AI for Less
50 sources reporting · latest verification 1 min ago

Providers

Compare models across different providers, sorted by Cost Index for a clear view of their relative cost. The index is calculated using the formula below.

Visibility filters: deprecated and retired included; snapshots hidden; runnable locally hidden; specialized models hidden; models without Cost Index hidden. Provider type: all. Price limit: all. Arena filter: all. Developers: all. Context: all; maximum output: all; image input: all; reasoning: all; tools: all. The reading and print tables include every model matching these filters, including rows behind “Show more” in the compact catalog.

Cost Index

Reference input price: $0.05; output price: $0.4 per 1M tokens. Selected workload: 2 input : 1 output. Cost Index = (model input price × 2 + model output price) / (reference input price × 2 + reference output price). Index ×1 corresponds to a weighted reference total of $0.5.

2 × +=$0.5= ×1

How do you use AI?

Real AI workloads can vary widely in their input-to-output ratio. Chat is relatively balanced, while RAG, agents, and long-context tasks often process far more input tokens than they generate. Because input and output are priced differently, the same model can rank very differently depending on the workload you choose.

AI Developers

Showing 253 of 1024 models

Anthropic AI Developer

Anthropic model prices — 20 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
claude-haiku-5-5×1.4$0.1 / $0.5 · Context 1,000,000×2.0 / ×1.3
claude-haiku-3-5 Retired Feb 19, 2026×11$0.8 / $4×16 / ×10
claude-haiku-4-5×14$1 / $5 · Context 200,000×20 / ×13
claude-sonnet-5×28$2 / $10 · Arena rank #58 · Context 1,000,000×40 / ×25
claude-sonnet-5-5×28$2 / $10 · Context 1,000,000×40 / ×25
claude-sonnet-4×42$3 / $15 · Context 200,000×60 / ×38
claude-sonnet-4-5 Deprecated · retires Nov 30, 2026×42$3 / $15 · Context 200,000×60 / ×38
claude-sonnet-4-6×42$3 / $15 · Arena rank #45 · Context 1,000,000×60 / ×38
claude-opus-5-5×56$4 / $20 · Context 1,000,000×80 / ×50
claude-opus-4-5×70$5 / $25 · Context 200,000×100 / ×63
claude-opus-4-6×70$5 / $25 · Arena rank #8 · Context 1,000,000×100 / ×63
claude-opus-4-7×70$5 / $25 · Arena rank #11 · Context 1,000,000×100 / ×63
claude-opus-4-8×70$5 / $25 · Arena rank #40 · Context 1,000,000×100 / ×63
claude-opus-5×70$5 / $25 · Context 1,000,000×100 / ×63
claude-fable-5×140$10 / $50 · Context 1,000,000×200 / ×125
claude-fable-5-1×140$10 / $50 · Context 1,000,000×200 / ×125
claude-mythos-5×140$10 / $50×200 / ×125
claude-mythos-5-1×140$10 / $50×200 / ×125
claude-opus-4×210$15 / $75 · Context 200,000×300 / ×188
claude-opus-4-1 Retired Aug 5, 2026×210$15 / $75 · Context 200,000×300 / ×188

OpenAI AI Developer

OpenAI model prices — 63 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
gpt-5-nano Deprecated · retires Dec 11, 2026×1.0$0.05 / $0.4 · Arena rank #236 · Context 400,000×1.0 / ×1.0
gpt-4.1-nano Deprecated · retires Oct 23, 2026×1.2$0.1 / $0.4 · Context 1,047,576×2.0 / ×1.0
gpt-6-luna×1.4$0.1 / $0.5 · Context 1,050,000×2.0 / ×1.3
gpt-4o-mini-search-preview Retired Jul 23, 2026×1.8$0.15 / $0.6 · Context 128,000×3.0 / ×1.5
gpt-4o-mini Deprecated · retires Jan 14, 2027×1.8$0.15 / $0.6 · Context 128,000×3.0 / ×1.5
babbage-002 Retired Sep 28, 2026×2.4$0.4 / $0.4×8.0 / ×1.0
gpt-5.6-luna×3.2$0.2 / $1.2 · Arena rank #75 · Context 1,050,000×4.0 / ×3.0
gpt-5.4-nano Deprecated · retires Apr 1, 2027×3.3$0.2 / $1.25 · Arena rank #161 · Context 400,000×4.0 / ×3.1
gpt-4.1-mini Deprecated · retires Jan 14, 2027×4.8$0.4 / $1.6 · Context 1,047,576×8.0 / ×4.0
gpt-3.5-turbo Deprecated · retires Oct 23, 2026×5.0$0.5 / $1.5 · Context 16,385×10 / ×3.8
gpt-3.5-turbo-0125 Deprecated · retires Oct 23, 2026×5.0$0.5 / $1.5 · Arena rank #335 · Context 16,385×10 / ×3.8
gpt-5-mini Deprecated · retires Dec 11, 2026×5.0$0.25 / $2 · Arena rank #177 · Context 400,000×5.0 / ×5.0
gpt-5.1-codex-mini Retired Jul 23, 2026×5.0$0.25 / $2 · Context 400,000×5.0 / ×5.0
gpt-3.5-turbo-1106 Retired Sep 28, 2026×8.0$1 / $2 · Arena rank #345 · Context 16,385×20 / ×5.0
gpt-3.5-turbo-instruct Retired Sep 28, 2026×10$1.5 / $2 · Context 16,385×30 / ×5.0
davinci-002 Retired Sep 28, 2026×12$2 / $2×40 / ×5.0
gpt-5.4-mini×12$0.75 / $4.5 · Arena rank #85 · Context 400,000×15 / ×11
o1-mini Retired Oct 27, 2025×13$1.1 / $4.4 · Arena rank #237 · Context 128,000×22 / ×11
o3-mini Deprecated · retires Oct 23, 2026×13$1.1 / $4.4 · Arena rank #220 · Context 200,000×22 / ×11
o4-mini Deprecated · retires Oct 23, 2026×13$1.1 / $4.4 · Context 200,000×22 / ×11
codex-mini-latest Retired Feb 12, 2026×18$1.5 / $6 · Context 200,000×30 / ×15
gpt-4.1 Deprecated · retires Jan 14, 2027×24$2 / $8 · Context 1,047,576×40 / ×20
o3 Deprecated · retires Dec 11, 2026×24$2 / $8 · Context 200,000×40 / ×20
o4-mini-deep-research Retired Jul 23, 2026×24$2 / $8 · Context 200,000×40 / ×20
gpt-5-codex Retired Jul 23, 2026×25$1.25 / $10 · Context 400,000×25 / ×25
gpt-5-search-api×25$1.25 / $10×25 / ×25
gpt-5.1-chat-latest Retired Jul 23, 2026×25$1.25 / $10 · Context 128,000×25 / ×25
gpt-5-chat-latest Retired Jul 23, 2026×25$1.25 / $10 · Context 128,000×25 / ×25
gpt-5 Deprecated · retires Dec 11, 2026×25$1.25 / $10 · Arena rank #106 · Context 400,000×25 / ×25
gpt-5.1 Deprecated · retires Apr 1, 2027×25$1.25 / $10 · Arena rank #99 · Context 400,000×25 / ×25
gpt-5.1-codex Retired Jul 23, 2026×25$1.25 / $10 · Context 400,000×25 / ×25
gpt-5.1-codex-max Retired Jul 23, 2026×25$1.25 / $10 · Context 400,000×25 / ×25
gpt-6.1-sol×28$2 / $10 · Context 1,050,000×40 / ×25
gpt-6-sol×28$2 / $10 · Context 1,050,000×40 / ×25
gpt-4o Deprecated · retires Jan 14, 2027×30$2.5 / $10 · Context 128,000×50 / ×25
gpt-4o-search-preview Retired Jul 23, 2026×30$2.5 / $10 · Context 128,000×50 / ×25
gpt-5.6-terra×32$2 / $12 · Arena rank #51 · Context 1,050,000×40 / ×30
gpt-5.2×35$1.75 / $14 · Arena rank #105 · Context 400,000×35 / ×35
gpt-5.2-chat-latest Retired Aug 10, 2026×35$1.75 / $14 · Context 128,000×35 / ×35
gpt-5.2-codex Retired Jul 23, 2026×35$1.75 / $14 · Context 400,000×35 / ×35
gpt-5.3-chat-latest Retired Aug 10, 2026×35$1.75 / $14 · Arena rank #78 · Context 128,000×35 / ×35
gpt-5.3-codex Deprecated · retires Apr 1, 2027×35$1.75 / $14 · Context 400,000×35 / ×35
computer-use-preview Retired Jul 23, 2026×36$3 / $12 · Context 8,192×60 / ×30
gpt-5.4×40$2.5 / $15 · Arena rank #55 · Context 1,050,000×50 / ×38
chatgpt-4o-latest Retired Feb 17, 2026×50$5 / $15 · Context 128,000×100 / ×38
gpt-5.6-sol×56$4 / $20 · Arena rank #21 · Context 1,050,000×80 / ×50
chat-latest×80$5 / $30 · Context 400,000×100 / ×75
gpt-5.5×80$5 / $30 · Arena rank #31 · Context 1,050,000×100 / ×75
gpt-4-turbo Deprecated · retires Oct 23, 2026×100$10 / $30 · Context 128,000×200 / ×75
gpt-4-turbo-preview Retired Mar 26, 2026×100$10 / $30 · Context 128,000×200 / ×75
o3-deep-research Retired Jul 23, 2026×120$10 / $40 · Context 200,000×200 / ×100
gpt-6-astra×140$10 / $50 · Context 1,050,000×200 / ×125
o1 Deprecated · retires Oct 23, 2026×180$15 / $60 · Context 200,000×300 / ×150
o1-preview Retired Jul 28, 2025×180$15 / $60 · Arena rank #178 · Context 128,000×300 / ×150
gpt-4 Deprecated · retires Oct 23, 2026×240$30 / $60 · Context 8,192×600 / ×150
gpt-4-0613 Deprecated · retires Oct 23, 2026×240$30 / $60 · Arena rank #307 · Context 8,192×600 / ×150
o3-pro Deprecated · retires Dec 11, 2026×240$20 / $80 · Context 200,000×400 / ×200
gpt-5-pro Deprecated · retires Dec 11, 2026×300$15 / $120 · Context 400,000×300 / ×300
gpt-5.2-pro×420$21 / $168 · Context 400,000×420 / ×420
gpt-5.4-pro×480$30 / $180 · Context 1,050,000×600 / ×450
gpt-5.5-pro×480$30 / $180 · Context 1,050,000×600 / ×450
gpt-4.5-preview Retired Jul 14, 2025×600$75 / $150 · Context 128,000×1500 / ×375
o1-pro Deprecated · retires Oct 23, 2026×1800$150 / $600 · Context 200,000×3000 / ×1500

