Next-generation Claude Fable 5.2 model combining deep multi-step reasoning, creative long-form writing, and autonomous agent workflows.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $7.2 $8
Output: $36 $40
Cache W: $9
Cache R: $0.18
Advanced Claude Fable 5.1 model for deep multi-step reasoning, creative long-form writing, and autonomous agent workflows.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $9 $10
Output: $45 $50
Cache W: $11.25
Cache R: $0.225
Specialized Claude Fable 5 model for creative writing, deep analytical synthesis, and controllable multi-step agent orchestration.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $9 $10
Output: $45 $50
Cache W: $11.25
Cache R: $0.9
High-performance Claude Opus 4.6 flagship for advanced programming, architecture planning, and deep professional reasoning.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $4.5 $5
Output: $22.5 $25
Cache W: $5.625
Cache R: $0.45
Enhanced Claude Opus 4.7 flagship for advanced software engineering, smart contract audits, and mission-critical reasoning.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $4.5 $5
Output: $22.5 $25
Cache W: $5.625
Cache R: $0.45
Top-tier Claude Opus 4.8 model for the most challenging logical reasoning, system-level programming, and long-horizon tasks.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $4.5 $5
Output: $22.5 $25
Cache W: $5.625
Cache R: $0.45
Frontier Claude Opus 5 model for complex multi-agent collaboration, engineering, and deep professional knowledge tasks.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $4.5 $5
Output: $22.5 $25
Cache W: $5.625
Cache R: $0.45
Next-generation flagship Claude Opus 5.5 built for long-horizon autonomous agents, large codebase architecture, and scientific reasoning.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $3.6 $4
Output: $18 $20
Cache W: $4.5
Cache R: $0.18
Everyday workhorse Claude agent model for coding, planning, web browsing, and general enterprise workflows.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $1.8 $2
Output: $9 $10
Cache W: $2.25
Cache R: $0.18
Enhanced Claude Sonnet 5.5 workhorse combining frontier coding benchmarks, 1M context window, and ultra-fast streaming.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $1.8 $2
Output: $9 $10
Cache W: $2.25
Cache R: $0.09
claude-sonnet-4-5-20250929Stable enterprise Claude Sonnet 4.5 model optimized for robust code generation and complex instruction following.
chat Visual Recognition Function Calls 200K ctx 10% OFF
Input: $2.7 $3
Output: $13.5 $15
Cache W: $3.375
Cache R: $0.27
Balanced Claude Sonnet 4.6 model delivering top-tier code engineering quality with low-latency responsiveness.
chat Visual Recognition Function Calls 200K ctx 10% OFF
Input: $2.7 $3
Output: $13.5 $15
Cache W: $3.375
Cache R: $0.27
claude-haiku-4-5-20251001Low-latency Claude Haiku 4.5 model ideal for high-concurrency real-time dialogue and lightweight agent automation.
chat Visual Recognition Function Calls 200K ctx 10% OFF
Input: $0.9 $1
Output: $4.5 $5
Cache W: $1.125
Cache R: $0.09
Ultra-fast Claude Haiku 5.5 model offering instant millisecond responses and high cost-efficiency for real-time subagents.
chat Visual Recognition Function Calls 1M ctx 10% OFF
Input: $0.09 $0.1
Output: $0.45 $0.5
Cache W: $0.1125
Cache R: $0.009
>100K (5x) $0.45 / $2.25
Professional-grade reasoning model excelling at complex mathematics, long-document analysis, and multilingual engineering.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.6 $2
Output: $9.6 $12
Cache W: $1.6
Cache R: $0.16
Gemini 3.1 Pro (CustomTools) gemini-3.1-pro-preview-customtoolsGemini 3.1 Pro custom tools edition, deeply optimized for complex function calling and multi-step agent orchestration.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.6 $2
Output: $9.6 $12
Cache W: $1.6
Cache R: $0.16
Google's flagship Gemini 4 Carbon multimodal model with a 1M-token context window, text/image/audio/video/document input, native tool use, and structured outputs.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.6 $2
Output: $8 $10
Cache W: $2
Cache R: $0.08
Google's next-gen Gemini 4 Argon flagship multimodal model with frontier long-context reasoning and cross-modal capabilities.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.6 $2
Output: $8 $10
Cache W: $2
Cache R: $0.08
High-speed multimodal Gemini model balancing fast latency, long context, and high-quality reasoning.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.2 $1.5
Output: $7.2 $9
Cache W: $1.5
Cache R: $0.12
Classic professional Gemini model with 1M ultra-long context window and deep analytical reasoning capabilities.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1 $1.25
Output: $8 $10
Cache W: $1.25
Cache R: $0.1
Professional high-fidelity voice synthesis model tailored for podcasts, audiobooks, and long-form audio generation.
