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.
74 models. Clear
| Model | Provider | Type | Price | Status |
|---|---|---|---|---|
| Cohere-embed-v3-english | Azure AI Foundry | Embeddings | $0.10 per 1M tokens | |
| Cohere-embed-v3-multilingual | Azure AI Foundry | Embeddings | $0.10 per 1M tokens | |
| embed-v-4-0 | Azure AI Foundry | Embeddings | $0.12 per 1M tokens | |
| amazon.nova-2-multimodal-embeddings-v1:0 | Amazon Bedrock | Embeddings | $0.135 per 1M tokens | |
| amazon.titan-embed-g1-text-02 | Amazon Bedrock | Embeddings | $0.10 per 1M tokens | |
| amazon.titan-embed-image-v1 | Amazon Bedrock | Embeddings | $0.80 per 1M tokens | |
| amazon.titan-embed-text-v1 | Amazon Bedrock | Embeddings | $0.10 per 1M tokens | |
| amazon.titan-embed-text-v2:0 | Amazon Bedrock | Embeddings | $0.02 per 1M tokens | |
| cohere.embed-english-v3 | Amazon Bedrock | Embeddings | $0.10 per 1M tokens | |
| cohere.embed-multilingual-v3 | Amazon Bedrock | Embeddings | $0.10 per 1M tokens | |
| cohere.embed-v4:0 | Amazon Bedrock | Embeddings | $0.12 per 1M tokens | |
| twelvelabs.marengo-embed-3-0-v1:0 | Amazon Bedrock | Embeddings | — per 1M tokens | |
| embed-english-light-v3.0 | Cohere | Embeddings | $0.10 per 1M tokens | |
| embed-english-v3.0 | Cohere | Embeddings | $0.10 per 1M tokens | |
| embed-multilingual-light-v3.0 | Cohere | Embeddings | $100.00 per 1M tokens | |
| embed-multilingual-v3.0 | Cohere | Embeddings | $0.10 per 1M tokens | |
| embed-v4.0 | Cohere | Embeddings | $0.12 per 1M tokens | |
| embed-v5.0-fast | Cohere | Embeddings | $0.08 per 1M tokens | |
| embed-v5.0-pro | Cohere | Embeddings | $0.12 per 1M tokens | |
| databricks-bge-large-en | Databricks | Embeddings | $0.10 per 1M tokens | |
| databricks-gte-large-en | Databricks | Embeddings | $0.13 per 1M tokens | |
| databricks-qwen3-embedding-0-6b | Databricks | Embeddings | $0.02 per 1M tokens | |
| accounts/fireworks/models/qwen3-embedding-0p6b | Fireworks AI | Embeddings | $0.00 per 1M tokens | |
| accounts/fireworks/models/qwen3-embedding-4b | Fireworks AI | Embeddings | $0.00 per 1M tokens | |
| accounts/fireworks/models/qwen3-embedding-8b | Fireworks AI | Embeddings | $0.10 per 1M tokens | |
| gemini-embedding-2 | Google Gemini | Embeddings | $0.20 per 1M tokens | |
| gemini-embedding-2-preview | Google Gemini | Embeddings | $0.20 per 1M tokens | |
| codestral-embed | Mistral | Embeddings | $0.15 per 1M tokens | |
| codestral-embed-2505 | Mistral | Embeddings | $0.15 per 1M tokens | |
| mistral-embed | Mistral | Embeddings | $0.10 per 1M tokens | |
| mistral-embed-2312 | Mistral | Embeddings | $0.10 per 1M tokens | |
| BAAI/bge-en-icl | Nebius | Embeddings | $0.01 per 1M tokens | |
| BAAI/bge-multilingual-gemma2 | Nebius | Embeddings | $0.01 per 1M tokens | |
| intfloat/e5-mistral-7b-instruct | Nebius | Embeddings | $0.01 per 1M tokens | |
| Qwen/Qwen3-Embedding-8B | Nebius | Embeddings | $0.01 per 1M tokens | |
| baai/bge-m3 | Novita AI | Embeddings | $0.01 per 1M tokens | |
| qwen/qwen3-embedding-0.6b | Novita AI | Embeddings | $0.07 per 1M tokens | |
| qwen/qwen3-embedding-8b | Novita AI | Embeddings | $0.07 per 1M tokens | |
| text-embedding-3-large | OpenAI | Embeddings | $0.13 per 1M tokens | |
| text-embedding-3-small | OpenAI | Embeddings | $0.02 per 1M tokens | |
| text-embedding-ada-002 | OpenAI | Embeddings | $0.10 per 1M tokens | |
| text-embedding-ada-002-v2 | OpenAI | Embeddings | $0.10 per 1M tokens | |
| pplx-embed-context-v1-0.6b | Perplexity | Embeddings | $0.008 per 1M tokens | |
| pplx-embed-context-v1-4b | Perplexity | Embeddings | $0.05 per 1M tokens | |
| pplx-embed-v1-0.6b | Perplexity | Embeddings | $0.004 per 1M tokens | |
| pplx-embed-v1-4b | Perplexity | Embeddings | $0.03 per 1M tokens | |
| BAAI/bge-base-en-v1.5 | Together AI | Embeddings | $0.008 per 1M tokens | |
| voyage-2 | Voyage AI | Embeddings | $0.10 per 1M tokens | |
| voyage-3 | Voyage AI | Embeddings | $0.06 per 1M tokens | |
| voyage-3-large | Voyage AI | Embeddings | $0.18 per 1M tokens | |
| voyage-3-lite | Voyage AI | Embeddings | $0.02 per 1M tokens | |
| voyage-3.5 | Voyage AI | Embeddings | $0.06 per 1M tokens | |
| voyage-3.5-lite | Voyage AI | Embeddings | $0.02 per 1M tokens | |
| voyage-4 | Voyage AI | Embeddings | $0.06 per 1M tokens | |
| voyage-4-large | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-4-lite | Voyage AI | Embeddings | $0.02 per 1M tokens | |
| voyage-code-2 | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-code-3 | Voyage AI | Embeddings | $0.18 per 1M tokens | |
| voyage-code-4 | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-context-3 | Voyage AI | Embeddings | $0.18 per 1M tokens | |
| voyage-context-4 | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-finance-2 | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-large-2 | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-large-2-instruct | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-law-2 | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-lite-01 | Voyage AI | Embeddings | $0.10 per 1M tokens | |
| voyage-lite-02-instruct | Voyage AI | Embeddings | $0.10 per 1M tokens | |
| voyage-multilingual-2 | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-multimodal-3 | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| voyage-multimodal-3.5 | Voyage AI | Embeddings | $0.12 per 1M tokens | |
| Cohere-Embed-V5-Fast | Azure AI Foundry | Embeddings | $0.08 per 1M tokens | Retires 2027-01-23 |
| Cohere-Embed-V5-Pro | Azure AI Foundry | Embeddings | $0.12 per 1M tokens | Retires 2027-01-23 |
| twelvelabs.marengo-embed-2-7-v1:0 | Amazon Bedrock | Embeddings | — per 1M tokens | Retires 2026-11-30 |
| gemini-embedding-001 | Google Gemini | Embeddings | $0.15 per 1M tokens | Retires 2028-05-14 |
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.