Model comparison
Compare models side by side on price, context, performance, endpoints and features. Each column is one model on one provider — put the same model twice to compare providers.
Overview
DeveloperDeepSeek
DeveloperDeepSeek
DeveloperDeepSeek
DeveloperDeepSeek
Context1M token
Context1M token
Context1M token
Context1M token
Max output384K token
Max output384K token
Max output384K token
Max output384K token
ReasoningSupported
ReasoningSupported
ReasoningSupported
ReasoningSupported
Input
Input
Input
Input
Output
Output
Output
Output
Pricing
InputOff-Peak$0.15$0.1425/1M tokensPeak$0.3$0.285/1M tokens
InputPeak$0.3$0.225/1M tokensOff-Peak$0.15$0.1125/1M tokens
InputPeak$0.3$0.195/1M tokensOff-Peak$0.15$0.0975/1M tokens
InputPeak$0.3$0.21/1M tokensOff-Peak$0.15$0.105/1M tokens
OutputOff-Peak$0.6$0.57/1M tokensPeak$1.2$1.14/1M tokens
OutputPeak$1.2$0.9/1M tokensOff-Peak$0.6$0.45/1M tokens
OutputPeak$1.2$0.78/1M tokensOff-Peak$0.6$0.39/1M tokens
OutputPeak$1.2$0.84/1M tokensOff-Peak$0.6$0.42/1M tokens
ReadOff-Peak$0.015$0.0143/1M tokensPeak$0.03$0.0285/1M tokens
ReadPeak$0.006$0.0045/1M tokensOff-Peak$0.003$0.0023/1M tokens
ReadPeak$0.006$0.0039/1M tokensOff-Peak$0.003$0.002/1M tokens
ReadPeak$0.006$0.0042/1M tokensOff-Peak$0.003$0.0021/1M tokens
Performance
Avg. time to first token1.93 s
Avg. time to first token2.71 s
Avg. time to first token8.18 s
Avg. time to first token2.81 s
Avg. throughput175.0 tok/s
Avg. throughput381.8 tok/s
Avg. throughput251.9 tok/s
Avg. throughput193.2 tok/s
Availability100.0%
Availability99.9%
Availability100.0%
Availability100.0%
Averages over the recent window, weighted by request volume — not percentiles. Hours with no successful samples are left out rather than counted as zero.
Endpoints
OpenAI Chat Completions
/v1/chat/completions/v1/chat/completions/v1/chat/completions/v1/chat/completionsOpenAI Responses
/v1/responses/v1/responses/v1/responses/v1/responsesAnthropic Messages
/v1/messages/v1/messages/v1/messages/v1/messagesGoogle Gemini
/v1beta/models/{model}:generateContent/v1beta/models/{model}:generateContent/v1beta/models/{model}:generateContent/v1beta/models/{model}:generateContentOpenAI Images
/v1/images/generations/v1/images/generations/v1/images/generations/v1/images/generations/v1/images/edits/v1/images/edits/v1/images/edits/v1/images/editsAlibaba Model Studio Video
/api/v1/services/aigc/video-generation/video-synthesis/api/v1/services/aigc/video-generation/video-synthesis/api/v1/services/aigc/video-generation/video-synthesis/api/v1/services/aigc/video-generation/video-synthesis/api/v1/tasks/{id}/api/v1/tasks/{id}/api/v1/tasks/{id}/api/v1/tasks/{id}MiniMax Video
/v2/video_generation/v2/video_generation/v2/video_generation/v2/video_generation/v2/query/video_generation/{id}/v2/query/video_generation/{id}/v2/query/video_generation/{id}/v2/query/video_generation/{id}Alibaba Model Studio Image
/api/v1/services/aigc/multimodal-generation/generation/api/v1/services/aigc/multimodal-generation/generation/api/v1/services/aigc/multimodal-generation/generation/api/v1/services/aigc/multimodal-generation/generation/api/v1/services/aigc/image-generation/generation/api/v1/services/aigc/image-generation/generation/api/v1/services/aigc/image-generation/generation/api/v1/services/aigc/image-generation/generationVolcengine Ark Video
/api/v3/contents/generations/tasks/api/v3/contents/generations/tasks/api/v3/contents/generations/tasks/api/v3/contents/generations/tasks/api/v3/contents/generations/tasks/{id}/api/v3/contents/generations/tasks/{id}/api/v3/contents/generations/tasks/{id}/api/v3/contents/generations/tasks/{id}Volcengine Ark Image
/api/v3/images/generations/api/v3/images/generations/api/v3/images/generations/api/v3/images/generationsxAI Video
/v1/videos/generations/v1/videos/generations/v1/videos/generations/v1/videos/generations/v1/videos/edits/v1/videos/edits/v1/videos/edits/v1/videos/edits/v1/videos/extensions/v1/videos/extensions/v1/videos/extensions/v1/videos/extensions/v1/videos/{id}/v1/videos/{id}/v1/videos/{id}/v1/videos/{id}TypeSafeAI System One
/v1/systemone/v1/systemone/v1/systemone/v1/systemoneAmux Tasks
/v1/tasks/v1/tasks/v1/tasks/v1/tasks/v1/tasks/{id}/v1/tasks/{id}/v1/tasks/{id}/v1/tasks/{id}/v1/tasks/{id}/cancel/v1/tasks/{id}/cancel/v1/tasks/{id}/cancel/v1/tasks/{id}/cancelFeatures
Streaming
Streaming
Streaming
Streaming
Reasoning
Reasoning
Reasoning
Reasoning
Function calling
Function calling
Function calling
Function calling
Structured output
Structured output
Structured output
Structured output
Prompt caching
Prompt caching
Prompt caching
Prompt caching
Vision
Vision
Vision
Vision
Image output
Image output
Image output
Image output
In-chat image generation
In-chat image generation
In-chat image generation
In-chat image generation
Video output
Video output
Video output
Video output