TokenReply

Loading…

Reload
74
Classic UIClassic
ClassicSign in

Google

Google models · 25

gemini-3.8-flash-plus-free

Plus-only free model. Same model as the paid gemini-3.8-flash, billed at zero, 50 requests per day.

Roleplay

Scores from gemini-3.8-flash

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

Creative Writing v3
gemini-3.8-flash: 1,744.5
145 Models · 2026-10-25

LiveBench · Story constraint following
gemini-3.8-flash-high: 82.75
71 Models · 2026-10-25

LiveBench · Theory of mind
gemini-3.8-flash-high: 76.92
71 Models · 2026-10-25

8.4/ 10
Input / 1M tokens
$0.00
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

Creative Writing v3
gemini-3.6-flash: 1,602.4
145 Models · 2026-10-25

LiveBench · Story constraint following
gemini-3.6-flash-high: 75.6
71 Models · 2026-10-25

LiveBench · Theory of mind
gemini-3.6-flash-high: 78.85
71 Models · 2026-10-25

7.6/ 10
Input / 1M tokens
$1.13
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
google/gemma-4-26B-A4B-it: 1,454.6
83 Models · 2026-10-25

Creative Writing v3
google/gemma-4-26B-A4B-it: 1,305
145 Models · 2026-10-25

6.5/ 10
Input / 1M tokens
$0.075
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
google/gemma-4-31B-it: 1,463.5
83 Models · 2026-10-25

Creative Writing v3
google/gemma-4-31B-it: 1,368.5
145 Models · 2026-10-25

6.7/ 10
Input / 1M tokens
$0.07

gemini-2.5-flash-image

Google Nano Banana (gemini-2.5-flash-image). Text-to-image and image editing on /v1/images/generations and /v1/images/edits, or inline in a chat response. Single resolution: this model ignores size tiers upstream, so one flat per-image price.

Roleplay

No matching public benchmark is available for this model.

Not measured
Per request
$0.06

gemini-3.5-flash-lite

Google's fastest and most cost-efficient Gemini 3.5 model for high-throughput agentic tasks, translation, and simple data processing.

Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

Creative Writing v3
gemini-3.5-flash-lite: 1,559.3
145 Models · 2026-10-25

LiveBench · Story constraint following
gemini-3.5-flash-lite-high: 67.47
71 Models · 2026-10-25

LiveBench · Theory of mind
gemini-3.5-flash-lite-high: 50
71 Models · 2026-10-25

5.3/ 10
Input / 1M tokens
$0.225

gemini-3.7-flash

Multimodal Google model for fast agentic workflows, coding, and complex multi-step reasoning, with a 1M-token context window.

Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

Creative Writing v3
gemini-3.7-flash: 1,719.6
145 Models · 2026-10-25

LiveBench · Story constraint following
gemini-3.7-flash-high: 82.25
71 Models · 2026-10-25

LiveBench · Theory of mind
gemini-3.7-flash-high: 82.69
71 Models · 2026-10-25

8.6/ 10
Input / 1M tokens
$0.563
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

LiveBench · Story constraint following
gemini-3.5-flash-high: 75.2
71 Models · 2026-10-25

LiveBench · Theory of mind
gemini-3.5-flash-high: 80.77
71 Models · 2026-10-25

7.9/ 10
Input / 1M tokens
$0.75

gemini-4-argon

Google's Gemini 4 generation model with a 1M-token context window and adjustable thinking, for complex reasoning, coding and agentic workflows.

Roleplay

No matching public benchmark is available for this model.

Not measured
Input / 1M tokens
$1

gemini-3.1-flash-image

Google Nano Banana 2 (gemini-3.1-flash-image). Text-to-image and image editing on /v1/images/generations and /v1/images/edits, or inline in a chat response. Resolution is priced by tier: 1K x1, 2K x1.5, 4K x2.25 (select with size, e.g. "2K" or "2816x1536"). Resolution selection requires the Vertex route.

Roleplay

No matching public benchmark is available for this model.

Not measured
Per request
$0.07

nano-banana-2

Google Nano Banana 2 (gemini-3.1-flash-image). Text-to-image and image editing on /v1/images/generations and /v1/images/edits, or inline in a chat response. Resolution is priced by tier: 1K x1, 2K x1.5, 4K x2.25 (select with size, e.g. "2K" or "2816x1536"). Resolution selection requires the Vertex route.

Roleplay

No matching public benchmark is available for this model.

Not measured
Per request
$0.07
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
gemini-3.1-pro-preview: 1,527.2
83 Models · 2026-10-25

Creative Writing v3
gemini-3.1-pro-preview: 1,491.2
145 Models · 2026-10-25

LiveBench · Story constraint following
gemini-3.1-pro-preview-high: 77.25
71 Models · 2026-10-25

LiveBench · Theory of mind
gemini-3.1-pro-preview-high: 80.77
71 Models · 2026-10-25

7.7/ 10
Input / 1M tokens
$1.5
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

LiveBench · Story constraint following (2025-12-23)
gemini-2.5-flash-lite-highthinking: 27.75
65 Models · 2026-10-25

LiveBench · Theory of mind (2025-12-23)
gemini-2.5-flash-lite-highthinking: 34.62
65 Models · 2026-10-25

2.8/ 10
Input / 1M tokens
$0.05

nano-banana

Google Nano Banana (gemini-2.5-flash-image). Text-to-image and image editing on /v1/images/generations and /v1/images/edits, or inline in a chat response. Single resolution: this model ignores size tiers upstream, so one flat per-image price.

Roleplay

No matching public benchmark is available for this model.

Not measured
Per request
$0.06
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

EQ-Bench 3
google/gemma-4-31B-it: 1,463.5
83 Models · 2026-10-25

Creative Writing v3
google/gemma-4-31B-it: 1,368.5
145 Models · 2026-10-25

6.7/ 10
Per request
$0.00
Roleplay

No matching public benchmark is available for this model.

Not measured
Input / 1M tokens
$0.125

gemini-3.8-flash

Multimodal Google model for fast agentic workflows, coding, and complex multi-step reasoning, with a 1M-token context window. Successor to Gemini 3.7 Flash.

Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

Creative Writing v3
gemini-3.8-flash: 1,744.5
145 Models · 2026-10-25

LiveBench · Story constraint following
gemini-3.8-flash-high: 82.75
71 Models · 2026-10-25

LiveBench · Theory of mind
gemini-3.8-flash-high: 76.92
71 Models · 2026-10-25

8.4/ 10
Input / 1M tokens
$0.375
Roleplay

No matching public benchmark is available for this model.

Not measured
Input / 1M tokens
$0.15
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

LiveBench · Story constraint following (2025-12-23)
gemini-3-flash-preview-high: 71.47
gemini-3-flash-preview-minimal: 30.7
65 Models · 2026-10-25

LiveBench · Theory of mind (2025-12-23)
gemini-3-flash-preview-high: 82.69
gemini-3-flash-preview-minimal: 51.92
65 Models · 2026-10-25

6.7/ 10
Input / 1M tokens
$0.375
Roleplay

No matching public benchmark is available for this model.

Not measured
Input / 1M tokens
$0.25
Roleplay

Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.

Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.

WritingBench · Literature & arts
gemini-2.5-pro: 80.92
54 Models · 2026-10-25

WritingBench · Character design
gemini-2.5-pro: 84
54 Models · 2026-10-25

WritingBench · Plot development
gemini-2.5-pro: 82.91
54 Models · 2026-10-25

WritingBench · Fan fiction
gemini-2.5-pro: 85.5
54 Models · 2026-10-25

9.5/ 10
Input / 1M tokens
$0.938