NovitaAI

[PROVIDER]
id: novita-ai
npm: @ai-sdk/openai-compatible
env: NOVITA_API_KEY
api: https://api.novita.ai/openai

Models

AutoGLM-Phone-9B-Multilingual

zai-org/autoglm-phone-9b-multilingual
in $0.04/M
out $0.14/M
ctx: 65,536 max out: 65,536 in: text, image out: text
reasoning tools vision structured temp open weights

baichuan-m2-32b

baichuan/baichuan-m2-32b
in $0.07/M
out $0.07/M
ctx: 131,072 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

Deepseek Prover V2 671B

deepseek/deepseek-prover-v2-671b
in $0.70/M
out $2.50/M
ctx: 160,000 max out: 160,000 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek R1 (Turbo)

deepseek/deepseek-r1-turbo
in $0.70/M
out $2.50/M
ctx: 64,000 max out: 16,000 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek R1 0528

deepseek/deepseek-r1-0528
in $0.70/M
out $2.50/M
cache read $0.35/M
ctx: 163,840 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek R1 0528 Qwen3 8B

deepseek/deepseek-r1-0528-qwen3-8b
in $0.06/M
out $0.09/M
ctx: 128,000 max out: 32,000 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek R1 Distill LLama 70B

deepseek/deepseek-r1-distill-llama-70b
in $0.80/M
out $0.80/M
ctx: 8,192 max out: 8,192 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek R1 Distill Qwen 14B

deepseek/deepseek-r1-distill-qwen-14b
in $0.15/M
out $0.15/M
ctx: 32,768 max out: 16,384 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek R1 Distill Qwen 32B

deepseek/deepseek-r1-distill-qwen-32b
in $0.30/M
out $0.30/M
ctx: 64,000 max out: 32,000 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek V3 (Turbo)

deepseek/deepseek-v3-turbo
in $0.40/M
out $1.30/M
ctx: 64,000 max out: 16,000 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek V3 0324

deepseek/deepseek-v3-0324
in $0.27/M
out $1.12/M
cache read $0.14/M
ctx: 163,840 max out: 163,840 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek V3.1

deepseek/deepseek-v3.1
in $0.27/M
out $1.00/M
cache read $0.14/M
ctx: 131,072 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Deepseek V3.1 Terminus

deepseek/deepseek-v3.1-terminus
in $0.27/M
out $1.00/M
cache read $0.14/M
ctx: 131,072 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Deepseek V3.2

deepseek/deepseek-v3.2
in $0.27/M
out $0.40/M
cache read $0.13/M
ctx: 163,840 max out: 65,536 in: text out: text
reasoning tools vision structured temp open weights

Deepseek V3.2 Exp

deepseek/deepseek-v3.2-exp
in $0.27/M
out $0.41/M
ctx: 163,840 max out: 65,536 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek V4 Flash

deepseek/deepseek-v4-flash
in $0.14/M
out $0.28/M
cache read $0.03/M
ctx: 1,048,576 max out: 393,216 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek V4 Pro

deepseek/deepseek-v4-pro
in $1.69/M
out $3.38/M
cache read $0.13/M
ctx: 1,048,576 max out: 393,216 in: text out: text
reasoning tools vision structured temp open weights

DeepSeek-OCR

deepseek/deepseek-ocr
in $0.03/M
out $0.03/M
ctx: 8,192 max out: 8,192 in: text, image out: text
reasoning tools vision structured temp open weights

deepseek/deepseek-ocr-2

deepseek/deepseek-ocr-2
in $0.03/M
out $0.03/M
ctx: 8,192 max out: 8,192 in: text, image out: text
reasoning tools vision structured temp open weights

ERNIE 4.5 21B A3B

baidu/ernie-4.5-21B-a3b
in $0.07/M
out $0.28/M
ctx: 120,000 max out: 8,000 in: text out: text
reasoning tools vision structured temp open weights

ERNIE 4.5 300B A47B

baidu/ernie-4.5-300b-a47b-paddle
in $0.28/M
out $1.10/M
ctx: 123,000 max out: 12,000 in: text out: text
reasoning tools vision structured temp open weights

ERNIE 4.5 VL 28B A3B

baidu/ernie-4.5-vl-28b-a3b
in $0.14/M
out $0.56/M
ctx: 30,000 max out: 8,000 in: text, image out: text
reasoning tools vision structured temp open weights

