1{ 2 "chat": { 3 "open-mistral-7b": { 4 "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.", 5 "inputTokens": 32000, 6 "inputTokenPrice": 0.25, 7 "outputTokens": 4096, 8 "outputTokenPrice": 0.25 9 }, 10 "open-mixtral-8x7b": { 11 "description": "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.", 12 "inputTokens": 32000, 13 "inputTokenPrice": 0.7, 14 "outputTokens": 4096, 15 "outputTokenPrice": 0.7 16 }, 17 "open-mixtral-8x22b": { 18 "description": "A 22B sparse Mixture-of-Experts (SMoE). Uses only 39B active parameters out of 141B. Fluent in English, French, Italian, German, Spanish, and strong in code.", 19 "inputTokens": 64000, 20 "inputTokenPrice": 2.0, 21 "outputTokens": 4096, 22 "outputTokenPrice": 6.0 23 }, 24 "mistral-small-latest": { 25 "description": "Cost-efficient reasoning for low-latency workloads. Fluent in English, French, Italian, German, Spanish, and strong in code.", 26 "inputTokens": 32000, 27 "inputTokenPrice": 2.00, 28 "outputTokens": 4096, 29 "outputTokenPrice": 6.00 30 }, 31 "mistral-medium-latest": { 32 "description": "Balanced reasoning for a wide range of tasks. Fluent in English, French, Italian, German, Spanish, and strong in code.", 33 "inputTokens": 32000, 34 "inputTokenPrice": 2.70, 35 "outputTokens": 4096, 36 "outputTokenPrice": 8.10 37 }, 38 "mistral-large-latest": { 39 "description": "Top-tier reasoning for high-complexity tasks. Fluent in English, French, Italian, German, Spanish, and strong in code.", 40 "inputTokens": 32000, 41 "inputTokenPrice": 8.00, 42 "outputTokens": 4096, 43 "outputTokenPrice": 24.00 44 } 45 }, 46 "embedding": { 47 "mistral-embed": { 48 "description": "State-of-the-art semantic for extracting representation of text extracts. English only for now.", 49 "inputTokenPrice": 0.10, 50 "inputTokens": 4096, 51 "dimensions": 1024 52 } 53 } 54} 55