AI Model Pricing and Billing

Compare available AI models, billing methods, and group pricing. Check model-specific rates and usage before sending requests.

How to read model prices

Prices depend on the model, group, and billing method. Token-based rates below are base USD credit rates per one million tokens before group multipliers and recharge adjustments. They are not a promise of the final charge. Dynamic and media pricing require the model-specific rules shown in the interactive catalog.

Check input, output, and cache usage separately. Compare the selected group and billing rules with the usage and cost records in your dashboard.

Publicly available models: 344. Availability may change.

Public model catalog and base billing rates
ModelDescriptionBillingBase rate (USD credits)
MiniMax-H3DynamicSee model-specific billing rules in the interactive catalog
MiniMax-M3.1-FlashDynamicSee model-specific billing rules in the interactive catalog
babbage-002Per tokenInput $0.4; output $0.4 / 1M tokens
chat-latestDynamicSee model-specific billing rules in the interactive catalog
chatgpt-image-latestDynamicSee model-specific billing rules in the interactive catalog
claude-fable-5DynamicSee model-specific billing rules in the interactive catalog
claude-fable-5-1Claude Fable 5.1Per tokenInput $10; output $50 / 1M tokens; cache read $0.25 / 1M tokens
claude-fable-5-2Claude Fable 5.2DynamicSee model-specific billing rules in the interactive catalog
claude-haiku-4-5-20251001DynamicSee model-specific billing rules in the interactive catalog
claude-haiku-5-5DynamicSee model-specific billing rules in the interactive catalog
claude-opus-4-1-20250805DynamicSee model-specific billing rules in the interactive catalog
claude-opus-4-5-20251101DynamicSee model-specific billing rules in the interactive catalog
claude-opus-4-6DynamicSee model-specific billing rules in the interactive catalog
claude-opus-4-7DynamicSee model-specific billing rules in the interactive catalog
claude-opus-4-8DynamicSee model-specific billing rules in the interactive catalog
claude-opus-5Claude Opus 5Per tokenInput $5; output $25 / 1M tokens; cache read $0.5 / 1M tokens
claude-opus-5-5Claude Opus 5.5Per tokenInput $4; output $20 / 1M tokens; cache read $0.2 / 1M tokens
claude-sonnet-4-5-20250929DynamicSee model-specific billing rules in the interactive catalog
claude-sonnet-4-6DynamicSee model-specific billing rules in the interactive catalog
claude-sonnet-5Per tokenInput $2; output $10 / 1M tokens; cache read $0.2 / 1M tokens
claude-sonnet-5-5Claude Sonnet 5.5Per tokenInput $2; output $10 / 1M tokens; cache read $0.2 / 1M tokens
davinci-002Per tokenInput $2; output $2 / 1M tokens
deepseek-flashDeepSeek V4.1 Flash 官方 API 模型名,支持文本、推理、Agent 与原生多模态视觉理解。DynamicSee model-specific billing rules in the interactive catalog
deepseek-v4-flashDynamicSee model-specific billing rules in the interactive catalog
deepseek-v4-proDynamicSee model-specific billing rules in the interactive catalog
deepseek-v4.1-flashDeepSeek V4.1 Flash,支持文本、推理、Agent 与原生多模态视觉理解。DynamicSee model-specific billing rules in the interactive catalog
doubao-seed-2-1-pro-260915DynamicSee model-specific billing rules in the interactive catalog
doubao-seed-2-1-turbo-260628DynamicSee model-specific billing rules in the interactive catalog
doubao-seedance-2-0-mini-260615DynamicSee model-specific billing rules in the interactive catalog
doubao-seedance-2-5-260628DynamicSee model-specific billing rules in the interactive catalog
doubao-seedance-2-5-flash-261115Per tokenInput $75; output $75 / 1M tokens
gemini-2.0-flashDynamicSee model-specific billing rules in the interactive catalog
gemini-2.5-flashDynamicSee model-specific billing rules in the interactive catalog
gemini-2.5-flash-imageOfficial Gemini 2.5 Flash Image model.Per tokenInput $0.3; output $30 / 1M tokens; cache read $0.075 / 1M tokens