ERNIE 4.5 VL 424B A47B

baidu/ernie-4.5-vl-424b-a47b
in $0.42/M
out $1.25/M
ctx: 123,000 max out: 16,000 in: text, image out: text
reasoning tools vision structured temp open weights

ERNIE-4.5-21B-A3B-Thinking

baidu/ernie-4.5-21B-a3b-thinking
in $0.07/M
out $0.28/M
ctx: 131,072 max out: 65,536 in: text out: text
reasoning tools vision structured temp open weights

ERNIE-4.5-VL-28B-A3B-Thinking

baidu/ernie-4.5-vl-28b-a3b-thinking
in $0.39/M
out $0.39/M
ctx: 131,072 max out: 65,536 in: text, image, video out: text
reasoning tools vision structured temp open weights

Gemma 3 12B

google/gemma-3-12b-it
in $0.05/M
out $0.10/M
ctx: 131,072 max out: 8,192 in: text, image out: text
reasoning tools vision structured temp open weights

Gemma 3 27B

google/gemma-3-27b-it
in $0.12/M
out $0.20/M
ctx: 98,304 max out: 16,384 in: text, image out: text
reasoning tools vision structured temp open weights

Gemma 4 26B A4B

google/gemma-4-26b-a4b-it
in $0.13/M
out $0.40/M
ctx: 262,144 max out: 131,072 in: text, image out: text
reasoning tools vision structured temp open weights

Gemma 4 31B

google/gemma-4-31b-it
in $0.14/M
out $0.40/M
ctx: 262,144 max out: 131,072 in: text, image out: text
reasoning tools vision structured temp open weights

GLM 4.5 Air

zai-org/glm-4.5-air
in $0.13/M
out $0.85/M
ctx: 131,072 max out: 98,304 in: text out: text
reasoning tools vision structured temp open weights

GLM 4.5V

zai-org/glm-4.5v
in $0.60/M
out $1.80/M
cache read $0.11/M
ctx: 65,536 max out: 16,384 in: text, video, image out: text
reasoning tools vision structured temp open weights

GLM 4.6

zai-org/glm-4.6
in $0.55/M
out $2.20/M
cache read $0.11/M
ctx: 204,800 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

GLM 4.6V

zai-org/glm-4.6v
in $0.30/M
out $0.90/M
cache read $0.06/M
ctx: 131,072 max out: 32,768 in: text, video, image out: text
reasoning tools vision structured temp open weights

GLM-4.5

zai-org/glm-4.5
in $0.60/M
out $2.20/M
cache read $0.11/M
ctx: 131,072 max out: 98,304 in: text out: text
reasoning tools vision structured temp open weights

GLM-4.7

zai-org/glm-4.7
in $0.60/M
out $2.20/M
cache read $0.11/M
ctx: 204,800 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

GLM-4.7-Flash

zai-org/glm-4.7-flash
in $0.07/M
out $0.40/M
cache read $0.01/M
ctx: 200,000 max out: 128,000 in: text out: text
reasoning tools vision structured temp open weights

GLM-5

zai-org/glm-5
in $1.00/M
out $3.20/M
cache read $0.20/M
ctx: 202,800 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

GLM-5.1

zai-org/glm-5.1
in $1.40/M
out $4.40/M
cache read $0.26/M
ctx: 204,800 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

GLM-5.2

zai-org/glm-5.2
in $1.40/M
out $4.40/M
cache read $0.26/M
ctx: 1,048,576 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

Hermes 2 Pro Llama 3 8B

nousresearch/hermes-2-pro-llama-3-8b
in $0.14/M
out $0.14/M
ctx: 8,192 max out: 8,192 in: text out: text
reasoning tools vision structured temp open weights

Kat Coder Pro

kwaipilot/kat-coder-pro
in $0.30/M
out $1.20/M
cache read $0.06/M
ctx: 256,000 max out: 128,000 in: text out: text
reasoning tools vision structured temp open weights

Kimi K2 0905

moonshotai/kimi-k2-0905
in $0.60/M
out $2.50/M
ctx: 262,144 max out: 262,144 in: text out: text
reasoning tools vision structured temp open weights

