Sais
Auto
Adaptive routing across enabled Sais chat models based on prompt shape, with a fast fallback to `sais/glm-5.3-flash`.
chat · api
Input / 1M tokens
—
Cached / 1M —
Output / 1M tokens
—
Models
Explore capabilities, compare prices, and choose a Sais public model ID. Prices are customer-facing USDG rates, independent of upstream cost.
89 models
89 shown
Sais
Adaptive routing across enabled Sais chat models based on prompt shape, with a fast fallback to `sais/glm-5.3-flash`.
chat · api
Input / 1M tokens
—
Cached / 1M —
Output / 1M tokens
—
Anthropic
Frontier route for ambitious coding, agentic work, and long-form reasoning.
chat · api
Input / 1M tokens
$8.34
Cached / 1M —
Output / 1M tokens
$41.67
Anthropic
NewLatest 1M-context Claude route for long-horizon agentic coding, research, and knowledge work.
chat · api
Input / 1M tokens
$9
Cached / 1M $0.225
Output / 1M tokens
$45
Anthropic
Frontier reasoning and coding route.
chat · api
Input / 1M tokens
$5.4
Cached / 1M $0.54
Output / 1M tokens
$27
Anthropic
Latest Opus frontier route for complex coding, agents, and long-horizon reasoning.
chat · api
Input / 1M tokens
$4.5
Cached / 1M $0.45
Output / 1M tokens
$22.5
Anthropic
High-end frontier reasoning, coding, and multimodal route.
chat · api
Input / 1M tokens
$1.67
Cached / 1M $0.167
Output / 1M tokens
$8.34
DeepSeek
1M-context route with upgraded agentic coding, tool use, and fast long-form analysis.
chat · api
Input / 1M tokens
$0.1575
Cached / 1M $0.0315
Output / 1M tokens
$0.315
DeepSeek
DeepSeek Pro class route for heavier reasoning and coding work.
chat · api
Input / 1M tokens
$1.557
Cached / 1M —
Output / 1M tokens
$3.4164
DeepSeek
NewCED-architecture DeepSeek Flash route with native vision, agentic coding, tool use, and compressed KV caching for long runs.
chat · api
Input / 1M tokens
$0.1575
Cached / 1M $0.0032
Output / 1M tokens
$0.63
Black Forest Labs
Flexible FLUX route balancing speed, cost, and visual quality.
images · api
From / image
$0.04
Black Forest Labs
Top-tier FLUX image route for maximum detail and fidelity.
images · api
From / image
$0.1
Black Forest Labs
High-fidelity FLUX image generation with strong composition control.
images · api
From / image
$0.06
Black Forest Labs
NewFLUX.3 Video with opening and closing keyframe control.
video · api
From / video
$0.4
Black Forest Labs
NewFLUX.3 Video text-to-video with controlled motion workflows.
video · api
From / video
$0.4
Fast 1M-context Gemini route for reasoning, multimodal analysis, agents, and coding.
chat · api
Input / 1M tokens
$1.6875
Cached / 1M $0.1688
Output / 1M tokens
$8.4375
Lower-cost uncensored route for general chat. No verified Sais upstream yet.
chat · api
Input / 1M tokens
$0.1463
Cached / 1M —
Output / 1M tokens
$0.45
Z.ai
Fast uncensored reasoning route. No verified Sais upstream yet.
chat · api
Input / 1M tokens
$0.126
Cached / 1M —
Output / 1M tokens
$0.72
Z.ai
Reasoning route for planning and code.
chat · api
Input / 1M tokens
$0.9
Cached / 1M —
Output / 1M tokens
$2.88
Z.ai
Higher-throughput GLM reasoning route.
chat · api
Input / 1M tokens
$1.08
Cached / 1M —
Output / 1M tokens
$3.6
Z.ai
1M-context agentic engineering route.
chat · api
Input / 1M tokens
$0.657
Cached / 1M —
Output / 1M tokens
$1.5319
Z.ai
Latest 1M-context GLM route for software engineering.
chat · api
Input / 1M tokens
$1.3
Cached / 1M —
Output / 1M tokens
$4.09
Z.ai
NewFast GLM coding and chat route with 1M context.
chat · api
Input / 1M tokens
$0.0675
Cached / 1M $0.0135
Output / 1M tokens
$0.225
OpenAI
OpenAI image generation and editing with reference-image support.
images · api
From / image
$0.08
OpenAI
NewFrontier OpenAI image route for detailed creative and design work.
images · api
From / image
$0.12
OpenAI
Frontier OpenAI route for hard reasoning, code, and long-context work.