gemini-2.5-flash-liteDynamicSee model-specific billing rules in the interactive catalog
gemini-2.5-flash-lite-preview-06-17DynamicSee model-specific billing rules in the interactive catalog
gemini-2.5-flash-lite-preview-09-2025DynamicSee model-specific billing rules in the interactive catalog
gemini-2.5-flash-preview-09-2025DynamicSee model-specific billing rules in the interactive catalog
gemini-2.5-flash-preview-ttsOfficial Gemini 2.5 Flash Preview text-to-speech model.Per tokenInput $0.5; output $10 / 1M tokens
gemini-2.5-proDynamicSee model-specific billing rules in the interactive catalog
gemini-2.5-pro-preview-ttsOfficial Gemini 2.5 Pro Preview text-to-speech model.Per tokenInput $1; output $20 / 1M tokens
gemini-2.5-pro-thinking-*Per tokenInput $1.25; output $10 / 1M tokens
gemini-3-flash-previewPer tokenInput $1; output $3 / 1M tokens; cache read $0.05 / 1M tokens
gemini-3-pro-previewPer tokenInput $2; output $12 / 1M tokens; cache read $0.2 / 1M tokens
gemini-3-pro-preview-11-2025Official Gemini 3 Pro preview model (November 2025 version).Per tokenInput $2; output $12 / 1M tokens; cache read $0.2 / 1M tokens
gemini-3.1-flash-litePer tokenInput $0.5; output $1.5 / 1M tokens; cache read $0.025 / 1M tokens
gemini-3.1-flash-tts-previewOfficial Gemini 3.1 Flash text-to-speech preview model.Per tokenInput $1; output $20 / 1M tokens
gemini-3.1-pro-previewPer tokenInput $2; output $12 / 1M tokens; cache read $0.2 / 1M tokens
gemini-3.1-pro-preview-customtoolsPer tokenInput $2; output $12 / 1M tokens; cache read $0.2 / 1M tokens
gemini-3.5-flashPer tokenInput $1.5; output $9 / 1M tokens; cache read $0.15 / 1M tokens
gemini-3.8-flashOfficial Gemini 3.8 Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows.Per tokenInput $0.75; output $3.75 / 1M tokens; cache read $0.075 / 1M tokens
gemini-3.8-flash-ttsDynamicSee model-specific billing rules in the interactive catalog
gemini-4-argonDynamicSee model-specific billing rules in the interactive catalog
gemini-4-carbonDynamicSee model-specific billing rules in the interactive catalog
gemini-4-hydrogenDynamicSee model-specific billing rules in the interactive catalog
gemini-embedding-001Per tokenInput $0.15; output $0.6 / 1M tokens
gemini-embedding-2-previewOfficial Gemini Embedding 2 multimodal embedding preview model.Per tokenInput $0.2; output $0.000001 / 1M tokens
gemini-flash-latestDynamicSee model-specific billing rules in the interactive catalog
gemini-flash-lite-latestDynamicSee model-specific billing rules in the interactive catalog
gemini-nano-banana-2.1DynamicSee model-specific billing rules in the interactive catalog
glm-5.1Per tokenInput $0.87; output $3.48 / 1M tokens; cache read $0.17 / 1M tokens
glm-5.2Per tokenInput $1.1; output $3.851 / 1M tokens; cache read $0.275 / 1M tokens
glm-5.3-flashDynamicSee model-specific billing rules in the interactive catalog
gpt-3.5-turboPer tokenInput $0.5; output $1.5 / 1M tokens; cache read $1.25 / 1M tokens
gpt-3.5-turbo-0125Per tokenInput $0.5; output $1.5 / 1M tokens
gpt-3.5-turbo-1106Per tokenInput $1; output $2 / 1M tokens
gpt-3.5-turbo-16kPer tokenInput $3; output $6 / 1M tokens
gpt-3.5-turbo-instructPer tokenInput $1.5; output $2 / 1M tokens
gpt-3.5-turbo-instruct-0914DynamicSee model-specific billing rules in the interactive catalog
gpt-4Per tokenInput $30; output $60 / 1M tokens; cache read $15 / 1M tokens
gpt-4-0613Per tokenInput $30; output $60 / 1M tokens
gpt-4-1106-previewPer tokenInput $10; output $20 / 1M tokens
gpt-4-turboPer tokenInput $10; output $30 / 1M tokens
gpt-4-turbo-2024-04-09Per tokenInput $10; output $30 / 1M tokens
gpt-4.1Per tokenInput $2; output $8 / 1M tokens; cache read $0.5 / 1M tokens
gpt-4.1-2025-04-14Per tokenInput $2; output $4 / 1M tokens
