Skip to content

Listings

All listings: Google

Every listing for the models on page 5 of 10 of Google, including each model's other versions and routes. Back to Google

Sold by Google

35 listings on this page sold by Google.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Modelllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueYapEpoch Capabilities Index
Llama 3.3 70B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
vertex_ai/meta/llama-3.3-70b-instruct-maas ยท maas
108.1
From 278 benchmarks. Plenty of data behind it.
77ย ยฑ9
Coding IQ 77.1, 95% interval 68โ€“86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.72batch $0.36$0.72batch $0.36128K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measured
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Text Multilingual Embedding 002
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
108.1
From 46 benchmarks. Plenty of data behind it.
Not enough data yet$0.10โ€”2KNot enough data yetNot measuredNot measured
Mistral Large
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
vertex_ai/mistral-large@2407 ยท 2407
108.0
From 293 benchmarks. Plenty of data behind it.
72ย ยฑ9
Coding IQ 72.2, 95% interval 63โ€“81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$6.00128K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
vertex_ai/mistral-large@2411-001 ยท 2411-001
108.0
From 293 benchmarks. Plenty of data behind it.
72ย ยฑ9
Coding IQ 72.2, 95% interval 63โ€“81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$6.00128K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
vertex_ai/mistral-large-2411 ยท 2411
108.0
From 293 benchmarks. Plenty of data behind it.
72ย ยฑ9
Coding IQ 72.2, 95% interval 63โ€“81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$6.00128K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Large
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
vertex_ai/mistral-large@latest ยท latest
108.0
From 293 benchmarks. Plenty of data behind it.
72ย ยฑ9
Coding IQ 72.2, 95% interval 63โ€“81. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$2.00$6.00128K
22.0
Poor value (22.0). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
120
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Small
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
vertex_ai/mistral-small-2503@001 ยท 001+2503
107.8
From 316 benchmarks. Plenty of data behind it.
78ย ยฑ10
Coding IQ 78.4, 95% interval 68โ€“89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10$0.3032K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ยฑ9
Chatty (59 ยฑ9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Mistral Small
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
vertex_ai/mistral-small-2503 ยท 2503
107.8
From 316 benchmarks. Plenty of data behind it.
78ย ยฑ10
Coding IQ 78.4, 95% interval 68โ€“89. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.10$0.30128K
27.4
Poor value (27.4). Costs more per task than its benchmark results predict. Plenty of data behind it.
59 ยฑ9
Chatty (59 ยฑ9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.
Not measured
Llama 3.1 70B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionLlama 3.3 70B InstructWe compared release dates and version names in our catalogue.
vertex_ai/meta/llama-3.1-70b-instruct-maas ยท maas
106.8
From 168 benchmarks. Plenty of data behind it.
โ‰ˆ 80ย ยฑ11
Coding IQ 80.3, 95% interval 69โ€“91. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
โ€”โ€”128K
41.0
Poor value (41.0). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
gemini-1.5-flash-002
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
106.6
From 224 benchmarks. Plenty of data behind it.
โ‰ˆ 76ย ยฑ10
Coding IQ 75.7, 95% interval 66โ€“86. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.075>128k $0.15$0.30>128k $0.60Not published by the provider
30.7
Poor value (30.7). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measuredNot measured
Llama 4 Scout
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas ยท maas
106.3
From 347 benchmarks. Plenty of data behind it.
69ย ยฑ8
Coding IQ 69.3, 95% interval 61โ€“78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.25batch $0.125$0.70batch $0.3510M
30.3
Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
Not measured
127.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Gemini 1.5 Flash-8B
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gemini-flash-1.5-8b
106.1
From 50 benchmarks. Plenty of data behind it.
Not enough data yet$0.0375>128k $0.075cache read $0.01$0.15>128k $0.301MNot enough data yetNot measuredNot measured
Gemini 1.5 Flash-8B
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gemini-1.5-flash-8b-latest ยท latest
106.1
From 50 benchmarks. Plenty of data behind it.
Not enough data yet$0.0375>128k $0.075$0.15>128k $0.30Not published by the providerNot enough data yetNot measuredNot measured
Llama 3.2 90B Vision Instruct
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
vertex_ai/meta/llama-3.2-90b-vision-instruct-maas ยท maas
106.1
From 54 benchmarks. Plenty of data behind it.
Not enough data yetโ€”โ€”128K
57.0
Good value (57.0). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Text Embedding 005
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
105.9
From 26 benchmarks. Plenty of data behind it.
Not enough data yet$0.10โ€”2KNot enough data yetNot measuredNot measured
Jamba 1.5 Large
๐Ÿ‡ฎ๐Ÿ‡ฑ
Maker headquartered in IL, according to the company's own website. The citation is on the model page.
105.4
From 113 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$8.00256K
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Jamba 1.5 Large
๐Ÿ‡ฎ๐Ÿ‡ฑ
Maker headquartered in IL, according to the company's own website. The citation is on the model page.
vertex_ai/jamba-1.5-large@001 ยท 001
105.4
From 113 benchmarks. Plenty of data behind it.
Not enough data yet$2.00$8.00256K
27.7
Poor value (27.7). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yetโ€”โ€”66K
