AI Model Picker

Recently Added Models

New models from the last 3 days

DeepSeek V4 Flash 0731 (Reasoning, Max Effort)
New
DeepSeek·$0.14/$0.28·113.0 t/s
Inkling Small
New
Thinking Machines·$0.30/$1.20·93.0 t/s

All Models

18 / 379

0(0–61)
0(0–78)
0.0(0.0–2121.4)
$262.50($0.04–$262.50)
Updated Artificial Analysis

DeepSeek V4 Flash 0731 (Reasoning, Max Effort)

New

DeepSeek·7/31/26

Pricing (per 1M)

Input: $0.14
Output: $0.28

Speed

Output t/s: 113.0
TTFT: 0.00s

Benchmarks

Intelligence: 49.9Coding: 69.1GPQA: 90.8HLE: 36.8SCICODE: 49.9LCR: 65.7TERMINALBENCH V2 1: 78.7TAU BANKING: 31.1

Claude Opus 5 (Adaptive Reasoning, Max Effort)

Anthropic·7/24/26

Pricing (per 1M)

Input: $5.00
Output: $25.00

Speed

Output t/s: 56.2
TTFT: 25.51s

Benchmarks

Intelligence: 60.7Coding: 78GPQA: 93.2HLE: 52.6SCICODE: 55.7LCR: 70.0TERMINALBENCH V2 1: 89.1TAU BANKING: 30.3

Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)

Anthropic·7/24/26

Pricing (per 1M)

Input: $5.00
Output: $25.00

Speed

Output t/s: 52.9
TTFT: 21.94s

Benchmarks

Intelligence: 60.1Coding: 77GPQA: 93.7HLE: 52.5SCICODE: 55.0LCR: 68.7TERMINALBENCH V2 1: 88.0TAU BANKING: 31.5

Claude Opus 5 (Adaptive Reasoning, High Effort)

Anthropic·7/24/26

Pricing (per 1M)

Input: $5.00
Output: $25.00

Speed

Output t/s: 53.6
TTFT: 9.45s

Benchmarks

Intelligence: 58.9Coding: 76.5GPQA: 93.7HLE: 50.7SCICODE: 54.3LCR: 67.0TERMINALBENCH V2 1: 87.6TAU BANKING: 32.8

GPT-5.6 Luna (max)

OpenAI·7/9/26

Pricing (per 1M)

Input: $0.20
Output: $1.20

Speed

Output t/s: 172.5
TTFT: 77.37s

Benchmarks

Intelligence: 51.2Coding: 71.4GPQA: 91.1HLE: 37.2SCICODE: 52.5LCR: 74.0TERMINALBENCH V2 1: 80.9TAU BANKING: 27.2

GPT-5.6 Luna (xhigh)

OpenAI·7/9/26

Pricing (per 1M)

Input: $0.20
Output: $1.20

Speed

Output t/s: 169.3
TTFT: 19.62s

Benchmarks

Intelligence: 49.1Coding: 68.6GPQA: 89.5HLE: 35.6SCICODE: 50.0LCR: 69.7TERMINALBENCH V2 1: 77.9TAU BANKING: 24.3

GPT-5.6 Terra (max)

OpenAI·7/9/26

Pricing (per 1M)

Input: $2.00
Output: $12.00

Speed

Output t/s: 127.5
TTFT: 73.33s

Benchmarks

Intelligence: 55Coding: 76.7GPQA: 92.5HLE: 41.8SCICODE: 53.9IFBENCH: 71.2LCR: 74.0TERMINALBENCH HARD: 57.6TERMINALBENCH V2 1: 88.0TAU2: 86.3TAU BANKING: 31.8

GPT-5.6 Sol (max)

OpenAI·7/9/26

Pricing (per 1M)

Input: $5.00
Output: $30.00

Speed

Output t/s: 66.9
TTFT: 57.23s

Benchmarks

Intelligence: 58.9Coding: 77.4GPQA: 94.1HLE: 47.2SCICODE: 56.1IFBENCH: 72.7LCR: 73.7TERMINALBENCH HARD: 65.9TERMINALBENCH V2 1: 88.0TAU2: 85.1TAU BANKING: 33.0

GPT-5.6 Sol (xhigh)

OpenAI·7/9/26

Pricing (per 1M)

Input: $5.00
Output: $30.00

Speed

Output t/s: 62.0
TTFT: 12.34s

Benchmarks

Intelligence: 57.7Coding: 78.3GPQA: 93.1HLE: 44.7SCICODE: 56.0IFBENCH: 71.0LCR: 71.0TERMINALBENCH HARD: 61.4TERMINALBENCH V2 1: 89.5TAU2: 84.8TAU BANKING: 32.6