audio 128K ctx 20% OFF
Input: $0.8 $1
Output: $16 $20
Cache W: $1
Cache R: $0.08
High-speed multimodal Gemini model balancing fast latency, long context, and high-quality reasoning.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.6 $0.75
Output: $3 $3.75
Cache W: $0.75
Cache R: $0.06
Gemini 3.8 Flash Lite TTS gemini-3.8-flash-lite-ttsHigh-fidelity neural text-to-speech model for natural, emotional multilingual voice synthesis.
audio 128K ctx 20% OFF
Input: $0.4 $0.5
Output: $4.8 $6
Cache W: $0.5
Cache R: $0.04
High-fidelity neural text-to-speech model for natural, emotional multilingual voice synthesis.
audio 128K ctx 20% OFF
Input: $0.4 $0.5
Output: $7.2 $9
Cache W: $0.5
Cache R: $0.04
Gemini 3.5 Live Translate Preview gemini-3.5-live-translate-previewReal-time speech and text simultaneous translation model with ultra-low latency.
realtime Visual Recognition 1M ctx 20% OFF
Input: $2.8 $3.5
Output: $16.8 $21
Cache W: $3.5
Cache R: $0.28
Gemini 3.5 Transcribe Live gemini-3.5-transcribe-liveHigh-accuracy streaming speech recognition and transcription model for multilingual audio.
audio 128K ctx 20% OFF
Input: $2.8 $3.5
Output: $16.8 $21
Cache W: $3.5
Cache R: $0.28
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $1.6 $2
Output: $96 $120
Cache W: $2
Cache R: $0.16
Gemini 3 Pro Image Preview gemini-3-pro-image-previewHigh-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $1.6 $2
Output: $96 $120
Cache W: $2
Cache R: $0.16
High-accuracy streaming speech recognition and transcription model for multilingual audio.
audio 128K ctx 20% OFF
Input: $1.6 $2
Output: $9.6 $12
Cache W: $2
Cache R: $0.16
Gemini Nano Banana 2.1 by Google for advanced reasoning, generation, and agent workflows.
image Visual Recognition 128K ctx 20% OFF
Input: $1.2 $1.5
Output: $24 $30
Cache W: $1.5
Cache R: $0.12
Gemini Omni 1.1 Flash Preview gemini-omni-1.1-flash-previewNative multimodal model supporting real-time audio, video, and text understanding and generation.
realtime Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.2 $1.5
Output: $14 $17.5
Cache W: $1.5
Cache R: $0.12
Gemini Omni Flash Preview gemini-omni-flash-previewNative multimodal model supporting real-time audio, video, and text understanding and generation.
realtime Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.2 $1.5
Output: $14 $17.5
Cache W: $1.5
Cache R: $0.12
Gemini 3.1 Flash TTS Preview gemini-3.1-flash-tts-previewHigh-fidelity neural text-to-speech model for natural, emotional multilingual voice synthesis.
audio 128K ctx 20% OFF
Input: $0.8 $1
Output: $16 $20
Cache W: $1
Cache R: $0.08
High-speed multimodal Gemini model balancing fast latency, long context, and high-quality reasoning.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.6 $0.75
Output: $3 $3.75
Cache W: $0.75
Cache R: $0.06
High-speed multimodal Gemini model balancing fast latency, long context, and high-quality reasoning.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.6 $0.75
Output: $3 $3.75
Cache W: $0.75
Cache R: $0.06
Gemini 3.8 Live by Google for advanced reasoning, generation, and agent workflows.
realtime Visual Recognition 1M ctx 20% OFF
Input: $0.6 $0.75
Output: $3.6 $4.5
Cache W: $0.75
Cache R: $0.06
High-fidelity neural text-to-speech model for natural, emotional multilingual voice synthesis.