Kimi K2 Instruct

moonshotai/kimi-k2-instruct
in $0.57/M
out $2.30/M
ctx: 131,072 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Kimi K2 Thinking

moonshotai/kimi-k2-thinking
in $0.60/M
out $2.50/M
ctx: 262,144 max out: 262,144 in: text out: text
reasoning tools vision structured temp open weights

Kimi K2.5

moonshotai/kimi-k2.5
in $0.60/M
out $3.00/M
cache read $0.10/M
ctx: 262,144 max out: 262,144 in: text, image, video out: text
reasoning tools vision structured temp open weights

Kimi K2.6

moonshotai/kimi-k2.6
in $0.95/M
out $4.00/M
cache read $0.16/M
ctx: 262,144 max out: 262,144 in: text, image, video out: text
reasoning tools vision structured temp open weights

L3 70B Euryale V2.1

sao10K/l3-70b-euryale-v2.1
in $1.48/M
out $1.48/M
ctx: 8,192 max out: 8,192 in: text out: text
reasoning tools vision structured temp open weights

L3 8B Stheno V3.2

sao10K/L3-8B-stheno-v3.2
in $0.05/M
out $0.05/M
ctx: 8,192 max out: 32,000 in: text out: text
reasoning tools vision structured temp open weights

L31 70B Euryale V2.2

sao10K/l31-70b-euryale-v2.2
in $1.48/M
out $1.48/M
ctx: 8,192 max out: 8,192 in: text out: text
reasoning tools vision structured temp open weights

Ling-2.6-1T

inclusionai/ling-2.6-1t
in $0.00/M
out $0.00/M
ctx: 262,144 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Ling-2.6-flash

inclusionai/ling-2.6-flash
in $0.10/M
out $0.30/M
cache read $0.02/M
ctx: 262,144 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Llama 3 8B Instruct

meta-llama/llama-3-8b-instruct
in $0.04/M
out $0.04/M
ctx: 8,192 max out: 8,192 in: text out: text
reasoning tools vision structured temp open weights

Llama 3.1 8B Instruct

meta-llama/llama-3.1-8b-instruct
in $0.02/M
out $0.05/M
ctx: 16,384 max out: 16,384 in: text out: text
reasoning tools vision structured temp open weights

Llama 3.2 3B Instruct

meta-llama/llama-3.2-3b-instruct
in $0.03/M
out $0.05/M
ctx: 32,768 max out: 32,000 in: text out: text
reasoning tools vision structured temp open weights

Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct
in $0.14/M
out $0.40/M
ctx: 131,072 max out: 120,000 in: text out: text
reasoning tools vision structured temp open weights

Llama 4 Maverick Instruct

meta-llama/llama-4-maverick-17b-128e-instruct-fp8
in $0.27/M
out $0.85/M
ctx: 1,048,576 max out: 8,192 in: text, image out: text
reasoning tools vision structured temp open weights

Llama 4 Scout Instruct

meta-llama/llama-4-scout-17b-16e-instruct
in $0.18/M
out $0.59/M
ctx: 131,072 max out: 131,072 in: text, image out: text
reasoning tools vision structured temp open weights

Llama3 70B Instruct

meta-llama/llama-3-70b-instruct
in $0.51/M
out $0.74/M
ctx: 8,192 max out: 8,000 in: text out: text
reasoning tools vision structured temp open weights

MiMo-V2-Pro

xiaomimimo/mimo-v2-pro
in $2.00/M
out $6.00/M
cache read $0.40/M
ctx: 1,048,576 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

MiMo-V2.5-Pro

xiaomimimo/mimo-v2.5-pro
in $2.00/M
out $6.00/M
cache read $0.40/M
ctx: 1,048,576 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

MiniMax M1

minimaxai/minimax-m1-80k
in $0.55/M
out $2.20/M
ctx: 1,000,000 max out: 40,000 in: text out: text
reasoning tools vision structured temp open weights

Minimax M2.1

minimax/minimax-m2.1
in $0.30/M
out $1.20/M
cache read $0.03/M
ctx: 204,800 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

MiniMax M2.5

minimax/minimax-m2.5
in $0.30/M
out $1.20/M
cache read $0.03/M
ctx: 204,800 max out: 131,100 in: text out: text
reasoning tools vision structured temp open weights