Google AI Developer

Google model prices — 14 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
gemini-2.5-flash-lite×1.2$0.1 / $0.4 · Context 1,048,576×2.0 / ×1.0
gemini-3.1-flash-lite×4.0$0.25 / $1.5 · Context 1,048,576×5.0 / ×3.8
gemini-2.5-flash×6.2$0.3 / $2.5 · Arena rank #151 · Context 1,048,576×6.0 / ×6.3
gemini-3.5-flash-lite×6.2$0.3 / $2.5 · Arena rank #72 · Context 1,048,576×6.0 / ×6.3
gemini-3-flash-preview×8.0$0.5 / $3 · Context 1,048,576×10 / ×7.5
gemini-3.6-flash×11$0.75 / $3.75 · Arena rank #23 · Context 1,048,576×15 / ×9.4
gemini-3.7-flash×11$0.75 / $3.75 · Context 1,048,576×15 / ×9.4
gemini-3.8-flash×11$0.75 / $3.75 · Context 1,048,576×15 / ×9.4
gemini-robotics-er-2-preview×14$1 / $5 · Context 131,072×20 / ×13
gemini-3.5-flash×24$1.5 / $9 · Arena rank #33 · Context 1,048,576×30 / ×23
gemini-2.5-pro×25$1.25 / $10 · Arena rank #87 · Context 1,048,576×25 / ×25
gemini-4-argon×28$2 / $10 · Context 1,048,576×40 / ×25
gemini-3.1-pro-preview×32$2 / $12 · Arena rank #19 · Context 1,048,576×40 / ×30
gemini-3.1-pro-preview-customtools×32$2 / $12 · Context 1,048,576×40 / ×30

Z.AI AI Developer

Z.AI model prices — 1 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
glm-5.3-flashx×4.0$0.37 / $1.25 · Context 1,048,576×7.4 / ×3.1

Alibaba / Qwen AI Developer

Alibaba / Qwen model prices — 21 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
qwen3.7-flash×0.4$0.03 / $0.13 · Context 1,000,000×0.6 / ×0.3
qwen-turbo×0.6$0.05 / $0.2×1.0 / ×0.5
qwen-flash×1.0$0.05 / $0.4 · Context 1,000,000×1.0 / ×1.0
qwen3.5-flash×1.2$0.1 / $0.4 · Arena rank #166 · Context 1,000,000×2.0 / ×1.0
qwen3.8-flash×1.5$0.15 / $0.47 · Context 1,000,000×3.0 / ×1.2
qwen-plus-latest×4.0$0.4 / $1.2 · Context 1,000,000×8.0 / ×3.0
qwen-plus×4.0$0.4 / $1.2 · Context 1,000,000×8.0 / ×3.0
qwen3.6-flash×4.0$0.25 / $1.5 · Context 1,000,000×5.0 / ×3.8
qwen3-coder-flash×4.2$0.3 / $1.5 · Context 1,000,000×6.0 / ×3.8
qwen3.7-plus×4.8$0.4 / $1.6 · Arena rank #69 · Context 1,000,000×8.0 / ×4.0
qwen3.5-plus×6.4$0.4 / $2.4 · Context 1,000,000×8.0 / ×6.0
qwen3.6-plus×8.0$0.5 / $3 · Arena rank #90 · Context 1,000,000×10 / ×7.5
qwq-plus×8.0$0.8 / $2.4×16 / ×6.0
qwen3-coder-plus×14$1 / $5 · Context 1,000,000×20 / ×13
qwen3-max×17$1.2 / $6 · Context 262,144×24 / ×15
qwen3-max-preview×17$1.2 / $6 · Arena rank #107×24 / ×15
qwen3.8-max×20$2 / $6 · Arena rank #24 · Context 1,000,000×40 / ×15
qwen3.8-max-0902×20$2 / $6 · Context 1,000,000×40 / ×15
qwen3.6-max-preview×21$1.3 / $7.8 · Arena rank #60 · Context 262,144×26 / ×20
qwen3.7-max×25$2.5 / $7.5 · Context 1,000,000×50 / ×19
qwen3.7-max-preview×25$2.5 / $7.5 · Arena rank #39 · Context 1,000,000×50 / ×19

Xiaomi MiMo AI Developer

Xiaomi MiMo model prices — 1 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
mimo-v2.6-pro-ultraspeed×35$4.35 / $8.7 · Context 1,000,000×87 / ×22

Mistral AI AI Developer

Mistral AI model prices — 6 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
voxtral-small-2507×1.2$0.1 / $0.4 · Context 32,768×2.0 / ×1.0
magistral-small-latest×1.8$0.15 / $0.6 · Context 262,144×3.0 / ×1.5
codestral-2508×3.0$0.3 / $0.9 · Context 256,000×6.0 / ×2.3
mistral-large-2512×5.0$0.5 / $1.5 · Context 262,144×10 / ×3.8
mistral-large-4×6.9$0.68 / $2.09 · Arena rank #111 · Context 1,048,576×14 / ×5.2
magistral-medium-latest×21$1.5 / $7.5 · Arena rank #117 · Context 262,144×30 / ×19

xAI AI Developer

xAI model prices — 8 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
grok-build-0.1×8.0$1 / $2 · Context 256,000×20 / ×5.0
grok-4.20-0309-non-reasoning×10$1.25 / $2.5 · Context 1,000,000×25 / ×6.3
grok-4.20-0309-reasoning×10$1.25 / $2.5 · Context 1,000,000×25 / ×6.3
grok-4.20-multi-agent-0309×10$1.25 / $2.5 · Context 1,000,000×25 / ×6.3
grok-4.3×10$1.25 / $2.5 · Arena rank #93 · Context 1,000,000×25 / ×6.3
grok-4.5×20$2 / $6 · Arena rank #52 · Context 500,000×40 / ×15
grok-4.6×20$2 / $6 · Arena rank #73 · Context 500,000×40 / ×15
grok-4.7×20$2 / $6 · Context 500,000×40 / ×15

DeepSeek AI Developer

DeepSeek model prices — 1 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
deepseek-flash≈×3.6Off-peak Input 0.15 · Output 0.6 / 1M tokensPeak Input 0.3 · Output 1.2 / 1M tokensApprox. current: Peak · Chinese public holidays ignored. · Context 1,048,576Approx. Peak · ×6.0 / ×3.0

Cohere AI Developer

Cohere model prices — 5 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
command-r7b-12-2024×0.5$0.0375 / $0.15 · Context 128,000×0.8 / ×0.4
command-r-08-2024×1.8$0.15 / $0.6 · Arena rank #322 · Context 128,000×3.0 / ×1.5
c4ai-aya-expanse-32b×5.0$0.5 / $1.5 · Arena rank #312 · Context 128,000×10 / ×3.8
command-r-plus-08-2024×30$2.5 / $10 · Arena rank #306 · Context 128,000×50 / ×25
command-a-03-2025×30$2.5 / $10 · Arena rank #212 · Context 256,000×50 / ×25

Meta AI Developer

Meta model prices — 1 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
muse-spark-1.2×14$1.25 / $4.25 · Context 1,048,576×25 / ×11

