Current section
Files
Jump to
Current section
Files
priv/models/alibaba.json
[
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qvq-max",
"input_cost": 1.2,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 8192,
"name": "QVQ Max",
"output_cost": 4.8,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-03-25"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 1000000,
"dialect": "openai_completions",
"id": "qwen-flash",
"input_cost": 0.05,
"input_modalities": [
"text"
],
"max_output_tokens": 32768,
"name": "Qwen Flash",
"output_cost": 0.4,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-07-28"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 32768,
"dialect": "openai_completions",
"id": "qwen-max",
"input_cost": 1.6,
"input_modalities": [
"text"
],
"max_output_tokens": 8192,
"name": "Qwen Max",
"output_cost": 6.4,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-04-03"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 32768,
"dialect": "openai_completions",
"id": "qwen-omni-turbo",
"input_cost": 0.07,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 2048,
"name": "Qwen-Omni Turbo",
"output_cost": 0.27,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-01-19"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 32768,
"dialect": "openai_completions",
"id": "qwen-omni-turbo-realtime",
"input_cost": 0.27,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 2048,
"name": "Qwen-Omni Turbo Realtime",
"output_cost": 1.07,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-05-08"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 1000000,
"dialect": "openai_completions",
"id": "qwen-plus",
"input_cost": 0.4,
"input_modalities": [
"text"
],
"max_output_tokens": 32768,
"name": "Qwen Plus",
"output_cost": 1.2,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2024-01-25"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 8192,
"dialect": "openai_completions",
"id": "qwen-plus-character-ja",
"input_cost": 0.5,
"input_modalities": [
"text"
],
"max_output_tokens": 512,
"name": "Qwen Plus Character (Japanese)",
"output_cost": 1.4,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-01"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 1000000,
"dialect": "openai_completions",
"id": "qwen-turbo",
"input_cost": 0.05,
"input_modalities": [
"text"
],
"max_output_tokens": 16384,
"name": "Qwen Turbo",
"output_cost": 0.2,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2024-11-01"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen-vl-max",
"input_cost": 0.8,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 8192,
"name": "Qwen-VL Max",
"output_cost": 3.2,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-04-08"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen-vl-plus",
"input_cost": 0.21,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 8192,
"name": "Qwen-VL Plus",
"output_cost": 0.63,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-01-25"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen2-5-14b-instruct",
"input_cost": 0.35,
"input_modalities": [
"text"
],
"max_output_tokens": 8192,
"name": "Qwen2.5 14B Instruct",
"output_cost": 1.4,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-09"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen2-5-32b-instruct",
"input_cost": 0.7,
"input_modalities": [
"text"
],
"max_output_tokens": 8192,
"name": "Qwen2.5 32B Instruct",
"output_cost": 2.8,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-09"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen2-5-72b-instruct",
"input_cost": 1.4,
"input_modalities": [
"text"
],
"max_output_tokens": 8192,
"name": "Qwen2.5 72B Instruct",
"output_cost": 5.6,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-09"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen2-5-7b-instruct",
"input_cost": 0.175,
"input_modalities": [
"text"
],
"max_output_tokens": 8192,
"name": "Qwen2.5 7B Instruct",
"output_cost": 0.7,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-09"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 32768,
"dialect": "openai_completions",
"id": "qwen2-5-omni-7b",
"input_cost": 0.1,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 2048,
"name": "Qwen2.5-Omni 7B",
"output_cost": 0.4,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-12"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen2-5-vl-72b-instruct",
"input_cost": 2.8,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 8192,
"name": "Qwen2.5-VL 72B Instruct",
"output_cost": 8.4,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-09"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen2-5-vl-7b-instruct",
"input_cost": 0.35,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 8192,
"name": "Qwen2.5-VL 7B Instruct",
"output_cost": 1.05,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2024-09"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen3-14b",
"input_cost": 0.35,
"input_modalities": [
"text"
],
"max_output_tokens": 8192,
"name": "Qwen3 14B",
"output_cost": 1.4,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-04"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen3-235b-a22b",
"input_cost": 0.7,
"input_modalities": [
"text"
],
"max_output_tokens": 16384,
"name": "Qwen3 235B-A22B",
"output_cost": 2.8,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-04"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen3-32b",