gpt-4.1-miniPer tokenInput $0.4; output $1.6 / 1M tokens; cache read $0.1 / 1M tokens
gpt-4.1-mini-2025-04-14Per tokenInput $0.4; output $1.6 / 1M tokens; cache read $0.1 / 1M tokens
gpt-4.1-nanoPer tokenInput $0.1; output $0.4 / 1M tokens; cache read $0.025 / 1M tokens
gpt-4.1-nano-2025-04-14Per tokenInput $0.1; output $0.2 / 1M tokens
gpt-4oPer tokenInput $2.5; output $10 / 1M tokens; cache read $1.25 / 1M tokens
gpt-4o-2024-05-13Per tokenInput $5; output $15 / 1M tokens
gpt-4o-2024-08-06Per tokenInput $2.5; output $10 / 1M tokens; cache read $1.25 / 1M tokens
gpt-4o-2024-11-20Per tokenInput $2.5; output $10 / 1M tokens; cache read $1.25 / 1M tokens
gpt-4o-miniPer tokenInput $0.15; output $0.6 / 1M tokens; cache read $0.075 / 1M tokens
gpt-4o-mini-2024-07-18Per tokenInput $0.15; output $0.6 / 1M tokens; cache read $0.075 / 1M tokens
gpt-4o-mini-search-previewPer tokenInput $0.15; output $0.6 / 1M tokens
gpt-4o-mini-search-preview-2025-03-11Per tokenInput $75; output $300 / 1M tokens
gpt-4o-mini-transcribePer tokenInput $75; output $300 / 1M tokens
gpt-4o-mini-transcribe-2025-03-20Per tokenInput $75; output $300 / 1M tokens
gpt-4o-mini-transcribe-2025-12-15Per tokenInput $75; output $300 / 1M tokens
gpt-4o-mini-ttsOfficial OpenAI GPT-4o mini text-to-speech model.Per request$0.3 / request before group multipliers
gpt-4o-mini-tts-2025-03-20Official OpenAI GPT-4o mini text-to-speech snapshot.DynamicSee model-specific billing rules in the interactive catalog
gpt-4o-mini-tts-2025-12-15Official OpenAI GPT-4o mini text-to-speech snapshot.DynamicSee model-specific billing rules in the interactive catalog
gpt-4o-search-previewPer tokenInput $2.5; output $10 / 1M tokens
gpt-4o-search-preview-2025-03-11Per tokenInput $75; output $300 / 1M tokens
gpt-4o-transcribePer tokenInput $75; output $300 / 1M tokens
gpt-4o-transcribe-diarizePer tokenInput $75; output $300 / 1M tokens
gpt-5Per tokenInput $1.25; output $10 / 1M tokens; cache read $0.125 / 1M tokens
gpt-5-2025-08-07Per tokenInput $1.25; output $10 / 1M tokens; cache read $0.125 / 1M tokens
gpt-5-chat-latestPer tokenInput $1.25; output $10 / 1M tokens; cache read $0.125 / 1M tokens
gpt-5-codexPer tokenInput $1.25; output $10 / 1M tokens; cache read $0.125 / 1M tokens
gpt-5-miniPer tokenInput $0.25; output $2 / 1M tokens; cache read $0.025 / 1M tokens
gpt-5-mini-2025-08-07Per tokenInput $0.25; output $2 / 1M tokens; cache read $0.025 / 1M tokens
gpt-5-nanoPer tokenInput $0.05; output $0.4 / 1M tokens; cache read $0.005 / 1M tokens
gpt-5-nano-2025-08-07Per tokenInput $0.05; output $0.4 / 1M tokens; cache read $0.005000000000000001 / 1M tokens
gpt-5-proPer tokenInput $15; output $120 / 1M tokens
gpt-5-pro-2025-10-06DynamicSee model-specific billing rules in the interactive catalog
gpt-5-search-apiDynamicSee model-specific billing rules in the interactive catalog
gpt-5-search-api-2025-10-14DynamicSee model-specific billing rules in the interactive catalog
gpt-5.1Per tokenInput $1.25; output $10 / 1M tokens; cache read $0.125 / 1M tokens
gpt-5.1-2025-11-13DynamicSee model-specific billing rules in the interactive catalog
gpt-5.1-chat-latestPer tokenInput $1.25; output $10 / 1M tokens; cache read $0.125 / 1M tokens
gpt-5.1-codexPer tokenInput $1.25; output $10 / 1M tokens; cache read $0.125 / 1M tokens
gpt-5.1-codex-maxPer tokenInput $1.25; output $10 / 1M tokens; cache read $0.125 / 1M tokens
gpt-5.1-codex-miniPer tokenInput $0.25; output $2 / 1M tokens; cache read $0.025 / 1M tokens
gpt-5.2Per tokenInput $1.75; output $14 / 1M tokens; cache read $0.175 / 1M tokens
gpt-5.2-2025-12-11DynamicSee model-specific billing rules in the interactive catalog
gpt-5.2-chat-latestPer tokenInput $1.75; output $14 / 1M tokens; cache read $0.175 / 1M tokens
gpt-5.2-codexPer tokenInput $1.75; output $14 / 1M tokens; cache read $0.175 / 1M tokens
