MaxAPI public pricing
1 credit = 1 USD. Failed requests are not charged. Available route_mode tiers vary by model and account access; use the JSON field, or X-MaxAPI-Route-Mode on Gemini-native endpoints, to select a supported tier.
These are public catalogue prices, not a live account quote. Check live pricing for current account-specific prices and enabled routes.
Catalogue summaries do not enumerate every conditional price tier or minimum charge. Check current account prices for the applicable conditions, billing units and minimum charges before estimating cost.
Routing precedence: a configured API key route_modes list takes priority over the request. Otherwise, an explicit request route is used; if neither is set, the model default applies. Check the API key settings before comparing route prices.
Current account prices · Machine-readable pricing
GPT Image 2
GPT Image 2 supports image generation and editing with token-based image billing on MaxAPI.
- official: text_input $5 / 1M tokens
- official: image_input $8 / 1M tokens
- official: image_output $30 / 1M tokens
- official-cheap: text_input $3 / 1M tokens
- official-cheap: image_input $4.8 / 1M tokens
- official-cheap: image_output $18 / 1M tokens
- mix: $0.019 per output image
GPT Image 2.5 Sunburst
Image generation and editing. Official and Official Cheap: actual token-based billing. Mix: 0.018 credits per successful request. Account multipliers apply.
- mix: $0.018 per call
- official: Uncached text input $4.5 / 1M tokens
- official: Cached text input $1.125 / 1M tokens
- official: Uncached image input $7.2 / 1M tokens
- official: Cached image input $1.8 / 1M tokens
- official: Image output $27 / 1M tokens
- official-cheap: Uncached text input $3.308823 / 1M tokens
- official-cheap: Cached text input $0.827205 / 1M tokens
- official-cheap: Uncached image input $5.294117 / 1M tokens
- official-cheap: Cached image input $1.323529 / 1M tokens
- official-cheap: Image output $19.852941 / 1M tokens
GPT Image 2.5 Flare
Image generation and editing. Official and Official Cheap: actual token-based billing. Mix: 0.018 credits per successful request. Account multipliers apply.
- mix: $0.018 per call
- official: Uncached text input $4.5 / 1M tokens
- official: Cached text input $1.125 / 1M tokens
- official: Uncached image input $7.2 / 1M tokens
- official: Cached image input $1.8 / 1M tokens
- official: Image output $27 / 1M tokens
- official-cheap: Uncached text input $3.308823 / 1M tokens
- official-cheap: Cached text input $0.827205 / 1M tokens
- official-cheap: Uncached image input $5.294117 / 1M tokens
- official-cheap: Cached image input $1.323529 / 1M tokens
- official-cheap: Image output $19.852941 / 1M tokens
Gemini 2.5 Flash Image
Gemini 2.5 Flash Image supports fast fixed-price image generation and reference-based editing on MaxAPI.
- mix: $0.005 per call
- official: $0.04 per call
- official-cheap: $0.024 per call
Gemini 3.1 Flash Lite Image
Nano Banana 2 Lite focuses on lightweight 1K generation and localized image edits. Check this MaxAPI entry's reference limits and route pricing before use.
- official: input $0.25 / 1M tokens
- official: output $30 / 1M tokens
- official: reasoning $1.5 / 1M tokens
- official-cheap: input $0.15 / 1M tokens
- official-cheap: output $18 / 1M tokens
- official-cheap: reasoning $0.9 / 1M tokens
- mix: $0.015 per call
Nanobanana Pro
Nanobanana Pro supports high quality image generation and reference-based editing on MaxAPI.
- official: input $2 / 1M tokens
- official: output $120 / 1M tokens
- official: reasoning $12 / 1M tokens
- official-cheap: input $1.2 / 1M tokens
- official-cheap: output $72 / 1M tokens
- official-cheap: reasoning $7.2 / 1M tokens
- mix: $0.065 per output image
Gemini 3.1 Flash Image Preview
Gemini 3.1 Flash Image Preview supports fast high-resolution image generation and reference-based editing on MaxAPI.
- official: input $0.5 / 1M tokens
- official: output $60 / 1M tokens
- official: reasoning $3 / 1M tokens
- official-cheap: input $0.3 / 1M tokens
- official-cheap: output $36 / 1M tokens
- official-cheap: reasoning $1.8 / 1M tokens
- mix: $0.045 per output image
Nano Banana 2.1
Nano Banana 2.1 generates and edits 1K, 2K, and 4K images with up to 14 references. The Gemini native API supports thinking levels, system instructions, and Google Search grounding.