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Claude 3 Sonnet
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
103.7
From 286 benchmarks. Plenty of data behind it.
โ‰ˆ 76ย ยฑ10
Coding IQ 75.7, 95% interval 66โ€“86. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00200K
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
119.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Sonnet
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Sonnet 5.5We compared release dates and version names in our catalogue.
vertex_ai/claude-3-sonnet@20240229 ยท 20240229
103.7
From 286 benchmarks. Plenty of data behind it.
โ‰ˆ 76ย ยฑ10
Coding IQ 75.7, 95% interval 66โ€“86. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$3.00$15.00200K
38.2
Poor value (38.2). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
119.7
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
gemini-1.5-pro-001
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
103.7
From 165 benchmarks. Plenty of data behind it.
Not enough data yet$1.25>128k $2.50$5.00>128k $10.00Not published by the providerNot enough data yetNot measuredNot measured
Gemini Pro
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
103.6
From 45 benchmarks. A fair amount of data behind it.
Not enough data yet$0.125$0.37533KNot enough data yetNot measuredNot measured
Gemma 2 27B IT
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionGemma 3 27B ITWe compared release dates and version names in our catalogue.
103.6
From 120 benchmarks. Plenty of data behind it.
โ‰ˆ 76ย ยฑ10
Coding IQ 75.7, 95% interval 65โ€“86. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.65$0.65Not published by the providerNot enough data yetNot measuredNot measured
Claude 3 Haiku
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
102.7
From 315 benchmarks. Plenty of data behind it.
76ย ยฑ10
Coding IQ 75.9, 95% interval 66โ€“86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.25cache read $0.03$1.25cache write $0.30200K
33.4
Poor value (33.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
117.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Claude 3 Haiku
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionClaude Haiku 5.5We compared release dates and version names in our catalogue.
vertex_ai/claude-3-haiku@20240307 ยท 20240307
102.7
From 315 benchmarks. Plenty of data behind it.
76ย ยฑ10
Coding IQ 75.9, 95% interval 66โ€“86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.25$1.25200K
33.4
Poor value (33.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
117.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Imagen 4 Ultra
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
imagen-4.0-ultra-generate-001
โ‰ˆ 102
From 33 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetโ€”โ€”Not published by the providerNot enough data yetNot measuredNot measured
Veo 3.1 Fast
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
gemini/veo-3.1-fast-generate-001
โ‰ˆ 102
From 10 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetโ€”โ€”1KNot enough data yetNot measuredNot measured
gemini-1.5-flash-001
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 2.0 FlashWe compared the version names in our catalogue.
99.5
From 135 benchmarks. Plenty of data behind it.
Not enough data yet$0.075>128k $0.15$0.30>128k $0.60Not published by the provider
37.6
Poor value (37.6). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Jamba 1.5 Mini
๐Ÿ‡ฎ๐Ÿ‡ฑ
Maker headquartered in IL, according to the company's own website. The citation is on the model page.
98.6
From 113 benchmarks. Plenty of data behind it.
Not enough data yet$0.20$0.40256K
26.9
Poor value (26.9). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Jamba 1.5 Mini
๐Ÿ‡ฎ๐Ÿ‡ฑ
Maker headquartered in IL, according to the company's own website. The citation is on the model page.
vertex_ai/jamba-1.5-mini@001 ยท 001
98.6
From 113 benchmarks. Plenty of data behind it.
Not enough data yet$0.20$0.40256K
26.9
Poor value (26.9). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Mistral Nemo
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
vertex_ai/mistral-nemo@2407 ยท 2407
98.1
From 85 benchmarks. Plenty of data behind it.
Not enough data yet$3.00$3.00128K
52.2
Fair value (52.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
113.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Mistral Nemo
๐Ÿ‡ซ๐Ÿ‡ท
Maker headquartered in FR, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
vertex_ai/mistral-nemo@latest ยท latest
98.1
From 85 benchmarks. Plenty of data behind it.
Not enough data yet$0.15$0.15128K
52.2
Fair value (52.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
113.9
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.1 8B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
Newer version
Newer versionLlama-3.3-8B-InstructWe compared the version names in our catalogue.
vertex_ai/meta/llama-3.1-8b-instruct-maas ยท maas
95.6
From 343 benchmarks. Plenty of data behind it.
70ย ยฑ9
Coding IQ 69.9, 95% interval 61โ€“79. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
โ€”โ€”128K
39.5
Poor value (39.5). Costs more per task than its benchmark results predict. A fair amount of data behind it.
Not measuredNot measured
Llama 3 8B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionLlama-3.3-8B-InstructWe compared the version names in our catalogue.
vertex_ai/meta/llama3-8b-instruct-maas ยท maas
93.2
From 199 benchmarks. Plenty of data behind it.
โ‰ˆ 76ย ยฑ11
Coding IQ 75.7, 95% interval 65โ€“87. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
โ€”โ€”32K
46.4
Poor value (46.4). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measuredNot measured
Imagen 3
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionImagen 4We compared release dates and version names in our catalogue.
gemini/imagen-3.0-generate-001
โ‰ˆ 90
From 149 benchmarks. Little data behind it, so treat it as a rough estimate.
Not enough data yetโ€”โ€”Not published by the providerNot enough data yetNot measuredNot measured

