AI Model Catalog: 3012 Models Compared — Pricing, Context & Benchmarks

Novita: mistralai/mistral-nemo T

No provider description is available for this model yet.

novita/mistralai/mistral-nemo 60.288K context $0.04/M input $0.17/M output

Novita: qwen/qwen-2.5-72b-instruct T

No provider description is available for this model yet.

novita/qwen/qwen-2.5-72b-instruct 32K context $0.38/M input $0.4/M output

Vertex_Ai Ai21_Models: jamba-1.5 T

No provider description is available for this model yet.

vertex_ai-ai21_models/jamba-1.5 256K context $0.2/M input $0.4/M output

Novita: meta-llama/llama-3.3-70b-instruct T

No provider description is available for this model yet.

novita/meta-llama/llama-3.3-70b-instruct 131.072K context $0.135/M input $0.4/M output

Novita: deepseek/deepseek-r1-distill-qwen-14b T

No provider description is available for this model yet.

novita/deepseek/deepseek-r1-distill-qwen-14b 32.768K context $0.15/M input $0.15/M output

Vertex_Ai Deepseek_Models: deepseek-ai/deepseek-r1-0528-maas T

No provider description is available for this model yet.

vertex_ai-deepseek_models/deepseek-ai/deepseek-r1-0528-maas 65.336K context $1.35/M input $5.4/M output

Novita: minimaxai/minimax-m1-80k T

No provider description is available for this model yet.

novita/minimaxai/minimax-m1-80k 1M context $0.55/M input $2.2/M output

Novita: deepseek/deepseek-r1-0528 T

No provider description is available for this model yet.

novita/deepseek/deepseek-r1-0528 163.84K context $0.7/M input $2.5/M output

Novita: deepseek/deepseek-r1-distill-qwen-32b T

No provider description is available for this model yet.

novita/deepseek/deepseek-r1-distill-qwen-32b 64K context $0.3/M input $0.3/M output

Novita: microsoft/wizardlm-2-8x22b T

No provider description is available for this model yet.

novita/microsoft/wizardlm-2-8x22b 65.535K context $0.62/M input $0.62/M output

Novita: deepseek/deepseek-r1-0528-qwen3-8b T

No provider description is available for this model yet.

novita/deepseek/deepseek-r1-0528-qwen3-8b 128K context $0.06/M input $0.09/M output

Novita: qwen/qwen3-235b-a22b-fp8 T

No provider description is available for this model yet.

novita/qwen/qwen3-235b-a22b-fp8 40.96K context $0.2/M input $0.8/M output

Novita: meta-llama/llama-4-maverick-17b-128e-instruct-fp8 T

No provider description is available for this model yet.

novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 1.04858M context $0.27/M input $0.85/M output

Novita: meta-llama/llama-4-scout-17b-16e-instruct T

No provider description is available for this model yet.

novita/meta-llama/llama-4-scout-17b-16e-instruct 131.072K context $0.18/M input $0.59/M output

Novita: qwen/qwen2.5-vl-72b-instruct T

No provider description is available for this model yet.

novita/qwen/qwen2.5-vl-72b-instruct 32.768K context $0.8/M input $0.8/M output

Novita: baidu/ernie-4.5-21B-a3b-thinking T

No provider description is available for this model yet.

novita/baidu/ernie-4.5-21b-a3b-thinking 131.072K context $0.07/M input $0.28/M output

Novita: baichuan/baichuan-m2-32b T

No provider description is available for this model yet.

novita/baichuan/baichuan-m2-32b 131.072K context $0.07/M input $0.07/M output

Novita: baidu/ernie-4.5-vl-424b-a47b T

No provider description is available for this model yet.

novita/baidu/ernie-4.5-vl-424b-a47b 123K context $0.42/M input $1.25/M output

Novita: baidu/ernie-4.5-300b-a47b-paddle T

No provider description is available for this model yet.

novita/baidu/ernie-4.5-300b-a47b-paddle 123K context $0.28/M input $1.1/M output

Novita: deepseek/deepseek-prover-v2-671b T

No provider description is available for this model yet.

novita/deepseek/deepseek-prover-v2-671b 160K context $0.7/M input $2.5/M output

Novita: qwen/qwen3-32b-fp8 T

No provider description is available for this model yet.