- official: input $1.5 / 1M tokens
- official: output $30 / 1M tokens
- official: reasoning $7.5 / 1M tokens
- official-cheap: input $0.9 / 1M tokens
- official-cheap: output $18 / 1M tokens
- official-cheap: reasoning $4.5 / 1M tokens
- mix: $0.045 per output image
Gemini 3 Pro Image Preview Beta
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
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
GPT Image 2 Beta supports image generation and editing with mix and official-cheap routes.
- official-cheap: text_input $0.35 / 1M tokens
- official-cheap: image_input $0.35 / 1M tokens
- official-cheap: image_output $0.7 / 1M tokens
- mix: $0.019 per output image
Gemini 2.5 Flash
Gemini 2.5 Flash is a fast, low-cost language model for chat and text generation, billed per token on MaxAPI.
- official-cheap: input $0.18 / 1M tokens
- official-cheap: output $1.5 / 1M tokens
- official-cheap: audio_input $0.6 / 1M tokens
- official-cheap: cache_read $0.018 / 1M tokens
Gemini 2.5 Flash-Lite
Gemini 2.5 Flash-Lite focuses on lightweight classification and explicit field extraction, billed per token on MaxAPI.
- official-cheap: input $0.06 / 1M tokens
- official-cheap: output $0.24 / 1M tokens
- official-cheap: audio_input $0.18 / 1M tokens
- official-cheap: cache_read $0.006 / 1M tokens
Gemini 2.5 Pro
Gemini 2.5 Pro focuses on complex technical reasoning and long-document analysis. Context capacity and pricing thresholds are separate; route limits apply.
- official-cheap: input (≤200k) $0.75 / 1M tokens
- official-cheap: output (≤200k) $6 / 1M tokens
- official-cheap: cache_read (≤200k) $0.075 / 1M tokens
- official-cheap: input (>200k) $1.5 / 1M tokens
- official-cheap: output (>200k) $9 / 1M tokens
- official-cheap: cache_read (>200k) $0.15 / 1M tokens
Gemini 3 Flash Preview
Gemini 3 Flash Preview supports interactive reasoning and multimodal understanding with text output. Preview availability and route capabilities should be checked.
- official-cheap: input $0.3 / 1M tokens
- official-cheap: output $1.8 / 1M tokens
- official-cheap: audio_input $0.6 / 1M tokens
- official-cheap: cache_read $0.03 / 1M tokens
Gemini 3.1 Flash-Lite
Gemini 3.1 Flash-Lite focuses on high-frequency translation, extraction and lightweight text workflows, billed per token on MaxAPI.
- official-cheap: input $0.15 / 1M tokens
- official-cheap: output $0.9 / 1M tokens
- official-cheap: audio_input $0.3 / 1M tokens
- official-cheap: cache_read $0.015 / 1M tokens
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview focuses on complex engineering, reasoning and multi-step planning. MaxAPI route capabilities and input limits apply.
- official-cheap: input (≤200k) $1.2 / 1M tokens
- official-cheap: output (≤200k) $7.2 / 1M tokens
- official-cheap: cache_read (≤200k) $0.12 / 1M tokens
- official-cheap: input (>200k) $2.4 / 1M tokens
- official-cheap: output (>200k) $10.8 / 1M tokens
- official-cheap: cache_read (>200k) $0.24 / 1M tokens
Gemini 4 Argon
Gemini 4 Argon is a stable long-context reasoning model for complex analysis and engineering, available through MaxAPI's official-cheap route with token-based billing and account chat history.
- official-cheap: input $2.4 / 1M tokens
- official-cheap: output $12 / 1M tokens
- official-cheap: cache_read $0.12 / 1M tokens
Gemini 3.8 Flash
Gemini 3.8 Flash supports text generation and software engineering workflows through MaxAPI's official-cheap route, with token-based billing and account chat history.
- official-cheap: input $0.45 / 1M tokens
- official-cheap: output $2.25 / 1M tokens
- official-cheap: cache_read $0.045 / 1M tokens
Gemini 3.5 Flash
Gemini 3.5 Flash is a stable text-model entry for iterative engineering and multi-step workflows. Applications manage execution and validation.
- official-cheap: input $0.9 / 1M tokens
- official-cheap: output $5.4 / 1M tokens
- official-cheap: cache_read $0.09 / 1M tokens
Seedance 2.0 Fast
Seedance 2.0 Fast generates video, billed per output token by resolution and whether a reference video is used.