OpenRouter Aggregator

OpenRouter model prices — 145 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
cohere/north-mini-code:free×0.0Free · Context 256,000×0.0 / ×0.0
stealth/space-bunny-alpha×0.0Free · Context 1,000,000×0.0 / ×0.0
inclusionai/ling-3.0-flash×0.2$0.021 / $0.063 · Context 262,144×0.4 / ×0.2
qwen/qwen3.7-flash×0.4$0.03 / $0.13 · Context 1,000,000×0.6 / ×0.3
inclusionai/ling-3.0-flash-fin×0.4$0.042 / $0.1232 · Context 262,144×0.8 / ×0.3
amazon/nova-micro-v1×0.4$0.035 / $0.14 · Context 128,000×0.7 / ×0.4
cohere/command-r7b-12-2024×0.5$0.0375 / $0.15 · Context 128,000×0.8 / ×0.4
amazon/nova-lite-v1×0.7$0.06 / $0.24 · Context 300,000×1.2 / ×0.6
qwen/qwen3.5-flash-02-23×0.8$0.065 / $0.26 · Context 1,000,000×1.3 / ×0.7
bytedance/ui-tars-1.5-7b×0.8$0.1 / $0.2 · Context 128,000×2.0 / ×0.5
meta/muse-spark-1.2-contributor×0.8$0.1 / $0.2 · Context 1,048,576×2.0 / ×0.5
meta/muse-spark-1.3-contributor×0.8$0.1 / $0.2 · Context 1,048,576×2.0 / ×0.5
openai/gpt-5-nano Deprecated · retires Dec 11, 2026 · at developer×1.0$0.05 / $0.4 · Arena rank #236 · Context 400,000×1.0 / ×1.0
google/gemini-2.5-flash-lite×1.2$0.1 / $0.4 · Context 1,048,576×2.0 / ×1.0
openai/gpt-4.1-nano Deprecated · retires Oct 23, 2026 · at developer×1.2$0.1 / $0.4 · Context 1,047,576×2.0 / ×1.0
nvidia/nemotron-3.5-content-safety×1.2$0.2 / $0.2 · Context 131,072×4.0 / ×0.5
anthropic/claude-haiku-5.5×1.4$0.1 / $0.5 · Context 1,000,000×2.0 / ×1.3
openai/gpt-6-luna×1.4$0.1 / $0.5 · Context 1,050,000×2.0 / ×1.3
qwen/qwen3.8-flash×1.5$0.15 / $0.47 · Context 1,000,000×3.0 / ×1.2
qwen/qwen3.8-omni-flash×1.5$0.15 / $0.47 · Context 1,000,000×3.0 / ×1.2
openai/gpt-5.6-luna-pro:batch×1.6$0.1 / $0.6 · Arena rank #75 · Context 1,050,000×2.0 / ×1.5
cohere/command-r-08-2024×1.8$0.15 / $0.6 · Arena rank #322 · Context 128,000×3.0 / ×1.5
openai/gpt-4o-mini Deprecated · retires Jan 14, 2027 · at developer×1.8$0.15 / $0.6 · Context 128,000×3.0 / ×1.5
mistralai/mistral-small-2603×1.8$0.15 / $0.6 · Context 262,144×3.0 / ×1.5
mistralai/mistral-saba×2.0$0.2 / $0.6 · Context 32,768×4.0 / ×1.5
qwen/qwen-plus×2.6$0.26 / $0.78 · Context 1,000,000×5.2 / ×2.0
qwen/qwen3-coder-flash×2.7$0.195 / $0.975 · Context 1,000,000×3.9 / ×2.4
mistralai/codestral-2508×3.0$0.3 / $0.9 · Context 256,000×6.0 / ×2.3
minimax/minimax-01×3.0$0.2 / $1.1 · Context 1,000,192×4.0 / ×2.8
qwen/qwen3.6-flash×3.0$0.1875 / $1.125 · Context 1,000,000×3.8 / ×2.8
deepseek/deepseek-chat×3.1$0.32 / $0.89 · Context 163,840×6.4 / ×2.2
openai/gpt-5.4-nano Deprecated · retires Apr 1, 2027 · at developer×3.3$0.2 / $1.25 · Arena rank #161 · Context 400,000×4.0 / ×3.1
deepseek/deepseek-v4.1-flash-1017×3.6$0.3 / $1.2 · Context 1,048,576×6.0 / ×3.0
minimax/minimax-m2-her×3.6$0.3 / $1.2 · Context 65,536×6.0 / ×3.0
microsoft/wizardlm-2-8x22b×3.7$0.62 / $0.62 · Context 65,535×12 / ×1.6
qwen/qwen3.7-plus×3.8$0.32 / $1.28 · Arena rank #69 · Context 1,000,000×6.4 / ×3.2
z-ai/glm-5.3-flashx×4.0$0.37 / $1.25 · Context 1,048,576×7.4 / ×3.1
google/gemini-3.1-flash-lite×4.0$0.25 / $1.5 · Context 1,048,576×5.0 / ×3.8
google/gemini-3.1-flash-lite-preview×4.0$0.25 / $1.5 · Arena rank #110 · Context 1,048,576×5.0 / ×3.8
qwen/qwen3.5-plus-02-15×4.2$0.26 / $1.56 · Context 1,000,000×5.2 / ×3.9
cohere/command-a-plus×4.2$0.3 / $1.5 · Context 192,000×6.0 / ×3.8
openai/gpt-4.1-mini Deprecated · retires Jan 14, 2027 · at developer×4.8$0.4 / $1.6 · Context 1,047,576×8.0 / ×4.0
openai/gpt-3.5-turbo Deprecated · retires Oct 23, 2026 · at developer×5.0$0.5 / $1.5 · Context 16,385×10 / ×3.8
mistralai/mistral-large-2512×5.0$0.5 / $1.5 · Context 262,144×10 / ×3.8
openai/gpt-5-mini Deprecated · retires Dec 11, 2026 · at developer×5.0$0.25 / $2 · Arena rank #177 · Context 400,000×5.0 / ×5.0
openai/gpt-5.1-codex-mini Retired Jul 23, 2026 · at developer×5.0$0.25 / $2 · Context 400,000×5.0 / ×5.0
sao10k/l3.1-euryale-70b×5.1$0.85 / $0.85 · Context 131,072×17 / ×2.1
qwen/qwen3.6-plus×5.2$0.325 / $1.95 · Arena rank #90 · Context 1,000,000×6.5 / ×4.9
mistralai/mistral-medium-3×5.6$0.4 / $2 · Context 131,072×8.0 / ×5.0
mistralai/mistral-medium-3.1×5.6$0.4 / $2 · Context 131,072×8.0 / ×5.0
amazon/nova-2-lite-v1×6.2$0.3 / $2.5 · Arena rank #243 · Context 1,000,000×6.0 / ×6.3
google/gemini-2.5-flash×6.2$0.3 / $2.5 · Arena rank #151 · Context 1,048,576×6.0 / ×6.3
google/gemini-3.5-flash-lite×6.2$0.3 / $2.5 · Arena rank #72 · Context 1,048,576×6.0 / ×6.3
minimax/minimax-m1×6.6$0.55 / $2.2 · Arena rank #202 · Context 1,000,000×11 / ×5.5
mistralai/mistral-large-4-0×6.9$0.68 / $2.09 · Arena rank #111 · Context 1,048,576×14 / ×5.2
google/gemini-3-flash-preview×8.0$0.5 / $3 · Context 1,048,576×10 / ×7.5
openai/gpt-3.5-turbo-0613 Retired Sep 13, 2024 · at developer×8.0$1 / $2 · Context 4,095×20 / ×5.0
x-ai/grok-build-0.1×8.0$1 / $2 · Context 256,000×20 / ×5.0
qwen/qwen3-coder-plus×9.1$0.65 / $3.25 · Context 1,000,000×13 / ×8.1
amazon/nova-pro-v1×9.6$0.8 / $3.2 · Context 300,000×16 / ×8.0
x-ai/grok-4.20×10$1.25 / $2.5 · Context 1,000,000×25 / ×6.3
x-ai/grok-4.20-multi-agent×10$1.25 / $2.5 · Context 1,000,000×25 / ×6.3
openai/gpt-3.5-turbo-instruct Retired Sep 28, 2026 · at developer×10$1.5 / $2 · Context 16,385×30 / ×5.0
x-ai/grok-4.3×10$1.25 / $2.5 · Arena rank #93 · Context 1,000,000×25 / ×6.3
google/gemini-3.6-flash×11$0.75 / $3.75 · Arena rank #23 · Context 1,048,576×15 / ×9.4
google/gemini-3.7-flash×11$0.75 / $3.75 · Context 1,048,576×15 / ×9.4
qwen/qwen3-max×11$0.78 / $3.9 · Context 262,144×16 / ×9.8
qwen/qwen3-max-thinking×11$0.78 / $3.9 · Context 262,144×16 / ×9.8
google/gemini-3.8-flash×12$0.825 / $4.125 · Context 1,048,576×17 / ×10
openai/gpt-5.4-mini×12$0.75 / $4.5 · Arena rank #85 · Context 400,000×15 / ×11
z-ai/glm-5-turbo×13$1.2 / $4 · Context 202,752×24 / ×10
z-ai/glm-5v-turbo×13$1.2 / $4 · Arena rank #109 · Context 202,752×24 / ×10
openai/o3-mini Deprecated · retires Oct 23, 2026 · at developer×13$1.1 / $4.4 · Arena rank #220 · Context 200,000×22 / ×11
openai/o4-mini Deprecated · retires Oct 23, 2026 · at developer×13$1.1 / $4.4 · Context 200,000×22 / ×11
meta/muse-spark-1.1×14$1.25 / $4.25 · Arena rank #13 · Context 1,048,576×25 / ×11
meta/muse-spark-1.2×14$1.25 / $4.25 · Context 1,048,576×25 / ×11
meta/muse-spark-1.3×14$1.25 / $4.25 · Context 1,048,576×25 / ×11
meta/muse-spark-open×14$1.25 / $4.25 · Context 1,048,576×25 / ×11
anthropic/claude-haiku-4.5×14$1 / $5 · Context 200,000×20 / ×13
openai/gpt-5.6-sol-pro:batch×14$1 / $5 · Arena rank #21 · Context 1,050,000×20 / ×13
writer/palmyra-x5×14$0.6 / $6 · Context 1,040,000×12 / ×15
qwen/qwen3.7-max×15$1.475 / $4.425 · Context 1,000,000×30 / ×11
openai/gpt-5.6-terra-pro:batch×16$1 / $6 · Arena rank #51 · Context 1,050,000×20 / ×15
qwen/qwen3.6-max-preview×16$1.027 / $6.162 · Arena rank #60 · Context 262,144×21 / ×15
openai/gpt-3.5-turbo-16k Retired Sep 13, 2024 · at developer×20$3 / $4 · Context 16,385×60 / ×10
x-ai/grok-4.5×20$2 / $6 · Arena rank #52 · Context 500,000×40 / ×15
x-ai/grok-4.6×20$2 / $6 · Arena rank #73 · Context 500,000×40 / ×15
x-ai/grok-4.7×20$2 / $6 · Context 500,000×40 / ×15
mistralai/mistral-large×20$2 / $6 · Context 128,000×40 / ×15
mistralai/mistral-large-2407×20$2 / $6 · Arena rank #269 · Context 131,072×40 / ×15
qwen/qwen3.8-max-0902×20$2 / $6 · Context 1,000,000×40 / ×15
mistralai/mistral-medium-3-5×21$1.5 / $7.5 · Arena rank #117 · Context 262,144×30 / ×19
google/gemini-3.5-flash×24$1.5 / $9 · Arena rank #33 · Context 1,048,576×30 / ×23
openai/gpt-4.1 Deprecated · retires Jan 14, 2027 · at developer×24$2 / $8 · Context 1,047,576×40 / ×20
openai/o3 Deprecated · retires Dec 11, 2026 · at developer×24$2 / $8 · Context 200,000×40 / ×20
google/gemini-2.5-pro×25$1.25 / $10 · Arena rank #87 · Context 1,048,576×25 / ×25
google/gemini-2.5-pro-preview×25$1.25 / $10 · Context 1,048,576×25 / ×25
openai/gpt-5 Deprecated · retires Dec 11, 2026 · at developer×25$1.25 / $10 · Arena rank #106 · Context 400,000×25 / ×25
openai/gpt-5.1 Deprecated · retires Apr 1, 2027 · at developer×25$1.25 / $10 · Arena rank #99 · Context 400,000×25 / ×25
openai/gpt-5.1-codex Retired Jul 23, 2026 · at developer×25$1.25 / $10 · Context 400,000×25 / ×25
openai/gpt-5.1-codex-max Retired Jul 23, 2026 · at developer×25$1.25 / $10 · Context 400,000×25 / ×25
anthropic/claude-sonnet-5×28$2 / $10 · Arena rank #58 · Context 1,000,000×40 / ×25
anthropic/claude-sonnet-5.5×28$2 / $10 · Context 1,000,000×40 / ×25
google/gemini-4-argon×28$2 / $10 · Context 1,048,576×40 / ×25
openai/gpt-6.1-sol×28$2 / $10 · Context 1,050,000×40 / ×25
openai/gpt-6-sol×28$2 / $10 · Context 1,050,000×40 / ×25
z-ai/glm-5.3-prime×29$2.8 / $8.8 · Context 1,000,000×56 / ×22
cohere/command-a×30$2.5 / $10 · Context 256,000×50 / ×25
cohere/command-r-plus-08-2024×30$2.5 / $10 · Arena rank #306 · Context 128,000×50 / ×25
openai/gpt-4o Deprecated · retires Jan 14, 2027 · at developer×30$2.5 / $10 · Context 128,000×50 / ×25
google/gemini-3.1-pro-preview×32$2 / $12 · Arena rank #19 · Context 1,048,576×40 / ×30
google/gemini-3.1-pro-preview-customtools×32$2 / $12 · Context 1,048,576×40 / ×30
xiaomi/mimo-v2.6-pro-ultraspeed×35$4.35 / $8.7 · Context 1,000,000×87 / ×22
amazon/nova-premier-v1×35$2.5 / $12.5 · Context 1,000,000×50 / ×31
openai/gpt-5.2×35$1.75 / $14 · Arena rank #105 · Context 400,000×35 / ×35
openai/gpt-5.2-codex Retired Jul 23, 2026 · at developer×35$1.75 / $14 · Context 400,000×35 / ×35
openai/gpt-5.2-chat×35$1.75 / $14 · Context 128,000×35 / ×35
openai/gpt-5.3-codex Deprecated · retires Apr 1, 2027 · at developer×35$1.75 / $14 · Context 400,000×35 / ×35
openai/gpt-5.4×40$2.5 / $15 · Arena rank #55 · Context 1,050,000×50 / ×38
qwen/qwen3.8-max-prime×40$4 / $12 · Context 1,000,000×80 / ×30
anthropic/claude-sonnet-4×42$3 / $15 · Context 200,000×60 / ×38
anthropic/claude-sonnet-4.5 Deprecated · retires Nov 30, 2026 · at developer×42$3 / $15 · Context 200,000×60 / ×38
anthropic/claude-sonnet-4.6×42$3 / $15 · Arena rank #45 · Context 1,000,000×60 / ×38
anthropic/claude-opus-5.5×56$4 / $20 · Context 1,000,000×80 / ×50
meta/muse-wonder×56$4 / $20 · Context 1,048,576×80 / ×50
anthropic/claude-opus-4.5×70$5 / $25 · Context 200,000×100 / ×63
anthropic/claude-opus-4.6×70$5 / $25 · Arena rank #8 · Context 1,000,000×100 / ×63
anthropic/claude-opus-4.7×70$5 / $25 · Arena rank #11 · Context 1,000,000×100 / ×63
anthropic/claude-opus-4.8×70$5 / $25 · Arena rank #40 · Context 1,000,000×100 / ×63
anthropic/claude-opus-5×70$5 / $25 · Context 1,000,000×100 / ×63
openai/gpt-chat-latest×80$5 / $30 · Context 400,000×100 / ×75
openai/gpt-5.5×80$5 / $30 · Arena rank #31 · Context 1,050,000×100 / ×75
openai/gpt-4-turbo Deprecated · retires Oct 23, 2026 · at developer×100$10 / $30 · Context 128,000×200 / ×75
anthropic/claude-fable-5×140$10 / $50 · Context 1,000,000×200 / ×125
anthropic/claude-fable-5.1×140$10 / $50 · Context 1,000,000×200 / ×125
openai/gpt-6-astra×140$10 / $50 · Context 1,050,000×200 / ×125
openai/o1 Deprecated · retires Oct 23, 2026 · at developer×180$15 / $60 · Context 200,000×300 / ×150
anthropic/claude-opus-4.1 Retired Aug 5, 2026 · at developer×210$15 / $75 · Context 200,000×300 / ×188
openai/gpt-4 Deprecated · retires Oct 23, 2026 · at developer×240$30 / $60 · Context 8,192×600 / ×150
openai/o3-pro Deprecated · retires Dec 11, 2026 · at developer×240$20 / $80 · Context 200,000×400 / ×200
openai/gpt-5-pro Deprecated · retires Dec 11, 2026 · at developer×300$15 / $120 · Context 400,000×300 / ×300
openai/gpt-5.2-pro×420$21 / $168 · Context 400,000×420 / ×420
openai/gpt-5.4-pro×480$30 / $180 · Context 1,050,000×600 / ×450
openai/gpt-5.5-pro×480$30 / $180 · Context 1,050,000×600 / ×450
openai/o1-pro Deprecated · retires Oct 23, 2026 · at developer×1800$150 / $600 · Context 200,000×3000 / ×1500