gpt-5.2-proPer tokenInput $21; output $168 / 1M tokens
gpt-5.2-pro-2025-12-11DynamicSee model-specific billing rules in the interactive catalog
gpt-5.3-chat-latestPer tokenInput $1.75; output $14 / 1M tokens; cache read $0.175 / 1M tokens
gpt-5.3-codexDynamicSee model-specific billing rules in the interactive catalog
gpt-5.4DynamicSee model-specific billing rules in the interactive catalog
gpt-5.4-2026-03-05DynamicSee model-specific billing rules in the interactive catalog
gpt-5.4-miniDynamicSee model-specific billing rules in the interactive catalog
gpt-5.4-mini-2026-03-17DynamicSee model-specific billing rules in the interactive catalog
gpt-5.4-nanoDynamicSee model-specific billing rules in the interactive catalog
gpt-5.4-nano-2026-03-17Per tokenInput $0.2; output $1.25 / 1M tokens
gpt-5.4-proDynamicSee model-specific billing rules in the interactive catalog
gpt-5.4-pro-2026-03-05DynamicSee model-specific billing rules in the interactive catalog
gpt-5.5DynamicSee model-specific billing rules in the interactive catalog
gpt-5.5-2026-04-23DynamicSee model-specific billing rules in the interactive catalog
gpt-5.5-proDynamicSee model-specific billing rules in the interactive catalog
gpt-5.5-pro-2026-04-23DynamicSee model-specific billing rules in the interactive catalog
gpt-5.6-lunaDynamicSee model-specific billing rules in the interactive catalog
gpt-5.6-solDynamicSee model-specific billing rules in the interactive catalog
gpt-5.6-terraDynamicSee model-specific billing rules in the interactive catalog
gpt-6-astraOfficial OpenAI model.Per tokenInput $10; output $50 / 1M tokens; cache read $1 / 1M tokens
gpt-6-lunaOfficial OpenAI model.Per tokenInput $0.1; output $0.5 / 1M tokens; cache read $0.01 / 1M tokens
gpt-6-solOfficial OpenAI model.Per tokenInput $2; output $10 / 1M tokens; cache read $0.2 / 1M tokens
gpt-6.1-solNear-Astra performance for complex coding, computer use, and professional work at a lower cost.Per tokenInput $2; output $10 / 1M tokens; cache read $0.1 / 1M tokens
gpt-6.1-terraA fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.DynamicSee model-specific billing rules in the interactive catalog
gpt-6.2-astraDynamicSee model-specific billing rules in the interactive catalog
gpt-6.2-solDynamicSee model-specific billing rules in the interactive catalog
gpt-audioDynamicSee model-specific billing rules in the interactive catalog
gpt-audio-1.5DynamicSee model-specific billing rules in the interactive catalog
gpt-audio-2025-08-28DynamicSee model-specific billing rules in the interactive catalog
gpt-audio-miniDynamicSee model-specific billing rules in the interactive catalog
gpt-audio-mini-2025-10-06DynamicSee model-specific billing rules in the interactive catalog
gpt-audio-mini-2025-12-15DynamicSee model-specific billing rules in the interactive catalog
gpt-image-1Official OpenAI GPT Image 1 image generation model.Usage / mediaSee model-specific units and media rates in the interactive catalog
gpt-image-1-miniOfficial OpenAI GPT Image 1 Mini image generation model.DynamicSee model-specific billing rules in the interactive catalog
gpt-image-1.5Official OpenAI GPT Image 1.5 image generation model.DynamicSee model-specific billing rules in the interactive catalog
gpt-image-2Official OpenAI GPT Image 2 image generation model.Usage / mediaSee model-specific units and media rates in the interactive catalog
gpt-image-2-2026-04-21Official OpenAI GPT Image 2 snapshot.DynamicSee model-specific billing rules in the interactive catalog
gpt-image-2.5-flareDynamicSee model-specific billing rules in the interactive catalog
gpt-image-2.5-sunburstDynamicSee model-specific billing rules in the interactive catalog
gpt-image-2.6-flareDynamicSee model-specific billing rules in the interactive catalog
