 in · $2.00 out per 1M | |
| gpt-live-1 | OpenAI | Realtime voice | $0.05 per minute | |
| gpt-realtime-1.5 | OpenAI | Realtime voice | $4.00 in · $16.00 out per 1M | |
| gpt-realtime-2 | OpenAI | Realtime voice | $4.00 in · $24.00 out per 1M | |
| gpt-realtime-2.1 | OpenAI | Realtime voice | $4.00 in · $24.00 out per 1M | |
| gpt-realtime-2.1-mini | OpenAI | Realtime voice | $0.60 in · $2.40 out per 1M | |
| gpt-realtime-translate | OpenAI | Realtime voice | $0.034 per minute | |
| grok-voice-2.0 | xAI | Realtime voice | $0.08 per minute | |
| grok-voice-3.0 | xAI | Realtime voice | $0.08 per minute | |
| grok-voice-latest | xAI | Realtime voice | $0.08 per minute | |
| gemini-2.5-flash-native-audio-preview-12-2025 | Google Gemini | Realtime voice | $0.50 in · $2.00 out per 1M | Retires 2026-11-17 |
| gemini-3.1-flash-live-preview | Google Gemini | Realtime voice | $0.75 in · $4.50 out per 1M | Retires 2026-11-17 |
| gpt-4o-mini-realtime-preview-2024-12-17 | OpenAI | Realtime voice | $0.60 in · $2.40 out per 1M | Retires 2027-01-20 |
| gpt-realtime | OpenAI | Realtime voice | $4.00 in · $16.00 out per 1M | Retires 2027-01-20 |
| gpt-realtime-mini | OpenAI | Realtime voice | $0.60 in · $2.40 out per 1M | Retires 2027-01-20 |
Token rates in USD per million tokens; other models per image, second, minute, character, query or page as noted. Sources: each provider's pricing page and LiteLLM's MIT-licensed price file, with Veqen's verified rules for caching, tiers and residency.