Grok 4.5 (high)

SpaceXAI·7/8/26

Pricing (per 1M)

Input: $2.00
Output: $6.00

Speed

Output t/s: 52.3
TTFT: 9.99s

Benchmarks

Intelligence: 53.8Coding: 72.4GPQA: 93.1HLE: 40.3SCICODE: 54.1LCR: 67.7TERMINALBENCH V2 1: 81.6TAU BANKING: 32.6

Claude Sonnet 5 (Adaptive Reasoning, Max Effort)

Anthropic·6/30/26

Pricing (per 1M)

Input: $2.00
Output: $10.00

Speed

Output t/s: 79.2
TTFT: 102.27s

Benchmarks

Intelligence: 53.4Coding: 71.5GPQA: 91.1HLE: 39.6SCICODE: 53.6LCR: 70.7TERMINALBENCH V2 1: 80.5TAU BANKING: 28.2

MiniMax-M3

MiniMax·5/31/26

Pricing (per 1M)

Input: $0.30
Output: $1.20

Speed

Output t/s: 78.0
TTFT: 1.88s

Benchmarks

Intelligence: 44.4Coding: 58.6GPQA: 92.9HLE: 37.1SCICODE: 45.4IFBENCH: 82.9LCR: 74.0TERMINALBENCH HARD: 42.4TERMINALBENCH V2 1: 65.2TAU2: 88.9TAU BANKING: 13.0

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)

Anthropic·5/27/26

Pricing (per 1M)

Input: $10.00
Output: $50.00

Speed

Output t/s: 59.6
TTFT: 54.37s

Benchmarks

Intelligence: 59.9Coding: 76.5GPQA: 92.6HLE: 53.3SCICODE: 60.2IFBENCH: 63.5LCR: 70.0TERMINALBENCH HARD: 62.9TERMINALBENCH V2 1: 84.6TAU2: 98.5TAU BANKING: 26.8

DeepSeek V4 Pro (Reasoning, Max Effort)

DeepSeek·4/24/26

Pricing (per 1M)

Input: $0.43
Output: $0.87

Speed

Output t/s: 58.2
TTFT: 1.04s

Benchmarks

Intelligence: 44.3Coding: 59.4GPQA: 88.8HLE: 35.9SCICODE: 50.0IFBENCH: 76.5LCR: 66.3TERMINALBENCH HARD: 46.2TERMINALBENCH V2 1: 64.0TAU2: 96.2TAU BANKING: 25.8

DeepSeek V4 Pro (Reasoning, High Effort)

DeepSeek·4/24/26

Pricing (per 1M)

Input: $0.43
Output: $0.87

Speed

Output t/s: 53.7
TTFT: 0.99s

Benchmarks

Intelligence: 43.1Coding: 58.7GPQA: 90.5HLE: 33.5SCICODE: 46.4IFBENCH: 71.3LCR: 65.0TERMINALBENCH HARD: 41.7TERMINALBENCH V2 1: 64.8TAU2: 94.2TAU BANKING: 23.7

Qwen3.5 4B (Reasoning)

Alibaba·3/10/26

Pricing (per 1M)

Input: $0.03
Output: $0.15

Speed

Output t/s: 21.1
TTFT: 0.44s

Benchmarks

Intelligence: 20.1Coding: 22.6GPQA: 77.1HLE: 7.8SCICODE: 16.1IFBENCH: 52.0LCR: 55.7TERMINALBENCH HARD: 18.2TERMINALBENCH V2 1: 25.8TAU2: 92.1TAU BANKING: 8.2

Qwen3.5 4B (Non-reasoning)

Alibaba·3/10/26

Pricing (per 1M)

Input: $0.03
Output: $0.15

Speed

Output t/s: 18.3
TTFT: 0.54s

Benchmarks

Intelligence: 16Coding: 20.3GPQA: 71.2HLE: 7.5SCICODE: 18.3IFBENCH: 33.3LCR: 28.3TERMINALBENCH HARD: 11.4TERMINALBENCH V2 1: 21.3TAU2: 87.7TAU BANKING: 3.1

HyperNova 60B 2605

Multiverse Computing

Pricing (per 1M)

Input: $0.04
Output: $0.14

Speed

Output t/s: 418.1
TTFT: 0.46s

Benchmarks

Intelligence: 17.8Coding: 23.2GPQA: 73.3HLE: 15.1SCICODE: 33.0IFBENCH: 66.5LCR: 31.7TERMINALBENCH HARD: 23.5TERMINALBENCH V2 1: 18.4TAU2: 63.2TAU BANKING: 5.4