novita/qwen/qwen3-32b-fp8 40.96K context $0.1/M input $0.45/M output

Novita: qwen/qwen3-30b-a3b-fp8 T

No provider description is available for this model yet.

novita/qwen/qwen3-30b-a3b-fp8 40.96K context $0.09/M input $0.45/M output

Novita: google/gemma-3-27b-it T

No provider description is available for this model yet.

novita/google/gemma-3-27b-it 98.304K context $0.119/M input $0.2/M output

Novita: deepseek/deepseek-v3-turbo T

No provider description is available for this model yet.

novita/deepseek/deepseek-v3-turbo 64K context $0.4/M input $1.3/M output

Novita: deepseek/deepseek-r1-turbo T

No provider description is available for this model yet.

novita/deepseek/deepseek-r1-turbo 64K context $0.7/M input $2.5/M output

Novita: baidu/ernie-4.5-vl-28b-a3b-thinking T

No provider description is available for this model yet.

novita/baidu/ernie-4.5-vl-28b-a3b-thinking 131.072K context $0.39/M input $0.39/M output

Novita: qwen/qwen3-vl-8b-instruct T

No provider description is available for this model yet.

novita/qwen/qwen3-vl-8b-instruct 131.072K context $0.08/M input $0.5/M output

Novita: zai-org/glm-4.5-air T

No provider description is available for this model yet.

novita/zai-org/glm-4.5-air 131.072K context $0.13/M input $0.85/M output

Novita: qwen/qwen3-vl-30b-a3b-instruct T

No provider description is available for this model yet.

novita/qwen/qwen3-vl-30b-a3b-instruct 131.072K context $0.2/M input $0.7/M output

Novita: qwen/qwen3-vl-30b-a3b-thinking T

No provider description is available for this model yet.

novita/qwen/qwen3-vl-30b-a3b-thinking 131.072K context $0.2/M input $1/M output

Novita: qwen/qwen3-omni-30b-a3b-thinking T

No provider description is available for this model yet.

novita/qwen/qwen3-omni-30b-a3b-thinking 65.536K context $0.25/M input $0.97/M output

Novita: qwen/qwen3-omni-30b-a3b-instruct T

No provider description is available for this model yet.

novita/qwen/qwen3-omni-30b-a3b-instruct 65.536K context $0.25/M input $0.97/M output

Novita: baidu/ernie-4.5-21B-a3b T

No provider description is available for this model yet.

novita/baidu/ernie-4.5-21b-a3b 120K context $0.07/M input $0.28/M output

Novita: qwen/qwen3-8b-fp8 T

No provider description is available for this model yet.

novita/qwen/qwen3-8b-fp8 128K context $0.035/M input $0.138/M output

Novita: qwen/qwen3-4b-fp8 T

No provider description is available for this model yet.

novita/qwen/qwen3-4b-fp8 128K context $0.03/M input $0.03/M output

Novita: qwen/qwen2.5-7b-instruct T

No provider description is available for this model yet.

novita/qwen/qwen2.5-7b-instruct 32K context $0.07/M input $0.07/M output

Novita: meta-llama/llama-3.2-3b-instruct T

No provider description is available for this model yet.

novita/meta-llama/llama-3.2-3b-instruct 32.768K context $0.03/M input $0.05/M output

Llamagate: llama-3.1-8b T

No provider description is available for this model yet.

llamagate/llama-3.1-8b 131.072K context $0.03/M input $0.05/M output

Llamagate: llama-3.2-3b T

No provider description is available for this model yet.

llamagate/llama-3.2-3b 131.072K context $0.04/M input $0.08/M output

Llamagate: mistral-7b-v0.3 T

No provider description is available for this model yet.

llamagate/mistral-7b-v0.3 32.768K context $0.1/M input $0.15/M output

Llamagate: qwen3-8b T

No provider description is available for this model yet.

llamagate/qwen3-8b 32.768K context $0.04/M input $0.14/M output

Llamagate: dolphin3-8b T

No provider description is available for this model yet.

llamagate/dolphin3-8b 128K context $0.08/M input $0.15/M output

Llamagate: deepseek-r1-8b T

No provider description is available for this model yet.

llamagate/deepseek-r1-8b 65.536K context $0.1/M input $0.2/M output

Llamagate: deepseek-r1-7b-qwen T

No provider description is available for this model yet.

llamagate/deepseek-r1-7b-qwen 131.072K context $0.08/M input $0.15/M output

Llamagate: openthinker-7b T

No provider description is available for this model yet.