chat · api
Input / 1M tokens
$5.625
Cached / 1M —
Output / 1M tokens
$33.75
OpenAI
Efficient frontier route for vision and broad reasoning.
chat · api
Input / 1M tokens
$1.125
Cached / 1M $0.1125
Output / 1M tokens
$6.75
OpenAI
Efficient GPT-5.6 Pro route. No distinct verified upstream ID yet.
chat · api
Input / 1M tokens
$1.125
Cached / 1M $0.1125
Output / 1M tokens
$6.75
OpenAI
Highest-tier GPT-5.6 route for difficult reasoning, vision, and long-context tasks.
chat · api
Input / 1M tokens
$5.625
Cached / 1M $0.5625
Output / 1M tokens
$33.75
OpenAI
Highest-tier GPT-5.6 Pro route. No distinct verified upstream ID yet.
chat · api
Input / 1M tokens
$5.625
Cached / 1M $0.5625
Output / 1M tokens
$33.75
OpenAI
Balanced GPT-5.6 frontier route for reasoning, multimodal analysis, and long-context work.
chat · api
Input / 1M tokens
$2.8125
Cached / 1M $0.2813
Output / 1M tokens
$16.875
OpenAI
Balanced GPT-5.6 Pro route. No distinct verified upstream ID yet.
chat · api
Input / 1M tokens
$2.8125
Cached / 1M $0.2813
Output / 1M tokens
$16.875
OpenAI
NewOpenAI flagship 1.05M-context route for difficult reasoning, coding, research, and multimodal work.
chat · api
Input / 1M tokens
$9
Cached / 1M $0.9
Output / 1M tokens
$45
xAI
Frontier xAI route for code, vision, tool use, deep reasoning, and live web research.
chat · api
Input / 1M tokens
$2.043
Cached / 1M $0.513
Output / 1M tokens
$6.12
xAI
NewAnimate a reference image with Grok Imagine 1.5 video and audio.
video · api
From / video
$0.3
xAI
NewText-to-video generation with Grok Imagine 1.5 and audio.
video · api
From / video
$0.3
xAI
xAI image generation route with strong stylistic control.
images · api
From / image
$0.1
xAI
Animate a local reference image into a short video with audio.
video · api
From / video
$0.28
xAI
Fast text-to-video generation with audio.
video · api
From / video
$0.28
MiniMax
Animate a reference image with MiniMax Hailuo 2.3 cinematic motion.
video · api
From / video
$0.1
MiniMax
Cinematic text-to-video generation with MiniMax Hailuo 2.3.
video · api
From / video
$0.1
Moonshot AI
Fast Kimi route for coding, analysis, and long-context chat.
chat · api
Input / 1M tokens
$0.504
Cached / 1M $0.198
Output / 1M tokens
$3.15
Moonshot AI
Fast general-chat and code route.
chat · api
Input / 1M tokens
$0.765
Cached / 1M $0.1632
Output / 1M tokens
$4.1895
Moonshot AI
Kimi code route for agentic software engineering, debugging, and repo work.
chat · api
Input / 1M tokens
$0.81
Cached / 1M $0.1728
Output / 1M tokens
$3.87
Moonshot AI
Frontier Kimi route for long-context coding, multimodal analysis, and agentic tool use.
chat · api
Input / 1M tokens
$1.3
Cached / 1M $0.115
Output / 1M tokens
$6.55
Kling
NewKling V3 Pro image-to-video with cinematic motion control.
video · api
From / video
$0.3
Kling
NewKling V3 Pro text-to-video with strong motion and style control.
video · api
From / video
$0.3
Microsoft
Precision Microsoft image route for design-ready visuals.
images · api
From / image
$0.1
Microsoft
Fast Microsoft image route for high-throughput production workflows.
images · api
From / image
$0.05
MiniMax
NewAnimate a reference image with cinematic motion and audio.
video · api
From / video
$0.13
MiniMax
NewCinematic text-to-video generation with audio.
video · api
From / video
$0.13
MiniMax
Frontier MiniMax route for coding, agents, multimodal analysis, and complex reasoning.
chat · api
Input / 1M tokens
$0.3
Cached / 1M $0.06
Output / 1M tokens
$1.2
Meta
NewAgentic Meta image route that reasons before rendering.
images · api
From / image
$0.12
Balanced Gemini image route with strong prompt following and editing.
images · api
From / image
$0.08
Lower-latency Gemini image route for quick drafts and iterations.
images · api
From / image
$0.05
Fast Gemini image generation and editing for everyday creative work.