audio 128K ctx 20% OFF
Input: $0.4 $0.5
Output: $8 $10
Cache W: $0.5
Cache R: $0.04
High-speed multimodal Gemini model balancing fast latency, long context, and high-quality reasoning.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.4 $0.5
Output: $2.4 $3
Cache W: $0.5
Cache R: $0.04
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $0.4 $0.5
Output: $48 $60
Cache W: $0.5
Cache R: $0.04
Gemini 3.1 Flash Image Preview gemini-3.1-flash-image-previewHigh-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $0.4 $0.5
Output: $48 $60
Cache W: $0.5
Cache R: $0.04
High-speed multimodal Gemini model balancing fast latency, long context, and high-quality reasoning.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.24 $0.3
Output: $2 $2.5
Cache W: $0.3
Cache R: $0.024
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $0.24 $0.3
Output: $24 $30
Cache W: $0.3
Cache R: $0.024
Lightweight and cost-efficient multimodal model designed for high-frequency subagent dispatching.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.24 $0.3
Output: $2 $2.5
Cache W: $0.3
Cache R: $0.024
Lightweight and cost-efficient multimodal model designed for high-frequency subagent dispatching.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.2 $0.25
Output: $1.2 $1.5
Cache W: $0.2
Cache R: $0.02
Gemini 3.1 Flash Lite Image gemini-3.1-flash-lite-imageHigh-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $0.2 $0.25
Output: $24 $30
Cache W: $0.25
Cache R: $0.02
Gemini 3.1 Flash Lite Preview gemini-3.1-flash-lite-previewLightweight and cost-efficient multimodal model designed for high-frequency subagent dispatching.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.2 $0.25
Output: $1.2 $1.5
Cache W: $0.2
Cache R: $0.02
High-dimensional semantic vector embedding model for enterprise RAG and cross-lingual retrieval.
embedding 32K ctx 20% OFF
Input: $0.16 $0.2
Output: $0.64 $0.8
Cache W: $0.2
Cache R: $0.016
High-dimensional semantic vector embedding model for enterprise RAG and cross-lingual retrieval.
embedding 32K ctx 20% OFF
Input: $0.12 $0.15
Output: $0.48 $0.6
Cache W: $0.15
Cache R: $0.012
High-performance open-weight model with strong code and instruction following capabilities.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.12 $0.15
Output: $0.48 $0.6
Cache W: $0.15
Cache R: $0.012
Lightweight and cost-efficient multimodal model designed for high-frequency subagent dispatching.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.08 $0.1
Output: $0.32 $0.4
Cache W: $0.1
Cache R: $0.008
Google Veo generative video generation model for cinematic motion and creative video production.
video Visual Recognition 128K ctx 20% OFF
Unit Price: $0.16 / second $0.2
Pay-per-use Veo 3.1 Fast Generate 001 veo-3.1-fast-generate-001Google Veo generative video generation model for cinematic motion and creative video production.
video Visual Recognition 128K ctx 20% OFF
Unit Price: $0.08 / second $0.1
Pay-per-use Google Lyria generative music and audio clip synthesis model.
audio 128K ctx 20% OFF
Unit Price: $0.064 / song $0.08
Pay-per-use Google Lyria generative music and audio clip synthesis model.
audio 128K ctx 20% OFF
Unit Price: $0.048 / song $0.06
Pay-per-use Veo 3.1 Lite Generate 001 veo-3.1-lite-generate-001Google Veo generative video generation model for cinematic motion and creative video production.
video Visual Recognition 128K ctx 20% OFF
Unit Price: $0.04 / second $0.05
Pay-per-use Google Lyria generative music and audio clip synthesis model.
audio 128K ctx 20% OFF
Unit Price: $0.032 / song $0.04
Pay-per-use Enterprise-grade multimodal flagship model for advanced reasoning, agent orchestration, and complex workflows.
chat Visual Recognition Function Calls 400K ctx 20% OFF
Input: $24 $30
Output: $144 $180
Cache W: $30
Cache R: $2.4
Next-generation OpenAI GPT-6 frontier model for complex reasoning, multi-agent systems, and system design.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $8 $10
Output: $40 $50
Cache W: $10
Cache R: $0.8
Enterprise-grade multimodal flagship model for advanced reasoning, agent orchestration, and complex workflows.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $4 $5
Output: $24 $30
Cache W: $5
Cache R: $0.4
Enterprise-grade multimodal flagship model for advanced reasoning, agent orchestration, and complex workflows.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $3.2 $4
Output: $16 $20
Cache W: $4
Cache R: $0.32
Enterprise-grade multimodal flagship model for advanced reasoning, agent orchestration, and complex workflows.
