DeepInfra

Models via DeepInfra

Model	Input/1M	Output/1M	Context	Score
Qwen3 235B A22B Alibaba	$0.20	$0.60	128K	0.9
GLM-4.5 Zhipu AI	$0.40	$1.60	131K	0.8
DeepSeek-V3.1 DeepSeek	$0.27	$1.00	164K	0.8
Llama 3.3 70B Instruct Meta	$0.23	$0.40	128K	0.8
Llama 3.1 405B Instruct Meta	$1.79	$1.79	128K	0.8
Qwen2.5 72B Instruct Alibaba	$0.35	$0.40	131K	0.8
DeepSeek R1 Distill Llama 70B DeepSeek	$0.10	$0.40	128K	0.8
Qwen3 32B Alibaba	$0.10	$0.30	128K	0.8
Llama 3.1 70B Instruct Meta	$0.35	$0.40	128K	0.7
DeepSeek R1 Distill Qwen 32B DeepSeek	$0.12	$0.18	128K	0.7
DeepSeek-R1 DeepSeek	$0.85	$2.50	131K	0.7
Qwen3 30B A3B Alibaba	$0.10	$0.30	128K	0.7
Phi-4-multimodal-instruct Microsoft	$0.05	$0.10	128K	0.7
Llama 4 Maverick Meta	$0.17	$0.60	1.0M	0.7
Mistral Small 3 24B Instruct Mistral AI	$0.07	$0.14	32K	0.7
Llama 3.2 90B Instruct Meta	$0.35	$0.40	128K	0.7
DeepSeek-V2.5 DeepSeek	$0.70	$1.40	8K	0.7
DeepSeek-R1-0528 DeepSeek	$0.50	$2.15	131K	0.7
Nemotron 3 Nano (30B A3B) NVIDIA	$0.06	$0.24	262K	0.7
Llama 4 Scout Meta	$0.08	$0.30	10.0M	0.7
Phi 4 Microsoft	$0.07	$0.14	16K	0.7
Gemma 3 27B Google	$0.10	$0.20	131K	0.7
Qwen2.5-Coder 32B Instruct Alibaba	$0.18	$0.18	128K	0.6
QwQ-32B-Preview Alibaba	$0.15	$0.60	33K	0.6
Llama 3.2 11B Instruct Meta	$0.05	$0.05	128K	0.6
Gemma 3 12B Google	$0.05	$0.10	131K	0.6
Llama 3.1 8B Instruct Meta	$0.05	$0.05	131K	0.6
GLM-4.6 Zhipu AI	$0.60	$2.00	131K	0.6
Llama 3.2 3B Instruct Meta	$0.01	$0.02	128K	0.6
Gemma 3 4B Google	$0.02	$0.04	131K	0.5
GPT OSS 120B OpenAI	$0.09	$0.45	131K	0.5