Run by Google

22 listings on this page where Google runs the model. Another provider sells these listings.

Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
ModelProviderllminfo IQCoding IQInput $/1MOutput $/1MMax Input TokensValueEpoch Capabilities Index
Llama 3.3 70B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
ย OpenRouter
108.1
From 278 benchmarks. Plenty of data behind it.
77ย ยฑ9
Coding IQ 77.1, 95% interval 68โ€“86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.72$0.72128K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Llama 3.3 70B Instruct
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us-central1
ย OpenRouter
108.1
From 278 benchmarks. Plenty of data behind it.
77ย ยฑ9
Coding IQ 77.1, 95% interval 68โ€“86. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.72$0.72128K
31.6
Poor value (31.6). Costs more per task than its benchmark results predict. A fair amount of data behind it.
126.2
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Text Multilingual Embedding 002
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
ย Llmgateway
108.1
From 46 benchmarks. Plenty of data behind it.
Not enough data yet$0.025โ€”Not published by the providerNot enough data yetNot measured
Llama 4 Scout
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo.
us-east5
ย OpenRouter
106.3
From 347 benchmarks. Plenty of data behind it.
69ย ยฑ8
Coding IQ 69.3, 95% interval 61โ€“78. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.
$0.25$0.701.3M
30.3
Poor value (30.3). Costs more per task than its benchmark results predict. Plenty of data behind it.
127.8
Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API
Text Embedding 005
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
ย Llmgateway
105.9
From 26 benchmarks. Plenty of data behind it.
Not enough data yet$0.025โ€”Not published by the providerNot enough data yetNot measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
ย Eden AI
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30cache read $0.03$2.5033K
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
ย Llmgateway
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.50Not published by the provider
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
global
ย OpenRouter
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30cache read $0.03$2.5033K
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@europe-central2 ยท ๐Ÿ‡ต๐Ÿ‡ฑ europe-central2
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@europe-north1 ยท ๐Ÿ‡ซ๐Ÿ‡ฎ europe-north1
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@europe-southwest1 ยท ๐Ÿ‡ช๐Ÿ‡ธ europe-southwest1
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@europe-west1 ยท ๐Ÿ‡ง๐Ÿ‡ช europe-west1
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@europe-west4 ยท ๐Ÿ‡ณ๐Ÿ‡ฑ europe-west4
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@europe-west8 ยท ๐Ÿ‡ฎ๐Ÿ‡น europe-west8
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@us-central1 ยท ๐Ÿ‡บ๐Ÿ‡ธ us-central1
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@us-east1 ยท ๐Ÿ‡บ๐Ÿ‡ธ us-east1
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@us-east4 ยท ๐Ÿ‡บ๐Ÿ‡ธ us-east4
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@us-east5 ยท ๐Ÿ‡บ๐Ÿ‡ธ us-east5
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@us-south1 ยท ๐Ÿ‡บ๐Ÿ‡ธ us-south1
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@us-west1 ยท ๐Ÿ‡บ๐Ÿ‡ธ us-west1
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured
Gemini 2.5 Flash Image
๐Ÿ‡บ๐Ÿ‡ธ
Maker headquartered in US, according to the company's own website. The citation is on the model page.
Newer version
Newer versionGemini 3.1 Flash ImageWe compared the version names in our catalogue.
vertex/gemini-2.5-flash-image@us-west4 ยท ๐Ÿ‡บ๐Ÿ‡ธ us-west4
ย Requesty
105.2
From 184 benchmarks. A fair amount of data behind it.
Not enough data yet$0.30$2.501M
60.9
Good value (60.9). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate.
Not measured

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works