chat Visual Recognition Function Calls 400K ctx 20% OFF
Input: $2 $2.5
Output: $12 $15
Cache W: $2.5
Cache R: $0.2
Next-generation OpenAI GPT-6 frontier model for complex reasoning, multi-agent systems, and system design.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.6 $2
Output: $8 $10
Cache W: $2
Cache R: $0.16
Next-generation OpenAI GPT-6 frontier model for complex reasoning, multi-agent systems, and system design.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.6 $2
Output: $8 $10
Cache W: $2
Cache R: $0.08
Next-generation OpenAI GPT-6 frontier model for complex reasoning, multi-agent systems, and system design.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.8 $1
Output: $4 $5
Cache W: $1
Cache R: $0.04
Next-generation OpenAI GPT-6 frontier model for complex reasoning, multi-agent systems, and system design.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.08 $0.1
Output: $0.4 $0.5
Cache W: $0.1
Cache R: $0.008
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 400K ctx 20% OFF
Input: $4 $5
Output: $25.6 $32
Cache W: $5
Cache R: $1
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 400K ctx 20% OFF
Input: $4 $5
Output: $24 $30
Cache W: $5
Cache R: $1
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 400K ctx 20% OFF
Input: $4 $5
Output: $24 $30
Cache W: $5
Cache R: $1
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 400K ctx 20% OFF
Input: $4 $5
Output: $24 $30
Cache W: $5
Cache R: $1
Ultra-low latency real-time voice and text model for natural conversational interactions.
realtime Visual Recognition Function Calls 400K ctx 20% OFF
Input: $4 $5
Output: $24 $30
Cache W: $5
Cache R: $1
Ultra-low latency real-time voice and text model for natural conversational interactions.
realtime Visual Recognition Function Calls 400K ctx 20% OFF
Input: $3.2 $4
Output: $19.2 $24
Cache W: $4
Cache R: $0.32
Ultra-low latency real-time voice and text model for natural conversational interactions.
realtime Visual Recognition Function Calls 400K ctx 20% OFF
Input: $3.2 $4
Output: $19.2 $24
Cache W: $4
Cache R: $0.32
Native audio understanding and speech generation model for high-quality multilingual interaction.
realtime Visual Recognition Function Calls 400K ctx 20% OFF
Input: $2 $2.5
Output: $8 $10
Cache W: $2.5
Cache R: $0.2
Enterprise-grade multimodal flagship model for advanced reasoning, agent orchestration, and complex workflows.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $1.6 $2
Output: $9.6 $12
Cache W: $2
Cache R: $0.16
Enterprise-grade multimodal flagship model for advanced reasoning, agent orchestration, and complex workflows.
chat Visual Recognition Function Calls 400K ctx 20% OFF
Input: $1.4 $1.75
Output: $11.2 $14
Cache W: $1.75
Cache R: $0.14
Specialized code engineering model optimized for full-stack development, terminal automation, and code reviews.
chat Visual Recognition Function Calls 400K ctx 20% OFF
Input: $1.4 $1.75
Output: $11.2 $14
Cache W: $1.75
Cache R: $0.14
Cost-efficient lightweight multimodal model balancing strong reasoning with ultra-low latency.
chat Visual Recognition Function Calls 400K ctx 20% OFF
Input: $0.6 $0.75
Output: $3.6 $4.5
Cache W: $0.75
Cache R: $0.06
Ultra-low latency real-time voice and text model for natural conversational interactions.
realtime Visual Recognition Function Calls 400K ctx 20% OFF
Input: $0.48 $0.6
Output: $1.92 $2.4
Cache W: $0.6
Cache R: $0.048
Cost-efficient lightweight multimodal model balancing strong reasoning with ultra-low latency.
chat Visual Recognition Function Calls 400K ctx 20% OFF
Input: $0.2 $0.25
Output: $1.6 $2
Cache W: $0.25
Cache R: $0.02
Cost-efficient lightweight multimodal model balancing strong reasoning with ultra-low latency.