gpt-image-2.6-sunburstDynamicSee model-specific billing rules in the interactive catalog
gpt-live-transcribeOfficial OpenAI model.Usage / mediaSee model-specific units and media rates in the interactive catalog
gpt-oss-120bPer tokenInput $0.25; output $0.69 / 1M tokens
gpt-realtimePer tokenInput $75; output $150 / 1M tokens
gpt-realtime-1.5Per tokenInput $75; output $150 / 1M tokens
gpt-realtime-2Per tokenInput $75; output $150 / 1M tokens
gpt-realtime-2.1Official OpenAI model.Per tokenInput $4; output $24 / 1M tokens; cache read $0.4 / 1M tokens
gpt-realtime-2.1-miniOfficial OpenAI model.Per tokenInput $0.6; output $2.4 / 1M tokens; cache read $0.06 / 1M tokens
gpt-realtime-2025-08-28Per tokenInput $75; output $150 / 1M tokens
gpt-realtime-miniPer tokenInput $75; output $150 / 1M tokens
gpt-realtime-mini-2025-10-06Per tokenInput $75; output $150 / 1M tokens
gpt-realtime-mini-2025-12-15Per tokenInput $75; output $150 / 1M tokens
gpt-realtime-translatePer tokenInput $75; output $150 / 1M tokens
gpt-realtime-whisperPer tokenInput $75; output $150 / 1M tokens
gpt-transcribeOfficial OpenAI model.Usage / mediaSee model-specific units and media rates in the interactive catalog
grok-4.7DynamicSee model-specific billing rules in the interactive catalog
grok-imagine-video-1.5-liteDynamicSee model-specific billing rules in the interactive catalog
hy4DynamicSee model-specific billing rules in the interactive catalog
hy4-flashDynamicSee model-specific billing rules in the interactive catalog
hy4-previewDynamicSee model-specific billing rules in the interactive catalog
kimi-k2.7-codePer tokenInput $0.95; output $3.9999999999999996 / 1M tokens; cache read $0.19 / 1M tokens
kimi-k3.1-proDynamicSee model-specific billing rules in the interactive catalog
mercury-3Inception Labs Mercury 3 diffusion reasoning model.Per tokenInput $0.1; output $0.35 / 1M tokens; cache read $0.01 / 1M tokens
mimo-v2.6-flashDynamicSee model-specific billing rules in the interactive catalog
mimo-v2.6-proDynamicSee model-specific billing rules in the interactive catalog
muse-videoPer tokenInput $75; output $75 / 1M tokens
o1Per tokenInput $15; output $60 / 1M tokens; cache read $7.5 / 1M tokens
o1-2024-12-17Per tokenInput $15; output $60 / 1M tokens; cache read $7.5 / 1M tokens
o1-proPer tokenInput $150; output $600 / 1M tokens
o1-pro-2025-03-19Per tokenInput $150; output $600 / 1M tokens
o3Per tokenInput $2; output $8 / 1M tokens; cache read $0.5 / 1M tokens
o3-2025-04-16Per tokenInput $2; output $8 / 1M tokens
o3-miniPer tokenInput $1.1; output $4.4 / 1M tokens; cache read $0.55 / 1M tokens
o3-mini-2025-01-31Per tokenInput $1.1; output $4.4 / 1M tokens; cache read $0.55 / 1M tokens
o4-miniPer tokenInput $1.1; output $4.4 / 1M tokens; cache read $0.275 / 1M tokens
o4-mini-2025-04-16Per tokenInput $1.1; output $1.1 / 1M tokens
omni-moderation-2024-09-26DynamicSee model-specific billing rules in the interactive catalog
omni-moderation-latestDynamicSee model-specific billing rules in the interactive catalog
qwen-audio-3.0-realtime-flashDynamicSee model-specific billing rules in the interactive catalog
qwen-audio-3.0-realtime-plusDynamicSee model-specific billing rules in the interactive catalog
qwen-coder-plusPer tokenInput $0.5; output $1 / 1M tokens
qwen-coder-turboDynamicSee model-specific billing rules in the interactive catalog
qwen-deep-research-2025-12-15DynamicSee model-specific billing rules in the interactive catalog
qwen-flashDynamicSee model-specific billing rules in the interactive catalog
qwen-flash-characterDynamicSee model-specific billing rules in the interactive catalog
qwen-flash-character-2026-02-26DynamicSee model-specific billing rules in the interactive catalog
qwen-image-2.0DynamicSee model-specific billing rules in the interactive catalog
qwen-image-2.0-2026-03-03DynamicSee model-specific billing rules in the interactive catalog