- official: 480p / 720p · no reference video $5.6 / 1M tokens
- official: 480p / 720p · with reference video $3.3 / 1M tokens
- official-cheap: 480p / 720p · no reference video $5.04 / 1M tokens
- official-cheap: 480p / 720p · with reference video $2.97 / 1M tokens
Seedance 2.0 Mini
Seedance 2.0 Mini is the lowest-cost Seedance 2.0 tier at 480p or 720p, billed per output token by resolution and whether a reference video is used.
- official: 480p / 720p · no reference video $3.5 / 1M tokens
- official: 480p / 720p · with reference video $2.1 / 1M tokens
- official-cheap: 480p / 720p · no reference video $3.15 / 1M tokens
- official-cheap: 480p / 720p · with reference video $1.89 / 1M tokens
Seedance 2.0
Seedance 2.0 supports up to 4K, billed per output token by resolution and whether a reference video is used.
- official: 480p / 720p · no reference video $7 / 1M tokens
- official: 480p / 720p · with reference video $4.3 / 1M tokens
- official: 1080p · no reference video $7.7 / 1M tokens
- official: 1080p · with reference video $4.7 / 1M tokens
- official: 4K · no reference video $4 / 1M tokens
- official: 4K · with reference video $2.4 / 1M tokens
- official-cheap: 480p / 720p · no reference video $6.3 / 1M tokens
- official-cheap: 480p / 720p · with reference video $3.87 / 1M tokens
- official-cheap: 1080p · no reference video $6.93 / 1M tokens
- official-cheap: 1080p · with reference video $4.23 / 1M tokens
- official-cheap: 4K · no reference video $3.6 / 1M tokens
- official-cheap: 4K · with reference video $2.16 / 1M tokens
Seedance 2.5
Seedance 2.5 multimodal video generation at 480p, 720p, or 1080p, billed per output token. Supports 4 to 30 second clips, up to 30 reference images, 10 reference videos, and 10 reference audio files.
- official: 480p / 720p · no reference video $10.7 / 1M tokens
- official: 480p / 720p · with reference video $6.4 / 1M tokens
- official: 1080p · no reference video $11.7 / 1M tokens
- official: 1080p · with reference video $7 / 1M tokens
- official-cheap: 480p / 720p · no reference video $9.63 / 1M tokens
- official-cheap: 480p / 720p · with reference video $5.76 / 1M tokens
- official-cheap: 1080p · no reference video $10.53 / 1M tokens
- official-cheap: 1080p · with reference video $6.3 / 1M tokens
Z-Image Turbo
Text-to-image via Replicate. Official pricing follows the returned resolution tier and billing megapixel count, not raw pixel area. Account multipliers apply.
- official: target 0.5, $0.0025 per returned billing megapixel
- official: target 1, $0.005 per returned billing megapixel
- official: target 2, $0.01 per returned billing megapixel
- official: target 3, $0.015 per returned billing megapixel
- official: target 4, $0.02 per returned billing megapixel
Qwen Image Edit 2511
Reference-image editing via Replicate with up to 16 input images and one output image. Official: 0.03 credits per output image; account multipliers apply.
- official: $0.03 per output image
Wan 2.2 I2V Fast
Image-to-video via Replicate with an optional last frame; 480p or 720p, no audio. Official: 0.05 credits per 480p video or 0.11 per 720p video (0.065 / 0.145 with 30 fps interpolation); account multipliers apply.
- official: 480p $0.05 / video
- official: 720p $0.11 / video
- official: 480p + 30 fps interpolation $0.065 / video
- official: 720p + 30 fps interpolation $0.145 / video
Seedream 4.0
Image generation and reference editing. Mix: 0.045 credits per output image; account multipliers apply. Official: 0.03 credits per image.
- mix: $0.045 per output image
- official: $0.03 per output image
Seedream 4.5
Image generation and reference editing. Mix: 0.045 credits per output image; account multipliers apply. Official: 0.04 credits per image.
- mix: $0.045 per output image
- official: $0.04 per output image
Seedream 5.0
Image generation and reference editing. Mix: 0.045 credits per output image; account multipliers apply.
- mix: $0.045 per output image
Seedream 5.0 Pro
Image generation and reference editing. Mix: 0.045 credits per output image; account multipliers apply. Official: 0.045 (1K) / 0.09 (2K) credits per image; layer decomposition: 0.0225 (small) / 0.045 (large) credits per output layer.
- mix: $0.045 per output image
- official: $0.09 per output image
- official: $0.045 per output image
- official: $0.0225 per output image
- official: $0.045 per output image
Seedream 5.0 Lite
Seedream 5.0 Lite image generation and reference editing. Official: 0.035 credits per output image; 2K/3K; account multipliers apply.
- official: $0.035 per output image