chat Visual Recognition Function Calls 400K ctx 20% OFF
Input: $0.16 $0.2
Output: $1 $1.25
Cache W: $0.2
Cache R: $0.016
Enterprise-grade multimodal flagship model for advanced reasoning, agent orchestration, and complex workflows.
chat Visual Recognition Function Calls 1M ctx 20% OFF
Input: $0.16 $0.2
Output: $0.96 $1.2
Cache W: $0.2
Cache R: $0.016
High-dimensional semantic vector embedding model for enterprise RAG and cross-lingual retrieval.
embedding 32K ctx 20% OFF
Input: $0.104 $0.13
Output: $0.104 $0.13
Cache W: $0.13
Cache R: $0.0104
High-dimensional semantic vector embedding model for enterprise RAG and cross-lingual retrieval.
embedding 32K ctx 20% OFF
Input: $0.016 $0.02
Output: $0.016 $0.02
Cache W: $0.02
Cache R: $0.0016
GPT-Live 1 by OpenAI for advanced reasoning, generation, and agent workflows.
realtime Visual Recognition 400K ctx 20% OFF
Unit Price: $0.04 / minute $0.05
Pay-per-use Ultra-low latency real-time voice and text model for natural conversational interactions.
audio 400K ctx 20% OFF
Unit Price: $0.0136 / minute $0.017
Pay-per-use High-accuracy streaming speech recognition and transcription model for multilingual audio.
audio 400K ctx 20% OFF
Unit Price: $0.0036 / minute $0.0045
Pay-per-use High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $4 $5
Output: $30.4 $38
Cache W: $5
Cache R: $0.4
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $4 $5
Output: $37.6 $47
Cache W: $5
Cache R: $0.4
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $4 $5
Output: $84.8 $106
Cache W: $5
Cache R: $0.4
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $1.4 $1.75
Output: $15.6 $19.5
Cache W: $1.75
Cache R: $0.14
High-resolution multimodal visual generation model with realistic photo texture and precise prompt adherence.
image Visual Recognition 128K ctx 20% OFF
Input: $1.4 $1.75
Output: $15.2 $19
Cache W: $1.75
Cache R: $0.14
dreamina-seedance-2-5-260628BytePlus Dreamina Seedance 2.5 flagship multimodal video generation model supporting text, reference images, video, and audio with native synchronized audio generation ($6.4/1M with video input, $10.7/1M without; 105% rate).
video Visual Recognition 128K ctx 105%
Input: $6.72
Output: $11.235
Cache W: $6.72
Cache R: $6.72
dreamina-seedance-2-5-flash-261115BytePlus Dreamina Seedance 2.5 Flash high-speed multimodal video generation model ($4.3/1M with video input, $7.0/1M without; 105% rate).
video Visual Recognition 128K ctx 105%
Input: $4.515
Output: $7.35
Cache W: $4.515
Cache R: $4.515
dreamina-seedance-2-0-260128BytePlus Dreamina Seedance 2.0 multimodal video generation model supporting 480P to 4K resolutions ($4.3/1M with video input, $7.0/1M without; 105% rate).
video Visual Recognition 128K ctx 105%
Input: $4.515
Output: $7.35
Cache W: $4.515
Cache R: $4.515
dreamina-seedance-2-0-fast-260128BytePlus Dreamina Seedance 2.0 Fast video generation model at 45% OFF / 5.5 Zhe (list price $3.3/$5.6 per 1M tokens).
video Visual Recognition Function Calls 128K ctx 45% OFF
Input: $1.815 $3.3
Output: $3.08 $5.6
Cache W: $1.815
Cache R: $1.815
dreamina-seedance-2-0-mini-260615BytePlus Dreamina Seedance 2.0 Mini cost-effective video generation model at 45% OFF / 5.5 Zhe (list price $2.1/$3.5 per 1M tokens).
video Visual Recognition 128K ctx 45% OFF
Input: $1.155 $2.1
Output: $1.925 $3.5
Cache W: $1.155
Cache R: $1.155
seedance-1-0-pro-fast-251015BytePlus Seedance 1.0 Pro Fast video generation model (105% rate).
video Visual Recognition 128K ctx 105%
Input: $2.625
Output: $4.41
Cache W: $2.625
Cache R: $2.625
BytePlus Seedance 1.0 Pro video generation model (105% rate).
