AI Model APIs
Browse and compare prices and capabilities for 2,260+ AI models from 80+ API providers
GLM-4.5
zhipuai
Input
$0.60/1M
Output
$2.20/1M
Context
131K
Max Output
98K
GLM-4.5-Flash
zhipuai
Input
Free/1M
Output
Free/1M
Context
131K
Max Output
98K
GLM-4.7
zhipuai
Input
$0.60/1M
Output
$2.20/1M
Context
205K
Max Output
131K
GPT OSS 120B
submodel
Input
$0.10/1M
Output
$0.50/1M
Context
131K
Max Output
33K
Qwen3 235B A22B Instruct 2507
submodel
Input
$0.20/1M
Output
$0.30/1M
Context
262K
Max Output
131K
Qwen3 Coder 480B A35B Instruct
submodel
Input
$0.20/1M
Output
$0.80/1M
Context
262K
Max Output
262K
Qwen3 235B A22B Thinking 2507
submodel
Input
$0.20/1M
Output
$0.60/1M
Context
262K
Max Output
131K
GLM 4.5 FP8
submodel
Input
$0.20/1M
Output
$0.80/1M
Context
131K
Max Output
131K
GLM 4.5 Air
submodel
Input
$0.10/1M
Output
$0.50/1M
Context
131K
Max Output
131K
DeepSeek R1 0528
submodel
Input
$0.50/1M
Output
$2.15/1M
Context
75K
Max Output
164K
DeepSeek V3.1
submodel
Input
$0.20/1M
Output
$0.80/1M
Context
75K
Max Output
164K
DeepSeek V3 0324
submodel
Input
$0.20/1M
Output
$0.80/1M
Context
75K
Max Output
164K
Kimi K2 Thinking
nano-gpt
Input
$0.30/1M
Output
$1.20/1M
Context
256K
Max Output
262K
Kimi K2 Instruct
nano-gpt
Input
$0.10/1M
Output
$2.00/1M
Context
256K
Max Output
8K
Hermes 4 405b Thinking
nano-gpt
Input
$1.00/1M
Output
$2.00/1M
Context
128K
Max Output
8K
Nvidia Nemotron Super 49B v1.5
nano-gpt
Input
$0.05/1M
Output
$0.25/1M
Context
128K
Max Output
16K
DeepSeek V3.2 Thinking
nano-gpt
Input
$0.28/1M
Output
$0.42/1M
Context
163K
Max Output
66K
Deepseek R1
nano-gpt
Input
$1.00/1M
Output
$2.00/1M
Context
128K
Max Output
8K
MiniMax M2.1
nano-gpt
Input
$0.33/1M
Output
$1.32/1M
Context
200K
Max Output
131K
GPT OSS 120B
nano-gpt
Input
$0.05/1M
Output
$0.25/1M
Context
128K
Max Output
16K
GLM 4.6 Thinking
nano-gpt
Input
$0.40/1M
Output
$1.50/1M
Context
200K
Max Output
66K
GLM 4.6
nano-gpt
Input
$0.40/1M
Output
$1.50/1M
Context
200K
Max Output
66K
Qwen3 Coder
nano-gpt
Input
$1.00/1M
Output
$2.00/1M
Context
106K
Max Output
8K
Qwen3 235B A22B Thinking 2507
nano-gpt
Input
$1.00/1M
Output
$2.00/1M
Context
262K
Max Output
8K
Devstral 2 123B
nano-gpt
Input
$0.40/1M
Output
$1.40/1M
Context
262K
Max Output
66K
Mistral Large 3 675B
nano-gpt
Input
$1.00/1M
Output
$3.00/1M
Context
262K
Max Output
256K
Ministral 3 14B
nano-gpt
Input
$0.10/1M
Output
$0.40/1M
Context
262K
Max Output
33K