llamagate/openthinker-7b 32.768K context $0.08/M input $0.15/M output

Llamagate: qwen2.5-coder-7b T

No provider description is available for this model yet.

llamagate/qwen2.5-coder-7b 32.768K context $0.06/M input $0.12/M output

Llamagate: qwen3-vl-8b T

No provider description is available for this model yet.

llamagate/qwen3-vl-8b 32.768K context $0.15/M input $0.55/M output

Llamagate: gemma3-4b T

No provider description is available for this model yet.

llamagate/gemma3-4b 128K context $0.03/M input $0.08/M output

Libertai: gemma-4-31b-it T

No provider description is available for this model yet.

libertai/gemma-4-31b-it 262.144K context $0.15/M input $0.4/M output

Bedrock_Converse: eu.deepseek.v3.2 T

No provider description is available for this model yet.

bedrock_converse/eu.deepseek.v3.2 163.84K context $0.74/M input $2.22/M output

Filterable model directory
Model	Creator	Inputs	Context	Input	Output	Released
mistralai/mistral-nemonovita/mistralai/mistral-nemo	Novita	T	60.288K	$0.04	$0.17	—
qwen/qwen-2.5-72b-instructnovita/qwen/qwen-2.5-72b-instruct	Novita	T	32K	$0.38	$0.4	—
jamba-1.5vertex_ai-ai21_models/jamba-1.5	Vertex_Ai Ai21_Models	T	256K	$0.2	$0.4	—
meta-llama/llama-3.3-70b-instructnovita/meta-llama/llama-3.3-70b-instruct	Novita	T	131.072K	$0.135	$0.4	—
deepseek/deepseek-r1-distill-qwen-14bnovita/deepseek/deepseek-r1-distill-qwen-14b	Novita	T	32.768K	$0.15	$0.15	—
deepseek-ai/deepseek-r1-0528-maasvertex_ai-deepseek_models/deepseek-ai/deepseek-r1-0528-maas	Vertex_Ai Deepseek_Models	T	65.336K	$1.35	$5.4	—
minimaxai/minimax-m1-80knovita/minimaxai/minimax-m1-80k	Novita	T	1M	$0.55	$2.2	—
deepseek/deepseek-r1-0528novita/deepseek/deepseek-r1-0528	Novita	T	163.84K	$0.7	$2.5	—
deepseek/deepseek-r1-distill-qwen-32bnovita/deepseek/deepseek-r1-distill-qwen-32b	Novita	T	64K	$0.3	$0.3	—
microsoft/wizardlm-2-8x22bnovita/microsoft/wizardlm-2-8x22b	Novita	T	65.535K	$0.62	$0.62	—
deepseek/deepseek-r1-0528-qwen3-8bnovita/deepseek/deepseek-r1-0528-qwen3-8b	Novita	T	128K	$0.06	$0.09	—
qwen/qwen3-235b-a22b-fp8novita/qwen/qwen3-235b-a22b-fp8	Novita	T	40.96K	$0.2	$0.8	—
meta-llama/llama-4-maverick-17b-128e-instruct-fp8novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8	Novita	T	1.04858M	$0.27	$0.85	—
meta-llama/llama-4-scout-17b-16e-instructnovita/meta-llama/llama-4-scout-17b-16e-instruct	Novita	T	131.072K	$0.18	$0.59	—
qwen/qwen2.5-vl-72b-instructnovita/qwen/qwen2.5-vl-72b-instruct	Novita	T	32.768K	$0.8	$0.8	—
baidu/ernie-4.5-21B-a3b-thinkingnovita/baidu/ernie-4.5-21b-a3b-thinking	Novita	T	131.072K	$0.07	$0.28	—
baichuan/baichuan-m2-32bnovita/baichuan/baichuan-m2-32b	Novita	T	131.072K	$0.07	$0.07	—