MiniMax M2.5 Highspeed

minimax/minimax-m2.5-highspeed
in $0.60/M
out $2.40/M
cache read $0.03/M
ctx: 204,800 max out: 131,100 in: text out: text
reasoning tools vision structured temp open weights

MiniMax M2.7

minimax/minimax-m2.7
in $0.30/M
out $1.20/M
cache read $0.06/M
ctx: 204,800 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

MiniMax-M2

minimax/minimax-m2
in $0.30/M
out $1.20/M
cache read $0.03/M
ctx: 204,800 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

MiniMax-M2.7-highspeed

minimax/minimax-m2.7-highspeed
in $0.60/M
out $2.40/M
cache read $0.06/M
cache write $0.38/M
ctx: 204,800 max out: 131,072 in: text out: text
reasoning tools vision structured temp open weights

Mistral Nemo

mistralai/mistral-nemo
in $0.04/M
out $0.17/M
ctx: 60,288 max out: 16,000 in: text out: text
reasoning tools vision structured temp open weights

Mythomax L2 13B

gryphe/mythomax-l2-13b
in $0.09/M
out $0.09/M
ctx: 4,096 max out: 3,200 in: text out: text
reasoning tools vision structured temp open weights

OpenAI GPT OSS 120B

openai/gpt-oss-120b
in $0.05/M
out $0.25/M
ctx: 131,072 max out: 32,768 in: text, image out: text
reasoning tools vision structured temp open weights

OpenAI: GPT OSS 20B

openai/gpt-oss-20b
in $0.04/M
out $0.15/M
ctx: 131,072 max out: 32,768 in: text, image out: text
reasoning tools vision structured temp open weights

PaddleOCR-VL

paddlepaddle/paddleocr-vl
in $0.02/M
out $0.02/M
ctx: 16,384 max out: 16,384 in: text, image out: text
reasoning tools vision structured temp open weights

Qwen 2.5 72B Instruct

qwen/qwen-2.5-72b-instruct
in $0.38/M
out $0.40/M
ctx: 32,000 max out: 8,192 in: text out: text
reasoning tools vision structured temp open weights

Qwen MT Plus

qwen/qwen-mt-plus
in $0.25/M
out $0.75/M
ctx: 16,384 max out: 8,192 in: text out: text
reasoning tools vision structured temp open weights

qwen/qwen3-vl-30b-a3b-instruct

qwen/qwen3-vl-30b-a3b-instruct
in $0.20/M
out $0.70/M
ctx: 131,072 max out: 32,768 in: text, video, image out: text
reasoning tools vision structured temp open weights

qwen/qwen3-vl-30b-a3b-thinking

qwen/qwen3-vl-30b-a3b-thinking
in $0.20/M
out $1.00/M
ctx: 131,072 max out: 32,768 in: text, image, video out: text
reasoning tools vision structured temp open weights

qwen/qwen3-vl-8b-instruct

qwen/qwen3-vl-8b-instruct
in $0.08/M
out $0.50/M
ctx: 131,072 max out: 32,768 in: text, image, video out: text
reasoning tools vision structured temp open weights

Qwen2.5 7B Instruct

qwen/qwen2.5-7b-instruct
in $0.07/M
out $0.07/M
ctx: 32,000 max out: 32,000 in: text out: text
reasoning tools vision structured temp open weights

Qwen2.5 VL 72B Instruct

qwen/qwen2.5-vl-72b-instruct
in $0.80/M
out $0.80/M
ctx: 32,768 max out: 32,768 in: text, image, video out: text
reasoning tools vision structured temp open weights

Qwen3 235B A22B

qwen/qwen3-235b-a22b-fp8
in $0.20/M
out $0.80/M
ctx: 40,960 max out: 20,000 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-instruct-2507
in $0.09/M
out $0.58/M
ctx: 131,072 max out: 16,384 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 235B A22b Thinking 2507

qwen/qwen3-235b-a22b-thinking-2507
in $0.30/M
out $3.00/M
ctx: 131,072 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 30B A3B

qwen/qwen3-30b-a3b-fp8
in $0.09/M
out $0.45/M
ctx: 40,960 max out: 20,000 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 32B

qwen/qwen3-32b-fp8
in $0.10/M
out $0.45/M
ctx: 40,960 max out: 20,000 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 4B

qwen/qwen3-4b-fp8
in $0.03/M
out $0.03/M
ctx: 128,000 max out: 20,000 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 8B