qwen-image-2.0-proDynamicSee model-specific billing rules in the interactive catalog
qwen-image-2.0-pro-2026-03-03DynamicSee model-specific billing rules in the interactive catalog
qwen-image-2.0-pro-2026-04-22DynamicSee model-specific billing rules in the interactive catalog
qwen-image-2.0-pro-2026-06-22DynamicSee model-specific billing rules in the interactive catalog
qwen-image-3.0DynamicSee model-specific billing rules in the interactive catalog
qwen-image-3.0-proDynamicSee model-specific billing rules in the interactive catalog
qwen-image-edit-maxDynamicSee model-specific billing rules in the interactive catalog
qwen-image-edit-max-2026-01-16DynamicSee model-specific billing rules in the interactive catalog
qwen-image-edit-plusDynamicSee model-specific billing rules in the interactive catalog
qwen-image-edit-plus-2025-10-30DynamicSee model-specific billing rules in the interactive catalog
qwen-image-edit-plus-2025-12-15DynamicSee model-specific billing rules in the interactive catalog
qwen-image-maxDynamicSee model-specific billing rules in the interactive catalog
qwen-image-max-2025-12-30DynamicSee model-specific billing rules in the interactive catalog
qwen-image-plus-2026-01-09DynamicSee model-specific billing rules in the interactive catalog
qwen-longPer tokenInput $0.5; output $2 / 1M tokens
qwen-math-plusPer tokenInput $0.574; output $1.721 / 1M tokens
qwen-math-plus-0919DynamicSee model-specific billing rules in the interactive catalog
qwen-math-plus-latestDynamicSee model-specific billing rules in the interactive catalog
qwen-math-turboPer tokenInput $0.287; output $0.861 / 1M tokens
qwen-maxPer tokenInput $2.4; output $9.6 / 1M tokens; cache read $0.48 / 1M tokens
qwen-mt-flashDynamicSee model-specific billing rules in the interactive catalog
qwen-mt-liteDynamicSee model-specific billing rules in the interactive catalog
qwen-mt-plusPer tokenInput $1.8; output $5.4 / 1M tokens
qwen-mt-turboPer tokenInput $0.7; output $1.9500000000000002 / 1M tokens
qwen-omni-turboPer tokenInput $4.44; output $8.89 / 1M tokens
qwen-plusPer tokenInput $4.8; output $64 / 1M tokens; cache read $0.48 / 1M tokens
qwen-plus-2025-01-25DynamicSee model-specific billing rules in the interactive catalog
qwen-plus-2025-04-28DynamicSee model-specific billing rules in the interactive catalog
qwen-plus-2025-07-14DynamicSee model-specific billing rules in the interactive catalog
qwen-plus-2025-09-11DynamicSee model-specific billing rules in the interactive catalog
qwen-plus-2025-12-01DynamicSee model-specific billing rules in the interactive catalog
qwen-plus-latestDynamicSee model-specific billing rules in the interactive catalog
qwen-tts-2025-05-22DynamicSee model-specific billing rules in the interactive catalog
qwen-turboPer tokenInput $0.3; output $3 / 1M tokens; cache read $0.06 / 1M tokens
qwen-vl-maxPer tokenInput $1.6; output $4 / 1M tokens; cache read $0.32 / 1M tokens
qwen-vl-ocrPer tokenInput $0.72; output $0.72 / 1M tokens
qwen-vl-ocr-2025-11-20DynamicSee model-specific billing rules in the interactive catalog
qwen-vl-ocr-latestDynamicSee model-specific billing rules in the interactive catalog
qwen-vl-plusPer tokenInput $0.8; output $2 / 1M tokens; cache read $0.16 / 1M tokens
qwen3-14bPer tokenInput $1; output $10 / 1M tokens
qwen3-235b-a22bPer tokenInput $2; output $20 / 1M tokens
qwen3-235b-a22b-instruct-2507Per tokenInput $2; output $8 / 1M tokens
qwen3-235b-a22b-thinking-2507Per tokenInput $2; output $20 / 1M tokens
qwen3-30b-a3bDynamicSee model-specific billing rules in the interactive catalog
qwen3-30b-a3b-instruct-2507DynamicSee model-specific billing rules in the interactive catalog
qwen3-30b-a3b-thinking-2507Per tokenInput $0.1; output $0.1 / 1M tokens
qwen3-32bPer tokenInput $2; output $20 / 1M tokens