video Visual Recognition 128K ctx 105%
Input: $3.675
Output: $6.3
Cache W: $3.675
Cache R: $3.675
BytePlus Dola Seedream 5.5 flagship text-to-image, image-to-image, and layer separation model at 25% OFF / 7.5 Zhe ($0.015/image).
image Visual Recognition Function Calls 128K ctx 25% OFF
Unit Price: $0.015 / image $0.02
Pay-per-use dola-seedream-5-0-pro-260628BytePlus Dola Seedream 5.0 Pro professional high-res image generation model at 35% OFF / 6.5 Zhe ($0.0293/image).
image Visual Recognition Function Calls 128K ctx 35% OFF
Unit Price: $0.0292 / image $0.045
Pay-per-use dola-seedream-5-0-flash-260915BytePlus Dola Seedream 5.0 Flash high-speed image generation model at 35% OFF / 6.5 Zhe ($0.0117/image).
image Visual Recognition Function Calls 128K ctx 35% OFF
Unit Price: $0.0117 / image $0.018
Pay-per-use BytePlus Seedream 5.0 Lite text-to-image & image-to-image model at 30% OFF / 7 Zhe ($0.0245/image).
image Visual Recognition Function Calls 128K ctx 30% OFF
Unit Price: $0.0245 / image $0.035
Pay-per-use BytePlus Seedream 4.5 image generation model at 35% OFF / 6.5 Zhe ($0.026/image).
image Visual Recognition 128K ctx 35% OFF
Unit Price: $0.026 / image $0.04
Pay-per-use BytePlus Seedream 4.0 (20260415) image generation model at 35% OFF / 6.5 Zhe ($0.0195/image).
image Visual Recognition Function Calls 128K ctx 35% OFF
Unit Price: $0.0195 / image $0.03
Pay-per-use BytePlus Seedream 4.0 image generation model at 35% OFF / 6.5 Zhe ($0.0195/image).
image Visual Recognition Function Calls 128K ctx 35% OFF
Unit Price: $0.0195 / image $0.03
Pay-per-use BytePlus Seedream 3.0 text-to-image model (105% rate).
image 64K ctx 105%
Unit Price: $0.0263 / image
Pay-per-use deepseek-v4-1-flash-261017BytePlus hosted DeepSeek V4.1 Flash 1M-context multimodal reasoning model at 50% OFF ($0.15/1M input, $0.60/1M output).
chat Visual Recognition Function Calls 1.048576M ctx 50% OFF
Input: $0.15 $0.3
Output: $0.6 $1.2
Cache W: $0.15
Cache R: $0.003
DeepSeek V4.1 Flash Economy deepseek-v4-1-flash-economy-261017BytePlus hosted DeepSeek V4.1 Flash Economy 1M-context multimodal model at 50% OFF ($0.12/1M input, $0.48/1M output).
chat Visual Recognition Function Calls 1.048576M ctx 50% OFF
Input: $0.12 $0.24
Output: $0.48 $0.96
Cache W: $0.12
Cache R: $0.0025
DeepSeek V4.1 Flash (260910) deepseek-v4-1-flash-260910BytePlus hosted DeepSeek V4.1 Flash (260910) 1M-context model at 50% OFF.
chat Visual Recognition Function Calls 1.048576M ctx 50% OFF
Input: $0.15 $0.3
Output: $0.6 $1.2
Cache W: $0.15
Cache R: $0.003
deepseek-v4-pro-ga-260813BytePlus hosted DeepSeek V4 Pro GA flagship reasoning model with 1M context window (105% rate).
chat Function Calls 1.048576M ctx 105%
Input: $1.386
Output: $4.158
Cache W: $1.386
Cache R: $0.0462
deepseek-v4-flash-ga-260731BytePlus hosted DeepSeek V4 Flash GA high-speed 1M-context reasoning model (105% rate).
chat Function Calls 1.048576M ctx 105%
Input: $0.462
Output: $1.386
Cache W: $0.462
Cache R: $0.0147
BytePlus hosted DeepSeek V4 Pro (260425) reasoning model with 1M context (105% rate).
chat Function Calls 1.048576M ctx 105%
Input: $1.386
Output: $4.158
Cache W: $1.386
Cache R: $0.0462
BytePlus hosted DeepSeek V4 Flash (260425) high-throughput model (105% rate).
chat Function Calls 1.048576M ctx 105%
Input: $0.462
Output: $1.386
Cache W: $0.462
Cache R: $0.0147
BytePlus hosted DeepSeek V3.1 128K language model (105% rate).
