AI Model APIs
Browse and compare prices and capabilities for 2,260+ AI models from 80+ API providers
MiniMax-M2.5
cortecs
Input
$0.32/1M
Output
$1.18/1M
Context
197K
Max Output
197K
MiniMax M2.7
nano-gpt
Input
$0.30/1M
Output
$1.20/1M
Context
205K
Max Output
131K
Grok 4.20 Multi-Agent
xai
Input
$2.00/1M
Output
$6.00/1M
Context
2.0M
Max Output
30K
Grok 4.20 (Reasoning)
xai
Input
$2.00/1M
Output
$6.00/1M
Context
2.0M
Max Output
30K
Grok 4.20 (Non-Reasoning)
xai
Input
$2.00/1M
Output
$6.00/1M
Context
2.0M
Max Output
30K
Nemotron 3 Super
nvidia
Input
$0.20/1M
Output
$0.80/1M
Context
262K
Max Output
262K
GLM-5
fastrouter
Input
$0.95/1M
Output
$3.15/1M
Context
205K
Max Output
131K
MiniMax M2.5
amazon-bedrock
Input
$0.30/1M
Output
$1.20/1M
Context
197K
Max Output
98K
GLM-5
amazon-bedrock
Input
$1.00/1M
Output
$3.20/1M
Context
203K
Max Output
101K
Kimi K2.5 Turbo
fireworks-ai
Input
Free/1M
Output
Free/1M
Context
256K
Max Output
256K
Nemotron 3 Super
openrouter
Input
$0.10/1M
Output
$0.50/1M
Context
262K
Max Output
262K
Nemotron 3 Super (free)
openrouter
Input
Free/1M
Output
Free/1M
Context
262K
Max Output
262K
Gemini Embedding 2
vercel
Input
Free/1M
Output
Free/1M
Context
N/A
Max Output
N/A
Grok 4.20 Non-Reasoning
vercel
Input
$2.00/1M
Output
$6.00/1M
Context
2.0M
Max Output
2.0M
Grok 4.20 Reasoning
vercel
Input
$2.00/1M
Output
$6.00/1M
Context
2.0M
Max Output
2.0M
Grok 4.20 Multi-Agent
vercel
Input
$2.00/1M
Output
$6.00/1M
Context
2.0M
Max Output
2.0M
Nemotron 3 Super
baseten
Input
$0.30/1M
Output
$0.75/1M
Context
262K
Max Output
33K
Claude Opus 4.6
cortecs
Input
$5.98/1M
Output
$29.89/1M
Context
1.0M
Max Output
1.0M
Claude Sonnet 4.6
cortecs
Input
$3.59/1M
Output
$17.92/1M
Context
1.0M
Max Output
1.0M
Claude Haiku 4.5
cortecs
Input
$1.09/1M
Output
$5.43/1M
Context
200K
Max Output
200K
Claude Opus 4.5
cortecs
Input
$5.98/1M
Output
$29.89/1M
Context
200K
Max Output
200K
GPT-5.4-Nano
poe
Input
$0.18/1M
Output
$1.10/1M
Context
400K
Max Output
128K
GPT-5.4-Mini
poe
Input
$0.68/1M
Output
$4.00/1M
Context
400K
Max Output
128K
Agentic Chat (GPT-5.3 Codex)
gitlab
Input
Free/1M
Output
Free/1M
Context
400K
Max Output
128K
Agentic Chat (GPT-5.4 Nano)
gitlab
Input
Free/1M
Output
Free/1M
Context
400K
Max Output
128K
Agentic Chat (GPT-5.4 Mini)
gitlab
Input
Free/1M
Output
Free/1M
Context
400K
Max Output
128K
Agentic Chat (GPT-5.4)
gitlab
Input
Free/1M
Output
Free/1M
Context
1.1M
Max Output
128K