DeepInfra Aggregator

DeepInfra model prices — 22 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo×0.2$0.02 / $0.04 · Context 128,000×0.4 / ×0.1
google/gemma-4-31B-it-turbo×1.0$0.09 / $0.34 · Context 256,000×1.8 / ×0.9
meta-llama/Llama-3.3-70B-Instruct-Turbo×1.0$0.1 / $0.32 · Context 128,000×2.0 / ×0.8
nvidia/Nemotron-Content-Safety-3.5×1.2$0.2 / $0.2 · Context 128,000×4.0 / ×0.5
nvidia/NVIDIA-Nemotron-3.5-Super-VL×1.2$0.1 / $0.4 · Context 256,000×2.0 / ×1.0
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo×2.4$0.4 / $0.4 · Context 128,000×8.0 / ×1.0
google/gemma-4-31B-it-Ultra×2.6$0.27 / $0.76 · Context 128,000×5.4 / ×1.9
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo×3.2$0.3 / $1 · Context 256,000×6.0 / ×2.5
google/gemini-3.1-flash-lite×4.0$0.25 / $1.5 · Context 1,048,576×5.0 / ×3.8
google/gemini-2.5-flash×6.2$0.3 / $2.5 · Arena rank #151 · Context 1,048,576×6.0 / ×6.3
anthropic/claude-haiku-4-5×14$1 / $5 · Context 200,000×20 / ×13
Qwen/Qwen3.8-Max×17$1.65 / $4.951 · Arena rank #24 · Context 1,000,000×33 / ×12
google/gemini-3.5-flash×24$1.5 / $9 · Arena rank #33 · Context 1,048,576×30 / ×23
google/gemini-2.5-pro×25$1.25 / $10 · Arena rank #87 · Context 1,048,576×25 / ×25
Qwen/Qwen3.7-Max×25$2.5 / $7.5 · Context 1,000,000×50 / ×19
google/gemini-3.1-pro×32$2 / $12 · Context 976,000×40 / ×30
anthropic/claude-sonnet-4-6×42$3 / $15 · Arena rank #45 · Context 1,000,000×60 / ×38
anthropic/claude-sonnet-5×42$3 / $15 · Arena rank #58 · Context 1,000,000×60 / ×38
anthropic/claude-opus-4-7×70$5 / $25 · Arena rank #11 · Context 1,000,000×100 / ×63
anthropic/claude-opus-4-8×70$5 / $25 · Arena rank #40 · Context 1,000,000×100 / ×63
anthropic/claude-opus-5×70$5 / $25 · Context 1,000,000×100 / ×63
anthropic/claude-fable-5×140$10 / $50 · Context 1,000,000×200 / ×125

Novita AI Aggregator

Novita AI model prices — 16 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
inclusionai/ling-3.0-flash×0.6$0.06 / $0.18 · Context 262,144×1.2 / ×0.5
inclusionai/ling-3.0-flash-sante×0.7$0.075 / $0.22 · Context 262,144×1.5 / ×0.6
inclusionai/ling-3.0-flash-fin×0.7$0.075 / $0.22 · Context 262,144×1.5 / ×0.6
inclusionai/ling-3.0-flash-vl×0.7$0.075 / $0.22 · Context 131,072×1.5 / ×0.6
baidu/ernie-4.5-21B-a3b×0.8$0.07 / $0.28 · Context 120,000×1.4 / ×0.7
qwen/qwen3.8-flash×1.5$0.15 / $0.47 · Context 1,000,000×3.0 / ×1.2
qwen/qwen-mt-plus×2.5$0.25 / $0.75 · Context 16,384×5.0 / ×1.9
inclusionai/ling-3.1-flash×3.0$0.3 / $0.9 · Context 262,144×6.0 / ×2.3
baidu/cobuddy×3.4$0.28 / $1.13 · Context 131,072×5.6 / ×2.8
deepseek/deepseek-v4.1-flash-1017×3.6$0.3 / $1.2 · Context 1,048,576×6.0 / ×3.0
microsoft/wizardlm-2-8x22b×3.7$0.62 / $0.62 · Context 65,535×12 / ×1.6
minimax/minimax-m2.5-highspeed×7.2$0.6 / $2.4 · Context 204,800×12 / ×6.0
deepseek/deepseek-r1-turbo×7.8$0.7 / $2.5 · Context 64,000×14 / ×6.3
qwen/qwen3-max×10$0.845 / $3.38 · Context 262,144×17 / ×8.5
qwen/qwen3.7-max×13$1.25 / $3.75 · Context 1,000,000×25 / ×9.4
qwen/qwen3.8-max×20$2 / $6 · Arena rank #24 · Context 1,000,000×40 / ×15

Hugging Face Inference Providers Aggregator

Hugging Face Inference Providers model prices — 6 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
inclusionAI/Ling-3.0-flash×0.6$0.06 / $0.18 · Context 262,144×1.2 / ×0.5
inclusionAI/Ling-3.0-flash-Fin×0.6$0.06 / $0.18 · Context 262,144×1.2 / ×0.5
inclusionAI/Ling-3.0-flash-VL×0.6$0.06 / $0.18 · Context 131,072×1.2 / ×0.5
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4×1.8$0.2 / $0.5 · Arena rank #138 · Context 1,048,576×4.0 / ×1.3
inclusionAI/Ling-3.1-flash×3.0$0.3 / $0.9 · Context 262,144×6.0 / ×2.3
meta-models/Muse-Spark-Open-816B-A42B×14$1.25 / $4.25 · Context 1,048,576×25 / ×11

Together AI Aggregator

Together AI model prices — 7 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
Qwen/Qwen3.8-Flash×1.5$0.15 / $0.47 · Context 1,000,000×3.0 / ×1.2
nvidia/NVIDIA-Nemotron-3.5-Super-VL×1.6$0.15 / $0.5 · Context 256,000×3.0 / ×1.3
Qwen/Qwen3.7-Plus×3.8$0.32 / $1.28 · Arena rank #69 · Context 1,000,000×6.4 / ×3.2
meta-llama/Llama-3.3-70B-Instruct-Turbo×6.2$1.04 / $1.04 · Context 128,000×21 / ×2.6
Qwen/Qwen3.6-Plus×8.0$0.5 / $3 · Arena rank #90 · Context 1,000,000×10 / ×7.5
meta-models/Muse-Spark-Open-816B-A42B×14$1.25 / $4.25 · Context 1,048,576×25 / ×11
Qwen/Qwen3.7-Max×25$2.5 / $7.5 · Context 1,000,000×50 / ×19

Fireworks AI Aggregator

Fireworks AI model prices — 11 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
accounts/fireworks/models/glm-5p3-flash×1.6$0.15 / $0.5 · Context 1,000,000×3.0 / ×1.3
accounts/fireworks/routers/glm-5p3-flash-us×2.4$0.225 / $0.75 · Context 1,000,000×4.5 / ×1.9
accounts/fireworks/models/deepseek-v4p1-flash×3.6$0.3 / $1.2 · Context 1,000,000×6.0 / ×3.0
accounts/fireworks/models/deepseek-v4p1-flash-1017×3.6$0.3 / $1.2 · Context 1,000,000×6.0 / ×3.0
accounts/fireworks/routers/deepseek-v4p1-flash-us×5.4$0.45 / $1.8 · Context 1,000,000×9.0 / ×4.5
accounts/fireworks/models/nemotron-3-ultra-nvfp4×7.2$0.6 / $2.4 · Context 1,000,000×12 / ×6.0
accounts/fireworks/models/glm-5p3×14$1.4 / $4.4 · Context 1,000,000×28 / ×11
accounts/fireworks/models/qwen3p8-max×20$2 / $6 · Arena rank #24 · Context 1,000,000×40 / ×15
accounts/fireworks/routers/glm-5p3-us×22$2.1 / $6.6 · Context 1,000,000×42 / ×17
accounts/fireworks/routers/glm-5p3-fast×22$2.1 / $6.6 · Context 1,000,000×42 / ×17
accounts/fireworks/routers/kimi-k3-fast×63$4.5 / $22.5 · Context 1,000,000×90 / ×56