qwen3-8bPer tokenInput $0.5; output $5 / 1M tokens
qwen3-coder-480b-a35b-instructPer tokenInput $30; output $300 / 1M tokens
qwen3-coder-flashPer tokenInput $5; output $25 / 1M tokens; cache read $0.5 / 1M tokens
qwen3-coder-nextPer tokenInput $0.158; output $0.84 / 1M tokens
qwen3-coder-plusPer tokenInput $20; output $200 / 1M tokens; cache read $2 / 1M tokens
qwen3-coder-plus-2025-07-22Per tokenInput $20; output $200 / 1M tokens
qwen3-coder-plus-2025-09-23Per tokenInput $20; output $200 / 1M tokens
qwen3-livetranslate-flashDynamicSee model-specific billing rules in the interactive catalog
qwen3-livetranslate-flash-2025-12-01DynamicSee model-specific billing rules in the interactive catalog
qwen3-livetranslate-flash-realtimePer tokenInput $10; output $38 / 1M tokens
qwen3-livetranslate-flash-realtime-2025-09-22DynamicSee model-specific billing rules in the interactive catalog
qwen3-maxDynamicSee model-specific billing rules in the interactive catalog
qwen3-max-2025-09-23Per tokenInput $15; output $60 / 1M tokens
qwen3-max-2026-01-23Per tokenInput $3; output $15 / 1M tokens; cache read $0.6 / 1M tokens
qwen3-max-previewDynamicSee model-specific billing rules in the interactive catalog
qwen3-next-80b-a3b-instructPer tokenInput $0.14; output $1.4 / 1M tokens
qwen3-next-80b-a3b-thinkingPer tokenInput $0.164; output $1.311 / 1M tokens
qwen3-omni-flashPer tokenInput $3.81; output $15.11 / 1M tokens
qwen3-omni-flash-2025-09-15DynamicSee model-specific billing rules in the interactive catalog
qwen3-omni-flash-2025-12-01DynamicSee model-specific billing rules in the interactive catalog
qwen3-omni-flash-realtimePer tokenInput $4.57; output $18.13 / 1M tokens
qwen3-omni-flash-realtime-2025-09-15DynamicSee model-specific billing rules in the interactive catalog
qwen3-omni-flash-realtime-2025-12-01DynamicSee model-specific billing rules in the interactive catalog
qwen3-tts-flashPer request$0.8 / request before group multipliers
qwen3-tts-flash-2025-09-18Per request$0.8 / request before group multipliers
qwen3-tts-flash-realtimePer request$1 / request before group multipliers
qwen3-tts-flash-realtime-2025-09-18Per request$1 / request before group multipliers
qwen3-vl-flashPer tokenInput $0.05; output $0.4 / 1M tokens; cache read $0.01 / 1M tokens
qwen3-vl-flash-2025-10-15DynamicSee model-specific billing rules in the interactive catalog
qwen3-vl-flash-2026-01-22DynamicSee model-specific billing rules in the interactive catalog
qwen3-vl-plusPer tokenInput $3; output $30 / 1M tokens; cache read $0.6 / 1M tokens
qwen3-vl-plus-2025-09-23Per tokenInput $3; output $30 / 1M tokens
qwen3-vl-plus-2025-12-19DynamicSee model-specific billing rules in the interactive catalog
qwen3.5-122b-a10bPer tokenInput $0.444; output $3.106 / 1M tokens
qwen3.5-27bPer tokenInput $0.3; output $2.4 / 1M tokens
qwen3.5-35b-a3bPer tokenInput $0.25; output $2 / 1M tokens
qwen3.5-397b-a17bDynamicSee model-specific billing rules in the interactive catalog
qwen3.5-flashPer tokenInput $0.172; output $1.7199999999999998 / 1M tokens
qwen3.5-flash-2026-02-23DynamicSee model-specific billing rules in the interactive catalog
qwen3.5-livetranslate-flash-realtimeDynamicSee model-specific billing rules in the interactive catalog
qwen3.5-livetranslate-flash-realtime-2026-05-19DynamicSee model-specific billing rules in the interactive catalog
qwen3.5-ocrDynamicSee model-specific billing rules in the interactive catalog
qwen3.5-omni-flashDynamicSee model-specific billing rules in the interactive catalog
qwen3.5-omni-flash-2026-03-15DynamicSee model-specific billing rules in the interactive catalog
qwen3.5-omni-flash-realtimeDynamicSee model-specific billing rules in the interactive catalog
qwen3.5-omni-flash-realtime-2026-03-15DynamicSee model-specific billing rules in the interactive catalog