qwen/qwen3-8b-fp8
in $0.04/M
out $0.14/M
ctx: 128,000 max out: 20,000 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 Coder 30b A3B Instruct

qwen/qwen3-coder-30b-a3b-instruct
in $0.07/M
out $0.27/M
ctx: 160,000 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 Coder 480B A35B Instruct

qwen/qwen3-coder-480b-a35b-instruct
in $0.30/M
out $1.30/M
ctx: 262,144 max out: 65,536 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 Coder Next

qwen/qwen3-coder-next
in $0.20/M
out $1.50/M
ctx: 262,144 max out: 65,536 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 Max

qwen/qwen3-max
in $2.11/M
out $8.45/M
ctx: 262,144 max out: 65,536 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 Next 80B A3B Instruct

qwen/qwen3-next-80b-a3b-instruct
in $0.15/M
out $1.50/M
ctx: 131,072 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 Next 80B A3B Thinking

qwen/qwen3-next-80b-a3b-thinking
in $0.15/M
out $1.50/M
ctx: 131,072 max out: 32,768 in: text out: text
reasoning tools vision structured temp open weights

Qwen3 Omni 30B A3B Instruct

qwen/qwen3-omni-30b-a3b-instruct
in $0.25/M
out $0.97/M
ctx: 65,536 max out: 16,384 in: text, video, audio, image out: text, audio
reasoning tools vision structured temp open weights

Qwen3 Omni 30B A3B Thinking

qwen/qwen3-omni-30b-a3b-thinking
in $0.25/M
out $0.97/M
ctx: 65,536 max out: 16,384 in: text, audio, video, image out: text
reasoning tools vision structured temp open weights

Qwen3 VL 235B A22B Instruct

qwen/qwen3-vl-235b-a22b-instruct
in $0.30/M
out $1.50/M
ctx: 131,072 max out: 32,768 in: text, image, video out: text
reasoning tools vision structured temp open weights

Qwen3 VL 235B A22B Thinking

qwen/qwen3-vl-235b-a22b-thinking
in $0.98/M
out $3.95/M
ctx: 131,072 max out: 32,768 in: text, image, video out: text
reasoning tools vision structured temp open weights

Qwen3.5-122B-A10B

qwen/qwen3.5-122b-a10b
in $0.40/M
out $3.20/M
ctx: 262,144 max out: 65,536 in: text, image, video out: text
reasoning tools vision structured temp open weights

Qwen3.5-27B

qwen/qwen3.5-27b
in $0.30/M
out $2.40/M
ctx: 262,144 max out: 65,536 in: text, image, video out: text
reasoning tools vision structured temp open weights

Qwen3.5-35B-A3B

qwen/qwen3.5-35b-a3b
in $0.25/M
out $2.00/M
ctx: 262,144 max out: 65,536 in: text, image, video out: text
reasoning tools vision structured temp open weights

Qwen3.5-397B-A17B

qwen/qwen3.5-397b-a17b
in $0.60/M
out $3.60/M
ctx: 262,144 max out: 64,000 in: text, image, video out: text
reasoning tools vision structured temp open weights

Qwen3.7-Max

qwen/qwen3.7-max
in $1.25/M
out $3.75/M
cache read $0.13/M
cache write $1.56/M
ctx: 1,000,000 max out: 65,536 in: text out: text
reasoning tools vision structured temp open weights

Ring-2.6-1T

inclusionai/ring-2.6-1t
in $0.30/M
out $2.50/M
cache read $0.06/M
ctx: 262,144 max out: 65,536 in: text out: text
reasoning tools vision structured temp open weights

Sao10k L3 8B Lunaris

sao10K/l3-8b-lunaris
in $0.05/M
out $0.05/M
ctx: 8,192 max out: 8,192 in: text out: text
reasoning tools vision structured temp open weights

Wizardlm 2 8x22B

microsoft/wizardlm-2-8x22b
in $0.62/M
out $0.62/M
ctx: 65,535 max out: 8,000 in: text out: text
reasoning tools vision structured temp open weights

XiaomiMiMo/MiMo-V2-Flash

xiaomimimo/mimo-v2-flash
in $0.10/M
out $0.30/M
cache read $0.30/M
ctx: 262,144 max out: 32,000 in: text out: text
reasoning tools vision structured temp open weights