Cloudflare Aggregator

Cloudflare model prices — 12 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
@cf/meta/llama-3.1-8b-instruct-fp8-fast×0.9$0.045 / $0.384×0.9 / ×1.0
@cf/meta/llama-3-8b-instruct-awq Deprecated×1.0$0.123 / $0.266 · Context 8,192×2.5 / ×0.7
@cf/meta/llama-3.1-8b-instruct-awq Deprecated×1.0$0.123 / $0.266 · Context 8,192×2.5 / ×0.7
@cf/meta/llama-3.1-8b-instruct-fp8×1.2$0.152 / $0.287 · Context 32,000×3.0 / ×0.7
@cf/ai4bharat/indictrans2-en-indic-1B×2.1$0.342 / $0.342×6.8 / ×0.9
@cf/meta/m2m100-1.2b×2.1$0.342 / $0.342×6.8 / ×0.9
@cf/meta/llama-3-8b-instruct Deprecated×2.8$0.282 / $0.827 · Arena rank #337 · Context 7,968×5.6 / ×2.1
@cf/moondream/moondream3.1-9B-A2B×3.2$0.3 / $1×6.0 / ×2.5
@cf/nvidia/nemotron-3-120b-a12b×5.0$0.5 / $1.5 · Context 256,000×10 / ×3.8
@cf/meta/llama-3.1-70b-instruct-fp8-fast×5.7$0.293 / $2.253×5.9 / ×5.6
@cf/meta/llama-3.3-70b-instruct-fp8-fast×5.7$0.293 / $2.253 · Context 24,000×5.9 / ×5.6
@cf/meta/llama-2-7b-chat-fp16 Deprecated×16$0.556 / $6.667 · Context 4,096×11 / ×17

Amazon Bedrock Aggregator

Amazon Bedrock model prices — 30 matching models; USD per 1M tokens unless another unit is stated
ModelCost IndexInput / output price, Arena rank and contextInput / output index
NovaMicro×0.4$0.035 / $0.14 · Context 128,000×0.7 / ×0.4
Ministral-3-3b-Instruct×0.6$0.1 / $0.1×2.0 / ×0.3
Nemotron-Nano-9B-V2×0.7$0.06 / $0.23×1.2 / ×0.6
NovaLite×0.7$0.06 / $0.24 · Context 300,000×1.2 / ×0.6
Nemotron-Nano-3-30B×0.7$0.06 / $0.24×1.2 / ×0.6
Ministral-3-8b-Instruct×0.9$0.15 / $0.15×3.0 / ×0.4
Llama3-2-11B×1.0$0.16 / $0.16×3.2 / ×0.4
TitanTextG1-Lite×1.0$0.15 / $0.2×3.0 / ×0.5
Mistral7B×1.0$0.15 / $0.2×3.0 / ×0.5
Voxtral-Mini-24B-2507×1.0$0.1 / $0.3×2.0 / ×0.8
Ministral-3-14b-Instruct×1.2$0.2 / $0.2×4.0 / ×0.5
writer.palmyra-vision-7b×1.8$0.15 / $0.6×3.0 / ×1.5
Llama4-Scout-17B×2.0$0.17 / $0.66×3.4 / ×1.7
Nemotron-Nano-12B-V2-VL-BF16×2.0$0.2 / $0.6×4.0 / ×1.5
TitanTextG1-Express×2.0$0.2 / $0.6×4.0 / ×1.5
Llama3-8B×2.4$0.3 / $0.6×6.0 / ×1.5
Llama4-Maverick-17B×2.9$0.24 / $0.97×4.8 / ×2.4
Mixtral8x7B×3.2$0.45 / $0.7×9.0 / ×1.8
Llama3-2-90B×4.3$0.72 / $0.72×14 / ×1.8
TitanText-Premier×5.0$0.5 / $1.5×10 / ×3.8
Mistral-Large-3-675b-Instruct×5.0$0.5 / $1.5×10 / ×3.8
mistral.devstral-2-123b×5.6$0.4 / $2×8.0 / ×5.0
Nova2.0Lite×6.8$0.33 / $2.75 · Arena rank #243 · Context 1,000,000×6.6 / ×6.9
Qwen3-VL-235B-A22B×7.4$0.53 / $2.66×11 / ×6.7
NovaPro×9.6$0.8 / $3.2 · Context 300,000×16 / ×8.0
MistralSmall×10$1 / $3×20 / ×7.5
Llama3-70B×18$2.65 / $3.5×53 / ×8.8
PixtralLarge2502×20$2 / $6×40 / ×15
NovaPremier×35$2.5 / $12.5 · Context 1,000,000×50 / ×31
MistralLarge×40$4 / $12 · Context 128,000×80 / ×30

Arena quality & value

Current model quality against the same Cost Index basis used above.

