Model hub
Browse available model capabilities behind the unified gateway and quickly choose the best fit for your product by scenario.
This page highlights the Gemini image models currently prioritized by BananaRouter, including gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, and gemini-2.5-flash-image.
gpt-image-2
From $0.0057/call
gpt-image-2
gpt-5.5
Input $0.40/1M tokensOutput $2.40/1M tokensCache write $0.02/1M tokensInput (>272K) $0.80/1M tokensOutput (>272K) $3.60/1M tokensCache write (>272K) $0.04/1M tokens
gpt-5.5
gpt-image-1.5
From $0.0057/call
gpt-image-1.5
GLM-5.2
Input $0.9143/1M tokensOutput $3.20/1M tokensCache read $0.2286/1M tokens
GLM-5.2
gemini-3.1-flash-lite-image
From $0.01/call
1K
gpt-5.6-sol
Input $0.40/1M tokensOutput $2.00/1M tokensCache read $0.04/1M tokensCache write $0.50/1M tokensInput (>272K) $0.80/1M tokensOutput (>272K) $3.00/1M tokensCached input (>272K) $0.08/1M tokensCache write (>272K) $1.00/1M tokens
gpt-5.6-sol
gpt-5.6-terra
Input $0.16/1M tokensOutput $0.96/1M tokensCache read $0.0157/1M tokensCache write $0.20/1M tokensInput (>272K) $0.32/1M tokensOutput (>272K) $1.44/1M tokensCached input (>272K) $0.0314/1M tokensCache write (>272K) $0.40/1M tokens
gpt-5.6-terra
gpt-5.6-luna
Input $0.0343/1M tokensOutput $0.2043/1M tokensCache read $0.0029/1M tokensCache write $0.0429/1M tokensInput (>272K) $0.0686/1M tokensOutput (>272K) $0.2143/1M tokensCached input (>272K) $0.0071/1M tokensCache write (>272K) $0.0086/1M tokens
gpt-5.6-luna
grok-imagine-video-1.5
From $0.1143/call
480p, 720p, 1080p
kimi-k3
Input $2.4286/1M tokensOutput $12.1429/1M tokensCache read $0.2429/1M tokens
kimi-k3
veo-3.1-generate-preview
From $0.0143/second
720p, 1080p
veo-3.1-fast-generate-preview
From $0.0071/second
720p, 1080p
gemini-3.5-flash-lite
Input $0.1057/1M tokensOutput $0.8757/1M tokensCache read $0.0105/1M tokens
gemini-3.5-flash-lite
MiniMax-H3
From $0.0714/second
768p, 2K
kling-3.0
From $0.0114/second
720p, 1080p, 4k
kling-3.0-omni
From $0.0114/second
720p, 1080p, 4k
midjourney
From $0.0429/call
midjourney
gemini-3.7-flash
Input $0.1871/1M tokensOutput $0.9371/1M tokensCache read $0.0714/1M tokens
gemini-3.7-flash
glm-5.3
Input $0.9143/1M tokensOutput $3.20/1M tokensCache read $0.2286/1M tokens
glm-5.3
qwen3.8-max
Input $1.2857/1M tokensOutput $3.8571/1M tokensCache read $0.1614/1M tokensCache write $1.6071/1M tokens
qwen3.8-max
MiniMax-M3
Input $0.54/1M tokensOutput $2.16/1M tokensCache read $0.1086/1M tokens
MiniMax-M3
gpt-5.2
Input $0.1757/1M tokensOutput $1.40/1M tokensCache read $0.002/1M tokens
gpt-5.2
grok-imagine-image-2.0
From $0.0429/image
1K, 2K
gemini-3.8-flash
Input $0.1871/1M tokensOutput $0.9371/1M tokensCache read $0.0714/1M tokens
gemini-3.8-flash
claude-fable-5-1
Input $3.7143/1M tokensOutput $18.4286/1M tokensCache read $0.4286/1M tokensCache write (5m) $4.2857/1M tokensCache write (1h) $6.8571/1M tokens
claude-fable-5-1
gpt-6-astra
Input $1.50/1M tokensOutput $7.50/1M tokensCache read $0.15/1M tokensCache write $1.8757/1M tokensInput (>272K) $3.00/1M tokensOutput (>272K) $11.25/1M tokensCached input (>272K) $0.30/1M tokensCache write (>272K) $3.75/1M tokens
gpt-6-astra
seedream-5.0
From $0.0429/call
2k, 3k, 4k
seedream-5.0-pro
From $0.0429/call
1k, 2k
gpt-image-2.5-flare
From $0.0057/call
gpt-image-2.5-flare
gpt-image-2.5-sunburst
From $0.0057/call
gpt-image-2.5-sunburst
doubao-seedream-5-0-pro-260628
From $0.0429/image
doubao-seedream-5-0-pro-260628
doubao-seedream-5-0-260128
From $0.0314/call
doubao-seedream-5-0-260128
deepseek-v4.1-flash
Off-peakInput $0.0857 · Cache read $0.0017 · Output $0.3429 / 1M tokensPeakInput $0.1714 · Cache read $0.0034 · Output $0.6857 / 1M tokens
deepseek-v4.1-flash
claude-opus-5-5
Input $1.4686/1M tokensOutput $7.34/1M tokensCache read $0.0729/1M tokensCache write (5m) $1.8343/1M tokensCache write (1h) $2.9357/1M tokens
claude-opus-5-5
gpt-6-sol
Input $0.30/1M tokensOutput $1.50/1M tokensCache read $0.03/1M tokensCache write $0.06/1M tokensInput (>272K) $0.60/1M tokensOutput (>272K) $3.00/1M tokensCached input (>272K) $0.06/1M tokensCache write (>272K) $0.12/1M tokens
gpt-6-sol
gpt-6.1-sol
Input $0.20/1M tokensOutput $1.00/1M tokensCache read $0.04/1M tokensCache write $0.02/1M tokensInput (>272K) $0.40/1M tokensOutput (>272K) $1.50/1M tokensCached input (>272K) $0.08/1M tokensCache write (>272K) $0.0343/1M tokens
gpt-6.1-sol
claude-sonnet-5-5
Input $0.7343/1M tokensOutput $3.67/1M tokensCache read $0.0729/1M tokensCache write (5m) $0.9171/1M tokensCache write (1h) $1.4686/1M tokens
claude-sonnet-5-5
veo_3_1
From $0.1357/call
720p
veo_3_1-fast
From $0.1143/call
720p
claude-haiku-5-5
Input $0.0371/1M tokensOutput $0.1829/1M tokensCache read $0.0043/1M tokensCache write (5m) $0.0457/1M tokensCache write (1h) $0.0729/1M tokens
claude-haiku-5-5
gemini-3.1-flash-image
From $0.0143/call
Fast Gemini image generation preview model with multi-resolution output, suitable for creative iteration and UI drafts.