images · api
From / image
$0.04
Google image generation and semantic image editing from a reference photo.
images · api
From / image
$0.16
NVIDIA
Very low-cost fast route for simple extraction and short answers.
chat · api
Input / 1M tokens
$0.0675
Cached / 1M —
Output / 1M tokens
$0.27
NVIDIA
Large reasoning route for structured analysis and planning.
chat · api
Input / 1M tokens
$0.5625
Cached / 1M $0.1688
Output / 1M tokens
$2.8125
Qwen
Long-context analysis and coding-heavy fallback. No verified uncensored upstream yet.
chat · api
Input / 1M tokens
$0.5625
Cached / 1M $0.0563
Output / 1M tokens
$3.375
Qwen
1M-context analysis route for long docs, codebases, and transcripts.
chat · api
Input / 1M tokens
$0.45
Cached / 1M $0.045
Output / 1M tokens
$1.8
Qwen
Vision-language model for coding, research, images, video, and agentic work.
chat · api
Input / 1M tokens
$0.36
Cached / 1M —
Output / 1M tokens
$2.56
Qwen
Uncensored Qwen 3.8 27B for open-ended chat. No verified uncensored upstream yet.
chat · api
Input / 1M tokens
$0.255
Cached / 1M —
Output / 1M tokens
$1.02
Qwen
Flagship 1M-context multimodal reasoning model for coding and long-horizon agent work.
chat · api
Input / 1M tokens
$2.25
Cached / 1M $0.2813
Output / 1M tokens
$6.75
Qwen
Specialist code route for repo work, refactors, and implementation plans.
chat · api
Input / 1M tokens
$0.315
Cached / 1M $0.036
Output / 1M tokens
$1.35
Qwen
Efficient Qwen image route for general creative generation.
images · api
From / image
$0.06
Qwen
NewHigher-quality Qwen image route for detailed visual output.
images · api
From / image
$0.1
Recraft
Design-ready image generation for brand and illustration workflows.
images · api
From / image
$0.08
Runway
NewRunway Gen 4.5 image-guided video generation.
video · api
From / video
$0.25
Runway
NewRunway Gen 4.5 text-to-video generation.
video · api
From / video
$0.25
ByteDance
Fast image-to-video route with Seedance 2.0 and audio.
video · api
From / video
$0.2
ByteDance
Fast text-to-video route with Seedance 2.0 and audio.
video · api
From / video
$0.2
ByteDance
NewCompact Seedance route for quick image-to-video clips with audio.
video · api
From / video
$0.12
ByteDance
NewCompact Seedance route for quick text-to-video clips with audio.
video · api
From / video
$0.12
ByteDance
Animate a source image with cinematic motion and audio.
video · api
From / video
$0.57
ByteDance
Cinematic text-to-video model with strong style and motion control.
video · api
From / video
$0.57
ByteDance
NewEfficient Seedream route for professional visuals with reference support.
images · api
From / image
$0.08
ByteDance
NewCommercial Seedream route with web-connected retrieval and complex prompts.
images · api
From / image
$0.12
ByteDance
Premium generation for composition and text-rich creative work.
images · api
From / image
$0.1
OpenAI
NewOpenAI Sora 2 Pro image-guided cinematic video generation.
video · api
From / video
$0.5
OpenAI
NewOpenAI Sora 2 Pro text-to-video generation.
video · api
From / video
$0.5
Lower-latency Veo 3.1 Fast image-to-video route.
video · api
From / video
$0.25
Lower-latency Veo 3.1 Fast text-to-video route.
video · api
From / video
$0.25
Google Veo 3.1 image-guided video generation with audio.
video · api
From / video
$0.35
Google Veo 3.1 text-to-video generation with audio.
video · api
From / video
$0.35
Alibaba
Fast text-to-video route for short clips.
video · api
From / video
$0.05
Alibaba
NewReference-guided video generation with Wan 3.0 and audio.
video · api
From / video
$0.1
Alibaba
NewFast-mode Wan 3.0 Prime for first-frame image-to-video.
video · api
From / video
$0.14
Alibaba
NewFast-mode Wan 3.0 Prime text-to-video with audio.
video · api
From / video
$0.14
Alibaba
NewText-to-video generation with Wan 3.0 up to 1080p and audio.
video · api
From / video
$0.1
100 credits = 1 USDG. Token prices are estimated reference rates; final text/chat settlement uses actual provider usage. A dash means no published customer rate. Media prices depend on configuration. Catalog entries can exist before an upstream route is enabled.