Arena chart data — Overall
ModelArena rankRatingCost IndexCheapest providerEvaluation
Amazon Nova 2 Lite2431335×6.2OpenRouternova-2-lite
Anthropic: Claude Opus 4.681497×70AnthropicClaude Opus 4.6
Anthropic: Claude Opus 4.7111494×70AnthropicClaude Opus 4.7
Anthropic: Claude Opus 4.8401474×70Anthropicclaude-opus-4-8
Anthropic: Claude Sonnet 4.6451472×42Anthropicclaude-sonnet-4-6
Anthropic: Claude Sonnet 5581461×28AnthropicArena evaluated claude-sonnet-5-high (High), not the base model. This reviewed representative evaluation is used for Anthropic: Claude Sonnet 5's rank, filters and quality comparisons.
c4ai-aya-expanse-32b3121267×5.0Coherec4ai-aya-expanse-32b
Claude Haiku 4 5 202510011441414×14Anthropicclaude-haiku-4-5-20251001
Claude Opus 4 5 20251101481470×70Anthropicclaude-opus-4-5-20251101
Claude Sonnet 4 5 20250929701455×42Anthropicclaude-sonnet-4-5-20250929
Cohere: Command R (08-2024)3221251×1.8Coherecommand-r-08-2024
Cohere: Command R+ (08-2024)3061276×30Coherecommand-r-plus-08-2024
command-a-03-20252121354×30Coherecommand-a-03-2025
DeepSeek V4 Flash 0423 (Preview)1041436×0.7DeepInfradeepseek-v4-flash
DeepSeek-V32081358×3.1DeepInfradeepseek-v3
DeepSeek-V3-03241671395×2.8Hugging Face Inference Providersdeepseek-v3-0324
DeepSeek-V3.11351417×2.9DeepInfradeepseek-v3.1
DeepSeek: DeepSeek V3.1 Terminus1411415×3.0Hugging Face Inference Providersdeepseek-v3.1-terminus
DeepSeek: DeepSeek V3.21231425×1.8DeepInfradeepseek-v3.2
DeepSeek: DeepSeek V3.2 Exp1291422×1.9Novita AIdeepseek-v3.2-exp
DeepSeek: DeepSeek V4 Pro 0423641458×7.6OpenRouterdeepseek-v4-pro
DeepSeek: R11651398×7.8Hugging Face Inference Providersdeepseek-r1
DeepSeek: R1 05281301421×6.3DeepInfradeepseek-r1-0528
Gemini 2.5 Flash1511409×6.2DeepInfragemini-2.5-flash
Gemini 2.5 Pro871445×25DeepInfragemini-2.5-pro
Gemini 3.1 Flash-Lite Preview1101433×4.0OpenRoutergemini-3.1-flash-lite-preview
Gemini 3.1 Pro Preview191487×32GoogleGemini 3.1 Pro Preview
Gemini 3.5 Flash331476×24DeepInfraArena has 2 reviewed evaluations for Gemini 3.5 Flash. AI for Less conservatively uses the lowest-performing result: gemini-3.5-flash-medium (Medium). gemini-3.5-flash-high (High): Arena #29, rating 1477. gemini-3.5-flash-medium (Medium): Arena #33, rating 1476 — used.
Gemini 3.5 Flash-Lite721455×6.2Googlegemini-3.5-flash-lite
Gemini 3.6 Flash231483×11GoogleArena evaluated gemini-3.6-flash-high (High), not the base model. This reviewed representative evaluation is used for Gemini 3.6 Flash's rank, filters and quality comparisons.
Gemma 2 27B2931290×3.9OpenRoutergemma-2-27b-it
Gemma 3 12B2331342×0.5DeepInfragemma-3-12b-it
Gemma 3 27B2001365×0.6DeepInfragemma-3-27b-it
Gemma 3 4B2841303×0.3Amazon Bedrockgemma-3-4b-it
Gemma 4 31B761452×6.9Cerebrasgemma-4-31b
GLM-4.51501411×6.8OpenRouterglm-4.5
GLM-4.5-Air1961373×2.2Hugging Face Inference Providersglm-4.5-air
GLM-4.61251424×6.0Hugging Face Inference Providersglm-4.6
GLM-4.6V1911378×3.0Novita AIglm-4.6v
GLM-4.7951441×5.1Hugging Face Inference Providersglm-4.7
GLM-4.7-Flash2011365×1.0Cloudflareglm-4.7-flash
GLM-5651457×6.6Hugging Face Inference Providersglm-5
GLM-5.1541465×9.9OpenRouterglm-5.1
GLM-5.2321476×7.3OpenRouterArena evaluated glm-5.2-max (Max), not the base model. This reviewed representative evaluation is used for GLM-5.2's rank, filters and quality comparisons.
GLM-5.3281479×3.1OpenRouterArena evaluated glm-5.3-max (Max), not the base model. This reviewed representative evaluation is used for GLM-5.3's rank, filters and quality comparisons.
GLM-5V-Turbo1091434×13OpenRouterglm-5v-turbo
gpt-3.5-turbo-01253351226×5.0OpenAIgpt-3.5-turbo-0125
gpt-3.5-turbo-11063451204×8.0OpenAIgpt-3.5-turbo-1106
GPT-4 Turbo (2024-04-09)2531325×100OpenAIgpt-4-turbo-2024-04-09
GPT-4 Turbo Preview2721313×100OpenAIgpt-4-0125-preview
gpt-4-03142961288×240OpenAIgpt-4-0314
gpt-4-06133071276×240OpenAIgpt-4-0613
gpt-4.1-2025-04-141421415×24OpenAIgpt-4.1-2025-04-14
gpt-4.1-mini-2025-04-141871383×4.8OpenAIgpt-4.1-mini-2025-04-14
gpt-4.1-nano-2025-04-142581322×1.2OpenAIgpt-4.1-nano-2025-04-14
GPT-4.5 Preview (2025-02-27)881445×600OpenAIgpt-4.5-preview-2025-02-27
gpt-4o-mini-2024-07-182651318×1.8OpenAIgpt-4o-mini-2024-07-18
gpt-5.21051435×35OpenAIgpt-5.2
gpt-5.3-chat-latest781450×35OpenAIgpt-5.3-chat-latest
gpt-5.6-luna751453×1.6OpenRouterArena evaluated gpt-5.6-luna-xhigh (xHigh), not the base model. This reviewed representative evaluation is used for gpt-5.6-luna's rank, filters and quality comparisons.
gpt-5.6-sol211485×14OpenRouterArena evaluated gpt-5.6-sol-xhigh (xHigh), not the base model. This reviewed representative evaluation is used for gpt-5.6-sol's rank, filters and quality comparisons.
gpt-5.6-terra511466×16OpenRouterArena evaluated gpt-5.6-terra-xhigh (xHigh), not the base model. This reviewed representative evaluation is used for gpt-5.6-terra's rank, filters and quality comparisons.
gpt-oss-120b2151352×0.5Hugging Face Inference Providersgpt-oss-120b
gpt-oss-20b2671317×0.3OpenRoutergpt-oss-20b
Granite-4.2-30B2351340×1.9Hugging Face Inference Providersgranite-4.2-30b
Granite-4.2-3B2921290×0.4Hugging Face Inference Providersgranite-4.2-3b
Granite-4.2-8B2901290×0.7Hugging Face Inference Providersgranite-4.2-8b
Grok 4.5521466×20OpenRoutergrok-4.5
Grok 4.6731454×20OpenRouterArena evaluated grok-4.6-high (High), not the base model. This reviewed representative evaluation is used for Grok 4.6's rank, filters and quality comparisons.
Llama 3 8b Instruct3371224×2.8Cloudflarellama-3-8b-instruct
Meta: Llama 3.1 70B Instruct2891293×2.4OpenRouterllama-3.1-70b-instruct
Meta: Llama 3.1 8B Instruct3431211×0.2Hugging Face Inference Providersllama-3.1-8b-instruct
Meta: Llama 3.2 1B Instruct3981111×0.5Cloudflarellama-3.2-1b-instruct
Meta: Llama 3.2 3B Instruct3691167×0.9OpenRouterllama-3.2-3b-instruct
Meta: Llama 3.3 70B Instruct2641318×1.0OpenRouterllama-3.3-70b-instruct
Meta: Llama 4 Maverick2491327×2.1OpenRouterllama-4-maverick-17b-128e-instruct
Meta: Llama 4 Scout2601322×0.9Hugging Face Inference Providersllama-4-scout-17b-16e-instruct
Meta: Muse Spark 1.1131490×14OpenRouterMuse Spark 1.1
MiniMax-M12021364×6.6OpenRouterminimax-m1
MiniMax-M22271343×3.1OpenRouterminimax-m2
MiniMax-M2.51761391×3.0OpenRouterminimax-m2.5
MiniMax-M2.71401415×3.0Hugging Face Inference Providersminimax-m2.7
MiniMax-M3961441×3.3Hugging Face Inference Providersminimax-m3
Mistral Large 24072691314×20OpenRoutermistral-large-2407
Mistral Large 41111432×6.9Mistral AImistral-large-4
Mistral Medium 3.51171426×21Mistral AImistral-medium-3.5
Mistral Small 33081274×0.4DeepInframistral-small-24b-instruct-2501
MoonshotAI: Kimi K2.51141431×6.3Hugging Face Inference ProvidersArena has 2 reviewed evaluations for MoonshotAI: Kimi K2.5. AI for Less conservatively uses the lowest-performing result: kimi-k2.5-instant (Instant). kimi-k2.5-thinking (Thinking): Arena #79, rating 1450. kimi-k2.5-instant (Instant): Arena #114, rating 1431 — used.
MoonshotAI: Kimi K2.6591461×9.4OpenRouterkimi-k2.6
Nemotron-3-Nano-30B-A3B2711314×0.6Novita AIArena evaluated nvidia-nemotron-3-nano-30b-a3b-bf16 (BF16), not the base model. This reviewed representative evaluation is used for Nemotron-3-Nano-30B-A3B's rank, filters and quality comparisons.
Nvidia Nemotron 3 Ultra 550b A55b Nvfp41211426×7.2Hugging Face Inference Providersnvidia-nemotron-3-ultra-550b-a55b-nvfp4
Nvidia Nemotron 3.5 Super Vl 120b A12b Nvfp41381416×1.8Hugging Face Inference Providersnvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4
NVIDIA-Nemotron-3-Super-120B-A12B2061360×1.1DeepInfranvidia-nemotron-3-super-120b-a12b
o1-2024-12-171581402×180OpenAIo1-2024-12-17
o1-mini2371337×13OpenAIo1-mini
o1-preview1781389×180OpenAIo1-preview
o3-mini2201348×13OpenAIo3-mini
o4-mini-2025-04-161741391×13OpenAIo4-mini-2025-04-16
OpenAI: GPT-4o (2024-05-13)2251346×50OpenAIgpt-4o-2024-05-13
OpenAI: GPT-4o (2024-08-06)2401336×30OpenAIgpt-4o-2024-08-06
OpenAI: GPT-51061435×25OpenAIArena evaluated gpt-5-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5's rank, filters and quality comparisons.
OpenAI: GPT-5 Mini1771390×5.0OpenAIArena evaluated gpt-5-mini-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5 Mini's rank, filters and quality comparisons.
OpenAI: GPT-5 Nano2361338×1.0OpenAIArena evaluated gpt-5-nano-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5 Nano's rank, filters and quality comparisons.
OpenAI: GPT-5.1991439×25OpenAIgpt-5.1
OpenAI: GPT-5.4551465×40OpenAIgpt-5.4
OpenAI: GPT-5.4 Mini851447×12OpenAIArena evaluated gpt-5.4-mini-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5.4 Mini's rank, filters and quality comparisons.
OpenAI: GPT-5.4 Nano1611401×3.3OpenAIArena evaluated gpt-5.4-nano-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5.4 Nano's rank, filters and quality comparisons.
OpenAI: GPT-5.5311477×80OpenAIgpt-5.5
Phi-43201256×0.6DeepInfraphi-4
Qwen: Qwen3 235B A22B1921375×2.0Hugging Face Inference Providersqwen3-235b-a22b
Qwen: Qwen3 235B A22B Thinking 25071631400×5.5Alibaba / Qwenqwen3-235b-a22b-thinking-2507
Qwen: Qwen3 30B A3B2501327×1.5DeepInfraqwen3-30b-a3b
Qwen: Qwen3 30B A3B Instruct 25071881382×1.0OpenRouterqwen3-30b-a3b-instruct-2507
Qwen: Qwen3 32B2231347×0.8Hugging Face Inference Providersqwen3-32b
Qwen: Qwen3 Next 80B A3B Instruct1641399×2.6DeepInfraqwen3-next-80b-a3b-instruct
Qwen: Qwen3 Next 80B A3B Thinking1981369×3.0Alibaba / Qwenqwen3-next-80b-a3b-thinking
Qwen: Qwen3 VL 235B A22B Instruct1461413×2.6DeepInfraqwen3-vl-235b-a22b-instruct
Qwen: Qwen3 VL 235B A22B Thinking1681395×9.6OpenRouterqwen3-vl-235b-a22b-thinking
Qwen: Qwen3.5 397B A17B941442×7.8DeepInfraqwen3.5-397b-a17b
Qwen: Qwen3.5-122B-A10B1361416×5.2OpenRouterqwen3.5-122b-a10b
Qwen: Qwen3.5-27B1531409×3.9OpenRouterqwen3.5-27b
Qwen: Qwen3.5-35B-A3B1691394×2.6DeepInfraqwen3.5-35b-a3b
Qwen: Qwen3.6 Max Preview601461×16OpenRouterqwen3.6-max-preview
Qwen: Qwen3.6 Plus901443×5.2OpenRouterqwen3.6-plus
Qwen: Qwen3.7 Plus691456×3.8OpenRouterqwen3.7-plus
Qwen: Qwen3.8 27B1001438×0.0OpenRouterqwen3.8-27b
Qwen: Qwen3.8 Max241482×17DeepInfraqwen3.8-max
Qwen2.5 Coder 32b Instruct3111271×0.6Hugging Face Inference Providersqwen2.5-coder-32b-instruct
Qwen2.5-72B-Instruct2851303×2.2DeepInfraqwen2.5-72b-instruct
Qwen3-235B-A22B-Instruct-25071281422×1.5DeepInfraqwen3-235b-a22b-instruct-2507
Qwen3-Coder-480B-A35B-Instruct1801388×4.6Hugging Face Inference Providersqwen3-coder-480b-a35b-instruct
qwen3-max-2025-09-231261423×17Alibaba / Qwenqwen3-max-2025-09-23
qwen3-max-preview1071434×17Alibaba / Qwenqwen3-max-preview
qwen3.5-flash1661396×1.2Alibaba / Qwenqwen3.5-flash
qwen3.7-max-preview391474×25Alibaba / Qwenqwen3.7-max-preview
Qwq 32b2411336×4.6Cloudflareqwq-32b
Tencent: Hy3741453×1.6Hugging Face Inference Providershy3
xAI: Grok 4.3931442×10OpenRoutergrok-4.3
Xiaomi: MiMo-V2.51081434×1.1Hugging Face Inference Providersmimo-v2.5
Xiaomi: MiMo-V2.5-Pro491467×3.5OpenRoutermimo-v2.5-pro
Xiaomi: MiMo-V2.6-Flash771451×1.1Novita AImimo-v2.6-flash
Xiaomi: MiMo-V2.6-Pro271479×3.5Novita AImimo-v2.6-pro
Z.ai: GLM 4.5V2141352×6.0Hugging Face Inference Providersglm-4.5v
Z.ai: GLM 5.3 Flash411474×0.6OpenRouterglm-5.3-flash

Quality vs cost

Higher Arena rating is better. Arena rank #1 is the top rank.

