MaxAPI public pricing
1 credit = 1 USD. Failed requests are not charged. Route modes (official, official-cheap, mix) are picked per request — the same model can offer multiple price tiers.
Pricing facts come from the backend bootstrap in services/gateway/internal/repository/db.go and are mirrored here for SEO. See pricing.json for the structured machine-readable form.
GPT Image 2 supports image generation and editing with token-based image billing on MaxAPI.
- official: text_input $5 per 1M tokens
- official: image_input $8 per 1M tokens
- official: image_output $30 per 1M tokens
- official-cheap: text_input $3 per 1M tokens
- official-cheap: image_input $4.8 per 1M tokens
- official-cheap: image_output $18 per 1M tokens
- mix: $0.019 per output image
Gemini 2.5 Flash Image supports fast fixed-price image generation and reference-based editing on MaxAPI.
- official: $0.04 per call
- official-cheap: $0.024 per call
Gemini 3.1 Flash Lite Image is the fastest, most cost-effective option for fixed-price 1K image generation and reference-based editing on MaxAPI.
Nanobanana Pro supports high quality image generation and reference-based editing on MaxAPI.
- official: input $2 per 1M tokens
- official: output $120 per 1M tokens
- official-cheap: input $1.2 per 1M tokens
- official-cheap: output $72 per 1M tokens
- mix: input $0.37 per 1M tokens
- mix: output $22.29 per 1M tokens
Gemini 3.1 Flash Image Preview supports fast high-resolution image generation and reference-based editing on MaxAPI.
- official: input $0.5 per 1M tokens
- official: output $60 per 1M tokens
- official-cheap: input $0.3 per 1M tokens
- official-cheap: output $36 per 1M tokens
- mix: input $0.093 per 1M tokens
- mix: output $11.14 per 1M tokens
Gemini 3 Pro Image Preview Beta supports 4K image generation and reference-based editing on MaxAPI.
- official-cheap: $0.085 per output image
- mix: $0.065 per output image
Gemini 3.1 Flash Image Preview Beta supports high-resolution image generation and reference-based editing on MaxAPI.
- official-cheap: $0.07 per output image
- mix: $0.045 per output image
GPT Image 2 Beta supports image generation and editing with mix and official-cheap routes.
- official-cheap: text_input $0.35 per 1M tokens
- official-cheap: image_input $0.35 per 1M tokens
- official-cheap: image_output $0.7 per 1M tokens
- mix: $0.019 per output image
Gemini 2.5 Flash is a fast, low-cost language model for chat and text generation, billed per token on MaxAPI.
- official-cheap: input $0.1235 per 1M tokens
- official-cheap: output $1.0294 per 1M tokens
- official-cheap: audio_input $0.4118 per 1M tokens
- official-cheap: cache_read $0.0124 per 1M tokens
Gemini 2.5 Flash-Lite is the most economical Gemini 2.5 language model for high-volume chat and text, billed per token on MaxAPI.
- official-cheap: input $0.0412 per 1M tokens
- official-cheap: output $0.1647 per 1M tokens
- official-cheap: audio_input $0.1235 per 1M tokens
- official-cheap: cache_read $0.0041 per 1M tokens
Gemini 2.5 Pro is a high-capability reasoning model with a 200k+ token context, billed per token on MaxAPI.
- official-cheap: input (≤200k) $0.5147 per 1M tokens
- official-cheap: output (≤200k) $4.1176 per 1M tokens
- official-cheap: cache_read (≤200k) $0.0515 per 1M tokens
- official-cheap: input (>200k) $1.0294 per 1M tokens
- official-cheap: output (>200k) $6.1765 per 1M tokens
- official-cheap: cache_read (>200k) $0.1029 per 1M tokens
Gemini 3 Flash Preview is a fast next-generation language model for chat and text generation, billed per token on MaxAPI.
- official-cheap: input $0.2059 per 1M tokens
- official-cheap: output $1.2353 per 1M tokens
- official-cheap: audio_input $0.4118 per 1M tokens
- official-cheap: cache_read $0.0206 per 1M tokens
Gemini 3.1 Flash-Lite is the most economical Gemini language model for high-volume chat and text, billed per token on MaxAPI.
- official-cheap: input $0.1029 per 1M tokens
- official-cheap: output $0.6176 per 1M tokens
- official-cheap: audio_input $0.2059 per 1M tokens
- official-cheap: cache_read $0.0103 per 1M tokens
Gemini 3.1 Pro Preview is a top-tier reasoning model with a 200k+ token context, billed per token on MaxAPI.
- official-cheap: input (≤200k) $0.8235 per 1M tokens
- official-cheap: output (≤200k) $4.9412 per 1M tokens
- official-cheap: cache_read (≤200k) $0.0824 per 1M tokens
- official-cheap: input (>200k) $1.6471 per 1M tokens
- official-cheap: output (>200k) $7.4118 per 1M tokens
- official-cheap: cache_read (>200k) $0.1647 per 1M tokens
Gemini 3.5 Flash is a balanced next-generation language model for chat and text generation, billed per token on MaxAPI.
- official-cheap: input $0.6176 per 1M tokens
- official-cheap: output $3.7059 per 1M tokens
- official-cheap: cache_read $0.0618 per 1M tokens
Seedance 2.0 Fast Beta generates 4 to 15 second videos with per-second billing.
- mix: 480p $0.0597 per second
- mix: 720p $0.0597 per second
Seedance 2.0 Beta supports per-second-billed text-to-video and reference video generation, including 1080p.
- mix: 480p $0.0597 per second
- mix: 720p $0.0597 per second
- mix: 1080p $0.0597 per second
Seedance 2.0 Fast Beta variant tuned for face/character consistency, 4 to 15 second videos with per-second billing.
- mix: 480p $0.0597 per second
- mix: 720p $0.0597 per second
Seedance 2.0 Beta variant tuned for face/character consistency, with per-second billing and 1080p support.
- mix: 480p $0.0597 per second
- mix: 720p $0.0597 per second
- mix: 1080p $0.0597 per second
Seedance 2.0 Fast generates video, billed per output token by resolution and reference mode.
- official-cheap: 480p $0.104 per second
- official-cheap: 720p $0.104 per second
- mix: 480p $0.09 per second
- mix: 720p $0.09 per second
Seedance 2.0 supports up to 1080p, billed per output token by resolution and reference mode.
- official-cheap: 480p $0.127 per second
- official-cheap: 720p $0.127 per second
- official-cheap: 1080p $0.127 per second
- mix: 480p $0.112 per second
- mix: 720p $0.112 per second
- mix: 1080p $0.112 per second