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": 8191, 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": 8191, 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, 21 "outputTokens": 8191, 22 "outputTokenPrice": 6 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": 1, 28 "outputTokens": 8191, 29 "outputTokenPrice": 3 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": 2.7, 35 "outputTokens": 8191, 36 "outputTokenPrice": 8.1 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": 128000, 41 "inputTokenPrice": 3, 42 "outputTokens": 128000, 43 "outputTokenPrice": 9 44 }, 45 "mistral-tiny": { 46 "description": "", 47 "inputTokens": 32000, 48 "inputTokenPrice": 0.25, 49 "outputTokens": 8191, 50 "outputTokenPrice": 0.25 51 }, 52 "mistral-small": { 53 "description": "", 54 "inputTokens": 32000, 55 "inputTokenPrice": 1, 56 "outputTokens": 8191, 57 "outputTokenPrice": 3 58 }, 59 "mistral-medium": { 60 "description": "", 61 "inputTokens": 32000, 62 "inputTokenPrice": 2.7, 63 "outputTokens": 8191, 64 "outputTokenPrice": 8.1 65 }, 66 "codestral-latest": { 67 "description": "", 68 "inputTokens": 32000, 69 "inputTokenPrice": 1, 70 "outputTokens": 8191, 71 "outputTokenPrice": 3 72 }, 73 "open-mistral-nemo": { 74 "description": "https:\/\/mistral.ai\/technology\/", 75 "inputTokens": 128000, 76 "inputTokenPrice": 0.3, 77 "outputTokens": 128000, 78 "outputTokenPrice": 0.3 79 }, 80 "open-codestral-mamba": { 81 "description": "https:\/\/mistral.ai\/technology\/", 82 "inputTokens": 256000, 83 "inputTokenPrice": 0.25, 84 "outputTokens": 256000, 85 "outputTokenPrice": 0.25 86 }, 87 "codestral-mamba-latest": { 88 "description": "https:\/\/mistral.ai\/technology\/", 89 "inputTokens": 256000, 90 "inputTokenPrice": 0.25, 91 "outputTokens": 256000, 92 "outputTokenPrice": 0.25 93 } 94 }, 95 "embedding": { 96 "mistral-embed": { 97 "description": "State-of-the-art semantic for extracting representation of text extracts. English only for now.", 98 "inputTokens": 8192, 99 "inputTokenPrice": 0.1, 100 "dimensions": 1024 101 } 102 } 103}