11001200130014001500×0.5×1×5×10×50×100×250×500Cost Index (log scale)Arena quality rating ↑ betterAmazon Nova 2 Lite Arena #243 · Rating 1335 Cost Index ×6.2 Cheapest at OpenRouterAnthropic: Claude Opus 4.6 Arena #8 · Rating 1497 Cost Index ×70 Cheapest at Anthropic Arena Top 10 #11Anthropic: Claude Opus 4.7 Arena #11 · Rating 1494 Cost Index ×70 Cheapest at Anthropic Arena Top 10 #22Anthropic: Claude Opus 4.8 Arena #40 · Rating 1474 Cost Index ×70 Cheapest at AnthropicAnthropic: Claude Sonnet 4.6 Arena #45 · Rating 1472 Cost Index ×42 Cheapest at AnthropicAnthropic: Claude Sonnet 5 Arena #58 · Rating 1461 Cost Index ×28 Cheapest at Anthropic Arena evaluated claude-sonnet-5-high (High), not the base model. This reviewed representative evaluation is used for Anthropic: Claude Sonnet 5's rank, filters and quality comparisons.c4ai-aya-expanse-32b Arena #312 · Rating 1267 Cost Index ×5.0 Cheapest at CohereClaude Haiku 4 5 20251001 Arena #144 · Rating 1414 Cost Index ×14 Cheapest at AnthropicClaude Opus 4 5 20251101 Arena #48 · Rating 1470 Cost Index ×70 Cheapest at AnthropicClaude Sonnet 4 5 20250929 Arena #70 · Rating 1455 Cost Index ×42 Cheapest at AnthropicCohere: Command R (08-2024) Arena #322 · Rating 1251 Cost Index ×1.8 Cheapest at CohereCohere: Command R+ (08-2024) Arena #306 · Rating 1276 Cost Index ×30 Cheapest at Coherecommand-a-03-2025 Arena #212 · Rating 1354 Cost Index ×30 Cheapest at CohereDeepSeek V4 Flash 0423 (Preview) Arena #104 · Rating 1436 Cost Index ×0.7 Cheapest at DeepInfraDeepSeek-V3 Arena #208 · Rating 1358 Cost Index ×3.1 Cheapest at DeepInfraDeepSeek-V3-0324 Arena #167 · Rating 1395 Cost Index ×2.8 Cheapest at Hugging Face Inference ProvidersDeepSeek-V3.1 Arena #135 · Rating 1417 Cost Index ×2.9 Cheapest at DeepInfraDeepSeek: DeepSeek V3.1 Terminus Arena #141 · Rating 1415 Cost Index ×3.0 Cheapest at Hugging Face Inference ProvidersDeepSeek: DeepSeek V3.2 Arena #123 · Rating 1425 Cost Index ×1.8 Cheapest at DeepInfraDeepSeek: DeepSeek V3.2 Exp Arena #129 · Rating 1422 Cost Index ×1.9 Cheapest at Novita AIDeepSeek: DeepSeek V4 Pro 0423 Arena #64 · Rating 1458 Cost Index ×7.6 Cheapest at OpenRouterDeepSeek: R1 Arena #165 · Rating 1398 Cost Index ×7.8 Cheapest at Hugging Face Inference ProvidersDeepSeek: R1 0528 Arena #130 · Rating 1421 Cost Index ×6.3 Cheapest at DeepInfraGemini 2.5 Flash Arena #151 · Rating 1409 Cost Index ×6.2 Cheapest at DeepInfraGemini 2.5 Pro Arena #87 · Rating 1445 Cost Index ×25 Cheapest at DeepInfraGemini 3.1 Flash-Lite Preview Arena #110 · Rating 1433 Cost Index ×4.0 Cheapest at OpenRouterGemini 3.1 Pro Preview Arena #19 · Rating 1487 Cost Index ×32 Cheapest at Google Arena Top 10 #44Gemini 3.5 Flash Arena #33 · Rating 1476 Cost Index ×24 Cheapest at DeepInfra Arena has 2 reviewed evaluations for Gemini 3.5 Flash. AI for Less conservatively uses the lowest-performing result: gemini-3.5-flash-medium (Medium). gemini-3.5-flash-high (High): Arena #29, rating 1477. gemini-3.5-flash-medium (Medium): Arena #33, rating 1476 — used.Gemini 3.5 Flash-Lite Arena #72 · Rating 1455 Cost Index ×6.2 Cheapest at GoogleGemini 3.6 Flash Arena #23 · Rating 1483 Cost Index ×11 Cheapest at Google Arena Top 10 #6 Arena evaluated gemini-3.6-flash-high (High), not the base model. This reviewed representative evaluation is used for Gemini 3.6 Flash's rank, filters and quality comparisons.6Gemma 2 27B Arena #293 · Rating 1290 Cost Index ×3.9 Cheapest at OpenRouterGemma 3 12B Arena #233 · Rating 1342 Cost Index ×0.5 Cheapest at DeepInfraGemma 3 27B Arena #200 · Rating 1365 Cost Index ×0.6 Cheapest at DeepInfraGemma 3 4B Arena #284 · Rating 1303 Cost Index ×0.3 Cheapest at Amazon BedrockGemma 4 31B Arena #76 · Rating 1452 Cost Index ×6.9 Cheapest at CerebrasGLM-4.5 Arena #150 · Rating 1411 Cost Index ×6.8 Cheapest at OpenRouterGLM-4.5-Air Arena #196 · Rating 1373 Cost Index ×2.2 Cheapest at Hugging Face Inference ProvidersGLM-4.6 Arena #125 · Rating 1424 Cost Index ×6.0 Cheapest at Hugging Face Inference ProvidersGLM-4.6V Arena #191 · Rating 1378 Cost Index ×3.0 Cheapest at Novita AIGLM-4.7 Arena #95 · Rating 1441 Cost Index ×5.1 Cheapest at Hugging Face Inference ProvidersGLM-4.7-Flash Arena #201 · Rating 1365 Cost Index ×1.0 Cheapest at CloudflareGLM-5 Arena #65 · Rating 1457 Cost Index ×6.6 Cheapest at Hugging Face Inference ProvidersGLM-5.1 Arena #54 · Rating 1465 Cost Index ×9.9 Cheapest at OpenRouterGLM-5.2 Arena #32 · Rating 1476 Cost Index ×7.3 Cheapest at OpenRouter Arena evaluated glm-5.2-max (Max), not the base model. This reviewed representative evaluation is used for GLM-5.2's rank, filters and quality comparisons.GLM-5.3 Arena #28 · Rating 1479 Cost Index ×3.1 Cheapest at OpenRouter Arena Top 10 #9 Arena evaluated glm-5.3-max (Max), not the base model. This reviewed representative evaluation is used for GLM-5.3's rank, filters and quality comparisons.9GLM-5V-Turbo Arena #109 · Rating 1434 Cost Index ×13 Cheapest at OpenRoutergpt-3.5-turbo-0125 Arena #335 · Rating 1226 Cost Index ×5.0 Cheapest at OpenAIgpt-3.5-turbo-1106 Arena #345 · Rating 1204 Cost Index ×8.0 Cheapest at OpenAIGPT-4 Turbo (2024-04-09) Arena #253 · Rating 1325 Cost Index ×100 Cheapest at OpenAIGPT-4 Turbo Preview Arena #272 · Rating 1313 Cost Index ×100 Cheapest at OpenAIgpt-4-0314 Arena #296 · Rating 1288 Cost Index ×240 Cheapest at OpenAIgpt-4-0613 Arena #307 · Rating 1276 Cost Index ×240 Cheapest at OpenAIgpt-4.1-2025-04-14 Arena #142 · Rating 1415 Cost Index ×24 Cheapest at OpenAIgpt-4.1-mini-2025-04-14 Arena #187 · Rating 1383 Cost Index ×4.8 Cheapest at OpenAIgpt-4.1-nano-2025-04-14 Arena #258 · Rating 1322 Cost Index ×1.2 Cheapest at OpenAIGPT-4.5 Preview (2025-02-27) Arena #88 · Rating 1445 Cost Index ×600 Cheapest at OpenAIgpt-4o-mini-2024-07-18 Arena #265 · Rating 1318 Cost Index ×1.8 Cheapest at OpenAIgpt-5.2 Arena #105 · Rating 1435 Cost Index ×35 Cheapest at OpenAIgpt-5.3-chat-latest Arena #78 · Rating 1450 Cost Index ×35 Cheapest at OpenAIgpt-5.6-luna Arena #75 · Rating 1453 Cost Index ×1.6 Cheapest at OpenRouter Arena evaluated gpt-5.6-luna-xhigh (xHigh), not the base model. This reviewed representative evaluation is used for gpt-5.6-luna's rank, filters and quality comparisons.gpt-5.6-sol Arena #21 · Rating 1485 Cost Index ×14 Cheapest at OpenRouter Arena Top 10 #5 Arena evaluated gpt-5.6-sol-xhigh (xHigh), not the base model. This reviewed representative evaluation is used for gpt-5.6-sol's rank, filters and quality comparisons.5gpt-5.6-terra Arena #51 · Rating 1466 Cost Index ×16 Cheapest at OpenRouter Arena evaluated gpt-5.6-terra-xhigh (xHigh), not the base model. This reviewed representative evaluation is used for gpt-5.6-terra's rank, filters and quality comparisons.gpt-oss-120b Arena #215 · Rating 1352 Cost Index ×0.5 Cheapest at Hugging Face Inference Providersgpt-oss-20b Arena #267 · Rating 1317 Cost Index ×0.3 Cheapest at OpenRouterGranite-4.2-30B Arena #235 · Rating 1340 Cost Index ×1.9 Cheapest at Hugging Face Inference ProvidersGranite-4.2-3B Arena #292 · Rating 1290 Cost Index ×0.4 Cheapest at Hugging Face Inference ProvidersGranite-4.2-8B Arena #290 · Rating 1290 Cost Index ×0.7 Cheapest at Hugging Face Inference ProvidersGrok 4.5 Arena #52 · Rating 1466 Cost Index ×20 Cheapest at OpenRouterGrok 4.6 Arena #73 · Rating 1454 Cost Index ×20 Cheapest at OpenRouter Arena evaluated grok-4.6-high (High), not the base model. This reviewed representative evaluation is used for Grok 4.6's rank, filters and quality comparisons.Llama 3 8b Instruct Arena #337 · Rating 1224 Cost Index ×2.8 Cheapest at CloudflareMeta: Llama 3.1 70B Instruct Arena #289 · Rating 1293 Cost Index ×2.4 Cheapest at OpenRouterMeta: Llama 3.1 8B Instruct Arena #343 · Rating 1211 Cost Index ×0.2 Cheapest at Hugging Face Inference ProvidersMeta: Llama 3.2 1B Instruct Arena #398 · Rating 1111 Cost Index ×0.5 Cheapest at CloudflareMeta: Llama 3.2 3B Instruct Arena #369 · Rating 1167 Cost Index ×0.9 Cheapest at OpenRouterMeta: Llama 