Skip to content

639 listings across 229 models

Page 3 of 10. The lists below split this page's listings into those sold by Google, run by Google, or sent to Google by a marketplace.

Sold by Google

29 listings on this page sold by Google.

Default order. 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
Gemma 4 26B A4Bmodels/gemma-4-26b-a4b-it
$0.06$0.33262K
Not enough data yet$0.30cache read $0.03$2.501MNot measuredNot measured
Grok 4.3
$1.25>200k $2.50cache read $0.20$2.50>200k $5.00200KNot measured
Claude Sonnet 3.7claude-3-7-sonnet
$3.00cache read $0.30$15.00cache write $3.75200K
Kimi K2 Thinkingvertex_ai/moonshotai/kimi-k2-thinking-maas · maas
$0.60cache read $0.06$2.50256K
Gemini 2.5 Computer Usemodels/gemini-2.5-computer-use-preview-10-2025
Not enough data yet$1.25>200k $2.50$10.00>200k $15.00128KNot enough data yetNot measuredNot measured
Not enough data yet$0.15batch $0.075—2KNot enough data yetNot measuredNot measured
Grok 4.1 Fastvertex_ai/xai/grok-4.1-fast-non-reasoning · non-reasoning
$0.20cache read $0.05$0.50128KNot measured
Claude Haiku 4.5
$1.00cache read $0.10batch $0.50$5.00cache write $1.25batch $2.50200K
DeepSeek R1vertex_ai/deepseek-ai/deepseek-r1-0528-maas · maas+0528 · 🇺🇸 us-central1
$1.35batch $0.675$5.40batch $2.7065K
Gemini 2.5 Flash
$0.30>200k $0.30cache read $0.03batch $0.15$2.50>200k $2.50batch $1.251M
Gemini 2.5 Flash Preview 05-20 (no think)gemini-2.5-flash-preview-05-20
Not enough data yet$0.15$0.60Not published by the providerNot measuredNot measured
Gemini Embedding 2gemini/gemini-embedding-2-preview
Not enough data yet$0.20batch $0.10—8KNot enough data yetNot measuredNot measured
Not enough data yet$0.15$0.60Not published by the providerNot enough data yetNot measuredNot measured
Qwen3 235B A22B Instruct 2507vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas · maas · 🇺🇸 global, us-south1
$0.22batch $0.11$0.88batch $0.44262KNot measured
Qwen3 Next 80B A3Bvertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas · maas+thinking · global
$0.15$1.20262KNot measuredNot measured
$0.15$0.60Not published by the providerNot measuredNot measured
Not enough data yet$2.00cache read $0.20batch $1.00$12.00batch $6.0066KNot enough data yetNot measuredNot measured
DeepSeek V3.1vertex_ai/deepseek-ai/deepseek-v3.1-maas · maas · 🇺🇸 us-central1
$0.60cache read $0.06batch $0.30$1.70batch $0.85164KNot measured
Not enough data yet$0.10cache read $0.01$0.401MNot measuredNot measured
Claude 3.5 Sonnet
$3.00cache read $0.30$15.00cache write $3.75200KNot measured
Qwen3 Codervertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas · maas · global
$0.22cache read $0.022batch $0.11$1.80batch $0.90262KNot measured
MiniMax M2vertex_ai/minimaxai/minimax-m2-maas · maas
$0.30cache read $0.03$1.20197KNot measuredNot measured
GPT OSS 120Bvertex_ai/openai/gpt-oss-120b-maas · maas
$0.09batch $0.045$0.36batch $0.18131K
Qwen3 Next 80B A3B Instructvertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas · maas · global
$0.15$1.20262KNot measuredNot measured
Show all 29 listings

Showing 25 of 29: one listing for each model.

Run by Google

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

Default order. 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
Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it
 Hugging Face$0.15$0.60262K
 LlmgatewayNot enough data yet$0.15—Not published by the providerNot enough data yetNot measuredNot measured
Claude Haiku 4.5
 Cortecs AI——200K
Gemini 2.5 Flash
 Cortecs AI——1M
 LlmgatewayNot enough data yet$0.20—Not published by the providerNot enough data yetNot measuredNot measured
 Eden AINot enough data yet$2.00cache read $0.20$12.0066KNot enough data yetNot measuredNot measured
GPT OSS 120B
 Hugging Face$0.09$0.36131K
Show all 36 listings

Showing 7 of 36: one listing for each model.

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

How this data works