chat Function Calls 131K ctx 105%
Input: $0.5775
Output: $1.764
Cache W: $0.5775
Cache R: $0.0147
BytePlus hosted GLM 5.3 Flash 1M-context multimodal model at 10% OFF / 9 Zhe ($0.135/1M input, $0.45/1M output).
chat Visual Recognition Function Calls 1.048576M ctx 10% OFF
Input: $0.135 $0.15
Output: $0.45 $0.5
Cache W: $0.135
Cache R: $0.027
BytePlus hosted GLM 5.3 flagship 1M-context multimodal reasoning model at 35% OFF / 6.5 Zhe ($0.65/1M input, $2.08/1M output).
chat Visual Recognition Function Calls 1.048576M ctx 35% OFF
Input: $0.65 $1
Output: $2.08 $3.2
Cache W: $0.65
Cache R: $0.0975
BytePlus hosted GLM 5.2 1M-context flagship language model at 50% OFF / 5 Zhe ($0.70/1M input, $2.20/1M output).
chat Function Calls 1.048576M ctx 50% OFF
Input: $0.7 $1.4
Output: $2.2 $4.4
Cache W: $0.7
Cache R: $0.13
dola-seed-2-1-turbo-260628BytePlus Dola Seed 2.1 Turbo 256K multimodal reasoning model supporting text, image, and video inputs (105% rate).
chat Visual Recognition Function Calls 262K ctx 105%
Input: $0.525
Output: $2.625
Cache W: $0.525
Cache R: $0.105
BytePlus Seed 2.0 Pro flagship 256K multimodal model (105% rate).
chat Visual Recognition Function Calls 262K ctx 105%
Input: $1.26
Output: $5.04
Cache W: $1.26
Cache R: $0.252
seed-2-0-code-preview-260328BytePlus Seed 2.0 Code Preview multimodal coding model with 256K context (105% rate).
chat Visual Recognition Function Calls 262K ctx 105%
Input: $0.63
Output: $2.52
Cache W: $0.63
Cache R: $0.126
BytePlus Seed 2.0 Lite omni-modal lightweight model supporting text, image, video, and audio inputs (105% rate).
chat Visual Recognition Function Calls 262K ctx 105%
Input: $0.315
Output: $1.26
Cache W: $0.315
Cache R: $0.063
BytePlus Seed 2.0 Mini ultra-fast omni-modal model with 256K context (105% rate).
chat Visual Recognition Function Calls 262K ctx 105%
Input: $0.1575
Output: $0.63
Cache W: $0.1575
Cache R: $0.0315
BytePlus Seed Translation neural machine translation model (105% rate).
chat Function Calls 128K ctx 105%
Input: $0.315
Output: $0.945
Cache W: $0.315
Cache R: $0.063
BytePlus Hyper3D Gen2 image-to-3D generation model ($13.3/1M tokens list price; 105% rate).
video Visual Recognition 64K ctx 105%
Input: $13.965
Output: $13.965
Cache W: $13.965
Cache R: $13.965
BytePlus HiTem3D 2.0 high-precision image-to-3D generation model ($20.0/1M tokens list price; 105% rate).
video Visual Recognition 64K ctx 105%
Input: $21
Output: $21
Cache W: $21
Cache R: $21
Skylark Embedding Vision (251215) skylark-embedding-vision-251215BytePlus Skylark Embedding Vision (251215) 128K multimodal embedding model for text, image, and video ($0.125/1M tokens list price; 105% rate).
embedding Visual Recognition 131K ctx 105%
Input: $0.1313
Output: $0.1313
Cache W: $0.1313
Cache R: $0.1313
skylark-embedding-vision-250615BytePlus Skylark Embedding Vision (250615) multimodal embedding model ($0.125/1M tokens list price; 105% rate).
embedding Visual Recognition 131K ctx 105%
Input: $0.1313
Output: $0.1313
Cache W: $0.1313
Cache R: $0.1313
Skylark Embedding Vision (250328) skylark-embedding-vision-250328BytePlus Skylark Embedding Vision (250328) multimodal embedding model (105% rate).
embedding Visual Recognition 64K ctx 105%
Input: $0.1313
Output: $0.1313
Cache W: $0.1313
Cache R: $0.1313