{ "chat": { "open-mistral-7b": { "description": "Our very first. A 7B transformer model, fast-deployed and easily customisable. Small, yet very powerful for a variety of use cases. English and code.", "inputTokens": 32000, "inputTokenPrice": 0.25, "outputTokens": 4096, "outputTokenPrice": 0.25 }, "open-mixtral-8x7b": { "description": "Currently the best open model. A 7B sparse Mixture-of-Experts (SMoE). Uses 12B active parameters out of 45B total. Fluent in English, French, Italian, German, Spanish, and strong in code.", "inputTokens": 32000, "inputTokenPrice": 0.7, "outputTokens": 4096, "outputTokenPrice": 0.7 }, "mistral-small-latest": { "description": "Cost-efficient reasoning for low-latency workloads. Fluent in English, French, Italian, German, Spanish, and strong in code.", "inputTokens": 32000, "inputTokenPrice": 2.00, "outputTokens": 4096, "outputTokenPrice": 6.00 }, "mistral-medium-latest": { "description": "Balanced reasoning for a wide range of tasks. Fluent in English, French, Italian, German, Spanish, and strong in code.", "inputTokens": 32000, "inputTokenPrice": 2.70, "outputTokens": 4096, "outputTokenPrice": 8.10 }, "mistral-large-latest": { "description": "Top-tier reasoning for high-complexity tasks. Fluent in English, French, Italian, German, Spanish, and strong in code.", "inputTokens": 32000, "inputTokenPrice": 8.00, "outputTokens": 4096, "outputTokenPrice": 24.00 } }, "embedding": { "mistral-embed": { "description": "State-of-the-art semantic for extracting representation of text extracts. English only for now.", "inputTokenPrice": 0.10, "inputTokens": 4096 } } }