CoreWeave

Hybrid19 models hosted

Avg Price

$0.893/M

Range

$0.090-$2.90

Reasoning

With AA Score

Tier Breakdown

Standard

$0.415/M

2 models

$0.360 - $0.470

Budget

$1.74/M

7 models

$0.220 - $2.90

Micro

$0.394/M

10 models

$0.090 - $1.21

ZDR: Processor-role privacy policy; no inference ZDR/training claim located.

Model	Owner	Tier	Host	Quant	Input $/M	Output $/M	Blended $/M▲	Cost / IQ	SIT Score
OpenAI: gpt-oss-20bREASONING	OpenAI	Micro	-	fp4	$0.030	$0.130	$0.090	$0.464	N/A
OpenAI: gpt-oss-120bREASONING	OpenAI	Micro	-	fp4	$0.030	$0.170	$0.114	$1.45	N/A
IBM: Granite 4.2 8BREASONING	IBM Granite	Micro	-	bf16	$0.100	$0.150	$0.130	$0.549	N/A
NVIDIA: Nemotron 3.5 LightningREASONING	NVIDIA	Micro	-	bf16	$0.070	$0.200	$0.148	$0.414	N/A
DeepSeek: DeepSeek V4 Flash 0731REASONING	DeepSeek	Budget	-	fp8	$0.130	$0.280	$0.220	$0.302	N/A
Google: Gemma 4 26B A4B REASONING	Google	Micro	-	bf16	$0.100	$0.300	$0.220	$0.547	N/A
Meta: Llama 3.1 8B Instruct	Meta Llama	Micro	-	bf16	$0.220	$0.220	$0.220	$0.392	N/A
Google: Gemma 4 31BREASONING	Google	Micro	-	fp4	$0.100	$0.340	$0.244	$0.624	N/A
Z.ai: GLM 5.3 FlashREASONING	Z.ai	Standard	-	nvfp4	$0.150	$0.500	$0.360	$0.344	N/A
DeepSeek: DeepSeek V4.1 FlashREASONING	DeepSeek	Standard	-	fp8	$0.200	$0.650	$0.470	$0.711	N/A
MiniMax: MiniMax M3REASONING	MiniMax	Budget	-	fp4	$0.230	$0.960	$0.668	$1.15	N/A
Meta: Llama 3.3 70B Instruct	Meta Llama	Micro	-	fp16	$0.710	$0.710	$0.710	$3.71	N/A
Qwen: Qwen3.6 35B A3BREASONING	Qwen	Micro	-	fp8	$0.250	$1.25	$0.850	$1.43	N/A
DeepSeek: DeepSeek V3.1REASONING	DeepSeek	Micro	-	fp8	$0.550	$1.65	$1.21	$3.44	N/A
Z.ai: GLM 5.2REASONING	Z.ai	Budget	-	fp4	$0.760	$2.42	$1.76	$3.23	N/A
Qwen: Qwen3.8 27BREASONING	Qwen	Budget	-	fp8	$0.400	$3.00	$1.96	$1.96	N/A
MoonshotAI: Kimi K2.6REASONING	Moonshot AI	Budget	-	fp4	$0.650	$3.41	$2.31	$3.56	N/A
MoonshotAI: Kimi K2.7 CodeREASONING	Moonshot AI	Budget	-	int4	$0.710	$3.50	$2.38	$4.31	N/A
DeepSeek: DeepSeek V4 Pro 0813REASONING	DeepSeek	Budget	-	fp8	$1.31	$3.96	$2.90	$3.23	N/A