"input_cost": 0.7,
"input_modalities": [
"text"
],
"max_output_tokens": 16384,
"name": "Qwen3 32B",
"output_cost": 2.8,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-04"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen3-8b",
"input_cost": 0.18,
"input_modalities": [
"text"
],
"max_output_tokens": 8192,
"name": "Qwen3 8B",
"output_cost": 0.7,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-04"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 262144,
"dialect": "openai_completions",
"id": "qwen3-coder-30b-a3b-instruct",
"input_cost": 0.45,
"input_modalities": [
"text"
],
"max_output_tokens": 65536,
"name": "Qwen3-Coder 30B-A3B Instruct",
"output_cost": 2.25,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-04"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 262144,
"dialect": "openai_completions",
"id": "qwen3-coder-480b-a35b-instruct",
"input_cost": 1.5,
"input_modalities": [
"text"
],
"max_output_tokens": 65536,
"name": "Qwen3-Coder 480B-A35B Instruct",
"output_cost": 7.5,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-04"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 1000000,
"dialect": "openai_completions",
"id": "qwen3-coder-flash",
"input_cost": 0.3,
"input_modalities": [
"text"
],
"max_output_tokens": 65536,
"name": "Qwen3 Coder Flash",
"output_cost": 1.5,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-07-28"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 1048576,
"dialect": "openai_completions",
"id": "qwen3-coder-plus",
"input_cost": 1,
"input_modalities": [
"text"
],
"max_output_tokens": 65536,
"name": "Qwen3 Coder Plus",
"output_cost": 5,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-07-23"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 262144,
"dialect": "openai_completions",
"id": "qwen3-max",
"input_cost": 1.2,
"input_modalities": [
"text"
],
"max_output_tokens": 65536,
"name": "Qwen3 Max",
"output_cost": 6,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-09-23"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen3-next-80b-a3b-instruct",
"input_cost": 0.5,
"input_modalities": [
"text"
],
"max_output_tokens": 32768,
"name": "Qwen3-Next 80B-A3B Instruct",
"output_cost": 2,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-09"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen3-next-80b-a3b-thinking",
"input_cost": 0.5,
"input_modalities": [
"text"
],
"max_output_tokens": 32768,
"name": "Qwen3-Next 80B-A3B (Thinking)",
"output_cost": 6,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-09"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 65536,
"dialect": "openai_completions",
"id": "qwen3-omni-flash",
"input_cost": 0.43,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 16384,
"name": "Qwen3-Omni Flash",
"output_cost": 1.66,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-09-15"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 65536,
"dialect": "openai_completions",
"id": "qwen3-omni-flash-realtime",
"input_cost": 0.52,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 16384,
"name": "Qwen3-Omni Flash Realtime",
"output_cost": 1.99,
"output_modalities": [
"text"
],
"reasoning": false,
"release_date": "2025-09-15"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen3-vl-235b-a22b",
"input_cost": 0.7,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 32768,
"name": "Qwen3-VL 235B-A22B",
"output_cost": 2.8,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-04"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwen3-vl-30b-a3b",
"input_cost": 0.2,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 32768,
"name": "Qwen3-VL 30B-A3B",
"output_cost": 0.8,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-04"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 262144,
"dialect": "openai_completions",
"id": "qwen3-vl-plus",
"input_cost": 0.2,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 32768,
"name": "Qwen3-VL Plus",
"output_cost": 1.6,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-09-23"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 262144,
"dialect": "openai_completions",
"id": "qwen3.5-397b-a17b",
"input_cost": 0.6,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 65536,
"name": "Qwen3.5 397B-A17B",
"output_cost": 3.6,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-02-16"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 1000000,
"dialect": "openai_completions",
"id": "qwen3.5-plus",
"input_cost": 0.4,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 65536,
"name": "Qwen3.5 Plus",
"output_cost": 2.4,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-02-16"
},
{
"cache_read_cost": 0.028,
"cache_write_cost": 0.344,
"context_size": 1000000,
"dialect": "openai_completions",
"id": "qwen3.6-plus",
"input_cost": 0.276,
"input_modalities": [
"text",
"image"
],
"max_output_tokens": 65536,
"name": "Qwen3.6 Plus",
"output_cost": 1.651,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2026-04-02"
},
{
"cache_read_cost": 0,
"cache_write_cost": 0,
"context_size": 131072,
"dialect": "openai_completions",
"id": "qwq-plus",
"input_cost": 0.8,
"input_modalities": [
"text"
],
"max_output_tokens": 8192,
"name": "QwQ Plus",
"output_cost": 2.4,
"output_modalities": [
"text"
],
"reasoning": true,
"release_date": "2025-03-05"
}
]