3.3 70B Instruct Arena #264 · Rating 1318 Cost Index ×1.0 Cheapest at OpenRouterMeta: Llama 4 Maverick Arena #249 · Rating 1327 Cost Index ×2.1 Cheapest at OpenRouterMeta: Llama 4 Scout Arena #260 · Rating 1322 Cost Index ×0.9 Cheapest at Hugging Face Inference ProvidersMeta: Muse Spark 1.1 Arena #13 · Rating 1490 Cost Index ×14 Cheapest at OpenRouter Arena Top 10 #33MiniMax-M1 Arena #202 · Rating 1364 Cost Index ×6.6 Cheapest at OpenRouterMiniMax-M2 Arena #227 · Rating 1343 Cost Index ×3.1 Cheapest at OpenRouterMiniMax-M2.5 Arena #176 · Rating 1391 Cost Index ×3.0 Cheapest at OpenRouterMiniMax-M2.7 Arena #140 · Rating 1415 Cost Index ×3.0 Cheapest at Hugging Face Inference ProvidersMiniMax-M3 Arena #96 · Rating 1441 Cost Index ×3.3 Cheapest at Hugging Face Inference ProvidersMistral Large 2407 Arena #269 · Rating 1314 Cost Index ×20 Cheapest at OpenRouterMistral Large 4 Arena #111 · Rating 1432 Cost Index ×6.9 Cheapest at Mistral AIMistral Medium 3.5 Arena #117 · Rating 1426 Cost Index ×21 Cheapest at Mistral AIMistral Small 3 Arena #308 · Rating 1274 Cost Index ×0.4 Cheapest at DeepInfraMoonshotAI: Kimi K2.5 Arena #114 · Rating 1431 Cost Index ×6.3 Cheapest at Hugging Face Inference Providers Arena has 2 reviewed evaluations for MoonshotAI: Kimi K2.5. AI for Less conservatively uses the lowest-performing result: kimi-k2.5-instant (Instant). kimi-k2.5-thinking (Thinking): Arena #79, rating 1450. kimi-k2.5-instant (Instant): Arena #114, rating 1431 — used.MoonshotAI: Kimi K2.6 Arena #59 · Rating 1461 Cost Index ×9.4 Cheapest at OpenRouterNemotron-3-Nano-30B-A3B Arena #271 · Rating 1314 Cost Index ×0.6 Cheapest at Novita AI Arena evaluated nvidia-nemotron-3-nano-30b-a3b-bf16 (BF16), not the base model. This reviewed representative evaluation is used for Nemotron-3-Nano-30B-A3B's rank, filters and quality comparisons.Nvidia Nemotron 3 Ultra 550b A55b Nvfp4 Arena #121 · Rating 1426 Cost Index ×7.2 Cheapest at Hugging Face Inference ProvidersNvidia Nemotron 3.5 Super Vl 120b A12b Nvfp4 Arena #138 · Rating 1416 Cost Index ×1.8 Cheapest at Hugging Face Inference ProvidersNVIDIA-Nemotron-3-Super-120B-A12B Arena #206 · Rating 1360 Cost Index ×1.1 Cheapest at DeepInfrao1-2024-12-17 Arena #158 · Rating 1402 Cost Index ×180 Cheapest at OpenAIo1-mini Arena #237 · Rating 1337 Cost Index ×13 Cheapest at OpenAIo1-preview Arena #178 · Rating 1389 Cost Index ×180 Cheapest at OpenAIo3-mini Arena #220 · Rating 1348 Cost Index ×13 Cheapest at OpenAIo4-mini-2025-04-16 Arena #174 · Rating 1391 Cost Index ×13 Cheapest at OpenAIOpenAI: GPT-4o (2024-05-13) Arena #225 · Rating 1346 Cost Index ×50 Cheapest at OpenAIOpenAI: GPT-4o (2024-08-06) Arena #240 · Rating 1336 Cost Index ×30 Cheapest at OpenAIOpenAI: GPT-5 Arena #106 · Rating 1435 Cost Index ×25 Cheapest at OpenAI Arena evaluated gpt-5-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5's rank, filters and quality comparisons.OpenAI: GPT-5 Mini Arena #177 · Rating 1390 Cost Index ×5.0 Cheapest at OpenAI Arena evaluated gpt-5-mini-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5 Mini's rank, filters and quality comparisons.OpenAI: GPT-5 Nano Arena #236 · Rating 1338 Cost Index ×1.0 Cheapest at OpenAI Arena evaluated gpt-5-nano-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5 Nano's rank, filters and quality comparisons.OpenAI: GPT-5.1 Arena #99 · Rating 1439 Cost Index ×25 Cheapest at OpenAIOpenAI: GPT-5.4 Arena #55 · Rating 1465 Cost Index ×40 Cheapest at OpenAIOpenAI: GPT-5.4 Mini Arena #85 · Rating 1447 Cost Index ×12 Cheapest at OpenAI Arena evaluated gpt-5.4-mini-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5.4 Mini's rank, filters and quality comparisons.OpenAI: GPT-5.4 Nano Arena #161 · Rating 1401 Cost Index ×3.3 Cheapest at OpenAI Arena evaluated gpt-5.4-nano-high (High), not the base model. This reviewed representative evaluation is used for OpenAI: GPT-5.4 Nano's rank, filters and quality comparisons.OpenAI: GPT-5.5 Arena #31 · Rating 1477 Cost Index ×80 Cheapest at OpenAI Arena Top 10 #1010Phi-4 Arena #320 · Rating 1256 Cost Index ×0.6 Cheapest at DeepInfraQwen: Qwen3 235B A22B Arena #192 · Rating 1375 Cost Index ×2.0 Cheapest at Hugging Face Inference ProvidersQwen: Qwen3 235B A22B Thinking 2507 Arena #163 · Rating 1400 Cost Index ×5.5 Cheapest at Alibaba / QwenQwen: Qwen3 30B A3B Arena #250 · Rating 1327 Cost Index ×1.5 Cheapest at DeepInfraQwen: Qwen3 30B A3B Instruct 2507 Arena #188 · Rating 1382 Cost Index ×1.0 Cheapest at OpenRouterQwen: Qwen3 32B Arena #223 · Rating 1347 Cost Index ×0.8 Cheapest at Hugging Face Inference ProvidersQwen: Qwen3 Next 80B A3B Instruct Arena #164 · Rating 1399 Cost Index ×2.6 Cheapest at DeepInfraQwen: Qwen3 Next 80B A3B Thinking Arena #198 · Rating 1369 Cost Index ×3.0 Cheapest at Alibaba / QwenQwen: Qwen3 VL 235B A22B Instruct Arena #146 · Rating 1413 Cost Index ×2.6 Cheapest at DeepInfraQwen: Qwen3 VL 235B A22B Thinking Arena #168 · Rating 1395 Cost Index ×9.6 Cheapest at OpenRouterQwen: Qwen3.5 397B A17B Arena #94 · Rating 1442 Cost Index ×7.8 Cheapest at DeepInfraQwen: Qwen3.5-122B-A10B Arena #136 · Rating 1416 Cost Index ×5.2 Cheapest at OpenRouterQwen: Qwen3.5-27B Arena #153 · Rating 1409 Cost Index ×3.9 Cheapest at OpenRouterQwen: Qwen3.5-35B-A3B Arena #169 · Rating 1394 Cost Index ×2.6 Cheapest at DeepInfraQwen: Qwen3.6 Max Preview Arena #60 · Rating 1461 Cost Index ×16 Cheapest at OpenRouterQwen: Qwen3.6 Plus Arena #90 · Rating 1443 Cost Index ×5.2 Cheapest at OpenRouterQwen: Qwen3.7 Plus Arena #69 · Rating 1456 Cost Index ×3.8 Cheapest at OpenRouterQwen: Qwen3.8 27B Arena #100 · Rating 1438 Cost Index ×0.0 Cheapest at OpenRouterQwen: Qwen3.8 Max Arena #24 · Rating 1482 Cost Index ×17 Cheapest at DeepInfra Arena Top 10 #77Qwen2.5 Coder 32b Instruct Arena #311 · Rating 1271 Cost Index ×0.6 Cheapest at Hugging Face Inference ProvidersQwen2.5-72B-Instruct Arena #285 · Rating 1303 Cost Index ×2.2 Cheapest at DeepInfraQwen3-235B-A22B-Instruct-2507 Arena #128 · Rating 1422 Cost Index ×1.5 Cheapest at DeepInfraQwen3-Coder-480B-A35B-Instruct Arena #180 · Rating 1388 Cost Index ×4.6 Cheapest at Hugging Face Inference Providersqwen3-max-2025-09-23 Arena #126 · Rating 1423 Cost Index ×17 Cheapest at Alibaba / Qwenqwen3-max-preview Arena #107 · Rating 1434 Cost Index ×17 Cheapest at Alibaba / Qwenqwen3.5-flash Arena #166 · Rating 1396 Cost Index ×1.2 Cheapest at Alibaba / Qwenqwen3.7-max-preview Arena #39 · Rating 1474 Cost Index ×25 Cheapest at Alibaba / QwenQwq 32b Arena #241 · Rating 1336 Cost Index ×4.6 Cheapest at CloudflareTencent: Hy3 Arena #74 · Rating 1453 Cost Index ×1.6 Cheapest at Hugging Face Inference ProvidersxAI: Grok 4.3 Arena #93 · Rating 1442 Cost Index ×10 Cheapest at OpenRouterXiaomi: MiMo-V2.5 Arena #108 · Rating 1434 Cost Index ×1.1 Cheapest at Hugging Face Inference ProvidersXiaomi: MiMo-V2.5-Pro Arena #49 · Rating 1467 Cost Index ×3.5 Cheapest at OpenRouterXiaomi: MiMo-V2.6-Flash Arena #77 · Rating 1451 Cost Index ×1.1 Cheapest at Novita AIXiaomi: MiMo-V2.6-Pro Arena #27 · Rating 1479 Cost Index ×3.5 Cheapest at Novita AI Arena Top 10 #88Z.ai: GLM 4.5V Arena #214 · Rating 1352 Cost Index ×6.0 Cheapest at Hugging Face Inference ProvidersZ.ai: GLM 5.3 Flash Arena #41 · Rating 1474 Cost Index ×0.6 Cheapest at OpenRouter

All Arena-ranked models Arena Top 10

Arena Top 10

The highest-ranked Arena models tracked by AI for Less, shown with their current Cost Index.

ModelArena rank and Cost Index
Anthropic: Claude Opus 4.6 Arena #8 · Cost ×70
Anthropic: Claude Opus 4.7 Arena #11 · Cost ×70
Meta: Muse Spark 1.1 Arena #13 · Cost ×14
Gemini 3.1 Pro Preview Arena #19 · Cost ×32
gpt-5.6-sol Arena #21 · Cost ×14
Gemini 3.6 Flash Arena #23 · Cost ×11
Qwen: Qwen3.8 Max Arena #24 · Cost ×17
Xiaomi: MiMo-V2.6-Pro Arena #27 · Cost ×3.5
GLM-5.3 Arena #28 · Cost ×3.1
OpenAI: GPT-5.5 Arena #31 · Cost ×80

Quality data: Arena leaderboard dataset · CC BY 4.0 · Text leaderboard · style-controlled · published 2026-10-15