qwen3.5-omni-plusDynamicSee model-specific billing rules in the interactive catalog
qwen3.5-omni-plus-2026-03-15DynamicSee model-specific billing rules in the interactive catalog
qwen3.5-omni-plus-realtimeDynamicSee model-specific billing rules in the interactive catalog
qwen3.5-omni-plus-realtime-2026-03-15DynamicSee model-specific billing rules in the interactive catalog
qwen3.5-plusPer tokenInput $0.2; output $1.2 / 1M tokens; cache read $0.02 / 1M tokens
qwen3.5-plus-2026-02-15DynamicSee model-specific billing rules in the interactive catalog
qwen3.5-plus-2026-04-20DynamicSee model-specific billing rules in the interactive catalog
qwen3.6-27bDynamicSee model-specific billing rules in the interactive catalog
qwen3.6-35b-a3bDynamicSee model-specific billing rules in the interactive catalog
qwen3.6-flashPer tokenInput $0.1875; output $1.125 / 1M tokens; cache read $0.01863970588235294 / 1M tokens
qwen3.6-flash-2026-04-16DynamicSee model-specific billing rules in the interactive catalog
qwen3.6-max-previewPer tokenInput $1.27; output $7.61 / 1M tokens; cache read $0.1268 / 1M tokens
qwen3.6-plusDynamicSee model-specific billing rules in the interactive catalog
qwen3.6-plus-2026-04-02DynamicSee model-specific billing rules in the interactive catalog
qwen3.7-flashDynamicSee model-specific billing rules in the interactive catalog
qwen3.7-flash-2026-07-15DynamicSee model-specific billing rules in the interactive catalog
qwen3.7-maxDynamicSee model-specific billing rules in the interactive catalog
qwen3.7-max-2026-05-17DynamicSee model-specific billing rules in the interactive catalog
qwen3.7-max-2026-05-20DynamicSee model-specific billing rules in the interactive catalog
qwen3.7-max-2026-06-08DynamicSee model-specific billing rules in the interactive catalog
qwen3.7-max-previewDynamicSee model-specific billing rules in the interactive catalog
qwen3.7-plusDynamicSee model-specific billing rules in the interactive catalog
qwen3.7-plus-2026-05-26DynamicSee model-specific billing rules in the interactive catalog
qwen3.7-text-embeddingAlibaba Cloud Qwen text embedding model.Per tokenInput $0.0744; output $0.000001 / 1M tokens
qwen3.8-2.4t-a95bDynamicSee model-specific billing rules in the interactive catalog
qwen3.8-27bDynamicSee model-specific billing rules in the interactive catalog
qwen3.8-flashDynamicSee model-specific billing rules in the interactive catalog
qwen3.8-maxPer tokenInput $2; output $6 / 1M tokens; cache read $0.25 / 1M tokens
qwen3.8-max-0902DynamicSee model-specific billing rules in the interactive catalog
qwen3.8-omni-flashDynamicSee model-specific billing rules in the interactive catalog
qwen3.8-omni-flash-realtimeDynamicSee model-specific billing rules in the interactive catalog
qwen4-maxPer tokenInput $75; output $75 / 1M tokens
sora-2Per request$0.3 / request before group multipliers
sora-2-proPer request$0.5 / request before group multipliers
text-embedding-3-largeOpenAI text embedding model.Per tokenInput $0.13; output $0.000001 / 1M tokens
text-embedding-3-smallOpenAI text embedding model.Per tokenInput $0.02; output $0.000001 / 1M tokens
text-embedding-ada-002OpenAI legacy text embedding model.Per tokenInput $0.1; output $0.000001 / 1M tokens
tts-1Usage / mediaSee model-specific units and media rates in the interactive catalog
tts-1-1106Usage / mediaSee model-specific units and media rates in the interactive catalog
tts-1-hdUsage / mediaSee model-specific units and media rates in the interactive catalog
tts-1-hd-1106Usage / mediaSee model-specific units and media rates in the interactive catalog
wan3.0-videoDynamicSee model-specific billing rules in the interactive catalog
whisper-1Per tokenInput $30; output $30 / 1M tokens

The interactive dashboard requires JavaScript. The information above remains available without JavaScript.