gemini-nano-banana-2.1
From $0.0171/call
1K, 2K, 4K
gemini-3-pro-image
From $0.0314/call
Higher-quality Gemini image model with stronger composition and detail for production-oriented visuals.
gemini-2.5-flash-image
From $0.01/call
Balanced Gemini 2.5 image model for everyday generation workloads with reliable latency.
gemini-3.1-pro-preview
Input $0.50/1M tokensOutput $3.00/1M tokensCache read $0.0571/1M tokensInput (>200k) $0.7143/1M tokensOutput (>200k) $5.1429/1M tokensCache read (>200k) $0.1143/1M tokens
gemini-3.1-pro-preview
gemini-3-flash-preview
Input $0.1257/1M tokensOutput $0.75/1M tokens
gemini-3-flash-preview
gemini-3.1-flash-lite
Input $0.0629/1M tokensOutput $0.3757/1M tokens
gemini-3.1-flash-lite
gemini-3.5-flash
Input $0.3757/1M tokensOutput $2.25/1M tokensCache read $0.15/1M tokens
gemini-3.5-flash
gemini-3.6-flash
Input $0.1871/1M tokensOutput $0.9371/1M tokensCache read $0.0743/1M tokens
gemini-3.6-flash
gemini-2.5-flash
Input $0.0757/1M tokensOutput $0.6257/1M tokensCache read $0.01/1M tokens
gemini-2.5-flash
gemini-2.5-pro
Input $0.3129/1M tokensOutput $2.50/1M tokensCache read $0.0414/1M tokens
gemini-2.5-pro
gemini-2.5-flash-lite
Input $0.0257/1M tokensOutput $0.10/1M tokensCache read $0.0029/1M tokens
gemini-2.5-flash-lite
claude-opus-4-8
Input $1.00/1M tokensOutput $5.00/1M tokensCache read $0.0857/1M tokensCache write (5m) $0.8571/1M tokensCache write (1h) $1.3714/1M tokens
claude-opus-4-8
claude-sonnet-5
Input $1.1429/1M tokensOutput $5.7143/1M tokensCache read $0.0714/1M tokensCache write (5m) $1.00/1M tokensCache write (1h) $1.60/1M tokens
claude-sonnet-5
claude-opus-4-7
Input $1.00/1M tokensOutput $5.00/1M tokensCache read $0.0857/1M tokensCache write (5m) $0.8571/1M tokensCache write (1h) $1.3714/1M tokens
claude-opus-4-7
claude-opus-4-6
Input $1.00/1M tokensOutput $5.00/1M tokensCache read $0.0857/1M tokensCache write (5m) $0.8571/1M tokensCache write (1h) $1.3714/1M tokens
claude-opus-4-6
claude-fable-5
Input $3.7143/1M tokensOutput $18.4286/1M tokensCache read $0.4286/1M tokensCache write (5m) $4.2857/1M tokensCache write (1h) $6.8571/1M tokens
claude-fable-5
claude-opus-5
Input $1.90/1M tokensOutput $9.50/1M tokensCache read $0.19/1M tokensCache write (5m) $2.3757/1M tokensCache write (1h) $3.80/1M tokens
claude-opus-5
claude-sonnet-4-6
Input $0.60/1M tokensOutput $3.00/1M tokensCache read $0.0714/1M tokensCache write (5m) $1.00/1M tokensCache write (1h) $1.60/1M tokens
claude-sonnet-4-6
deepseek-v4-flash
Off-peakInput $0.0857 · Cache read $0.0017 · Output $0.3429 / 1M tokensPeakInput $0.1714 · Cache read $0.0034 · Output $0.6857 / 1M tokens
deepseek-v4-flash
deepseek-v4-pro
Off-peakInput $0.5143 · Cache read $0.0171 · Output $1.5429 / 1M tokensPeakInput $1.0286 · Cache read $0.0343 · Output $3.0857 / 1M tokens
deepseek-v4-pro
grok-imagine-image-quality
From $0.0357/image
1k, 2k
grok-imagine-image
From $0.0214/image
1k, 2k