baidu/ernie-4.5-vl-424b-a47bnovita/baidu/ernie-4.5-vl-424b-a47b	Novita	T	123K	$0.42	$1.25	—
baidu/ernie-4.5-300b-a47b-paddlenovita/baidu/ernie-4.5-300b-a47b-paddle	Novita	T	123K	$0.28	$1.1	—
deepseek/deepseek-prover-v2-671bnovita/deepseek/deepseek-prover-v2-671b	Novita	T	160K	$0.7	$2.5	—
qwen/qwen3-32b-fp8novita/qwen/qwen3-32b-fp8	Novita	T	40.96K	$0.1	$0.45	—
qwen/qwen3-30b-a3b-fp8novita/qwen/qwen3-30b-a3b-fp8	Novita	T	40.96K	$0.09	$0.45	—
google/gemma-3-27b-itnovita/google/gemma-3-27b-it	Novita	T	98.304K	$0.119	$0.2	—
deepseek/deepseek-v3-turbonovita/deepseek/deepseek-v3-turbo	Novita	T	64K	$0.4	$1.3	—
deepseek/deepseek-r1-turbonovita/deepseek/deepseek-r1-turbo	Novita	T	64K	$0.7	$2.5	—
baidu/ernie-4.5-vl-28b-a3b-thinkingnovita/baidu/ernie-4.5-vl-28b-a3b-thinking	Novita	T	131.072K	$0.39	$0.39	—
qwen/qwen3-vl-8b-instructnovita/qwen/qwen3-vl-8b-instruct	Novita	T	131.072K	$0.08	$0.5	—
zai-org/glm-4.5-airnovita/zai-org/glm-4.5-air	Novita	T	131.072K	$0.13	$0.85	—
qwen/qwen3-vl-30b-a3b-instructnovita/qwen/qwen3-vl-30b-a3b-instruct	Novita	T	131.072K	$0.2	$0.7	—
qwen/qwen3-vl-30b-a3b-thinkingnovita/qwen/qwen3-vl-30b-a3b-thinking	Novita	T	131.072K	$0.2	$1	—
qwen/qwen3-omni-30b-a3b-thinkingnovita/qwen/qwen3-omni-30b-a3b-thinking	Novita	T	65.536K	$0.25	$0.97	—
qwen/qwen3-omni-30b-a3b-instructnovita/qwen/qwen3-omni-30b-a3b-instruct	Novita	T	65.536K	$0.25	$0.97	—
baidu/ernie-4.5-21B-a3bnovita/baidu/ernie-4.5-21b-a3b	Novita	T	120K	$0.07	$0.28	—
qwen/qwen3-8b-fp8novita/qwen/qwen3-8b-fp8	Novita	T	128K	$0.035	$0.138	—
qwen/qwen3-4b-fp8novita/qwen/qwen3-4b-fp8	Novita	T	128K	$0.03	$0.03	—
qwen/qwen2.5-7b-instructnovita/qwen/qwen2.5-7b-instruct	Novita	T	32K	$0.07	$0.07	—
meta-llama/llama-3.2-3b-instructnovita/meta-llama/llama-3.2-3b-instruct	Novita	T	32.768K	$0.03	$0.05	—
llama-3.1-8bllamagate/llama-3.1-8b	Llamagate	T	131.072K	$0.03	$0.05	—
llama-3.2-3bllamagate/llama-3.2-3b	Llamagate	T	131.072K	$0.04	$0.08	—
mistral-7b-v0.3llamagate/mistral-7b-v0.3	Llamagate	T	32.768K	$0.1	$0.15	—
qwen3-8bllamagate/qwen3-8b	Llamagate	T	32.768K	$0.04	$0.14	—
dolphin3-8bllamagate/dolphin3-8b	Llamagate	T	128K	$0.08	$0.15	—
deepseek-r1-8bllamagate/deepseek-r1-8b	Llamagate	T	65.536K	$0.1	$0.2	—
deepseek-r1-7b-qwenllamagate/deepseek-r1-7b-qwen	Llamagate	T	131.072K	$0.08	$0.15	—
openthinker-7bllamagate/openthinker-7b	Llamagate	T	32.768K	$0.08	$0.15	—
qwen2.5-coder-7bllamagate/qwen2.5-coder-7b	Llamagate	T	32.768K	$0.06	$0.12	—
qwen3-vl-8bllamagate/qwen3-vl-8b	Llamagate	T	32.768K	$0.15	$0.55	—
gemma3-4bllamagate/gemma3-4b	Llamagate	T	128K	$0.03	$0.08	—
gemma-4-31b-itlibertai/gemma-4-31b-it	Libertai	T	262.144K	$0.15	$0.4	—
eu.deepseek.v3.2bedrock_converse/eu.deepseek.v3.2	Bedrock_Converse	T	163.84K	$0.74	$2.22	—