Try Bifrost Enterprise free for 14 days.
Request access
[ LLM COST CALCULATOR ]

Calculate LLM API Costs

Compare pricing across hundreds of AI models. Calculate costs for chat, image generation, audio transcription, and more.

[ OUR NUMBERS AT A GLANCE ]

Models
4,079
Providers
77
Modes
11

Browse by Provider

View all models from a specific provider

Loading providers...

All Models

Click on any model to calculate costs for your specific use case

Showing 100 of 4079 models
Model Name
Provider
Mode
Input
Output
Capabilities
claude-opus-4-8
deepinfra/anthropic/claude-opus-4-8
DeepInfraChat$5.00$25.00
FunctionsVisionReasoning
claude-opus-5
deepinfra/anthropic/claude-opus-5
DeepInfraChat$5.00$25.00
FunctionsVisionReasoning
claude-sonnet-4-6
deepinfra/anthropic/claude-sonnet-4-6
DeepInfraChat$3.00$15.00
FunctionsVisionReasoning
cobuddy
novita/baidu/cobuddy
NovitaChat$0.28$1.13
FunctionsReasoning
community
novita/deepseek/deepseek-v3/community
NovitaChat$0.89$0.89
Functions
community
novita/deepseek/deepseek-r1/community
NovitaChat$4.00$4.00
FunctionsReasoning
deepseek_v3
novita/deepseek/deepseek_v3
NovitaChat$0.89$0.89
Functions
deepseek-ocr-2
novita/deepseek/deepseek-ocr-2
NovitaChat$0.03$0.03
Vision
deepseek-r1
novita/deepseek/deepseek-r1
NovitaChat$4.00$4.00
FunctionsReasoning
deepseek-v4-flash
novita/deepseek/deepseek-v4-flash
NovitaChat$0.14$0.28
FunctionsReasoning
DeepSeek-V4-Flash
wandb/deepseek-ai/DeepSeek-V4-Flash
WandbChat$0.14$0.28
Reasoning
deepseek-v4-flash-0731
novita/deepseek/deepseek-v4-flash-0731
NovitaChat$0.44$1.32
FunctionsReasoning
DeepSeek-V4-Flash-0731
wandb/deepseek-ai/DeepSeek-V4-Flash-0731
WandbChat$0.13$0.28
Reasoning
deepseek-v4-flash-vision-exp
novita/deepseek/deepseek-v4-flash-vision-exp
NovitaChat$0.44$1.32
FunctionsVisionReasoning
deepseek-v4-pro
novita/deepseek/deepseek-v4-pro
NovitaChat$1.60$3.20
FunctionsReasoning
DeepSeek-V4-Pro
wandb/deepseek-ai/DeepSeek-V4-Pro
WandbChat$1.15$2.55
Reasoning
deepseek-v4-pro-0813
novita/deepseek/deepseek-v4-pro-0813
NovitaChat$1.32$3.96
FunctionsReasoning
DeepSeek-V4-Pro-0813
wandb/deepseek-ai/DeepSeek-V4-Pro-0813
WandbChat$1.31$3.96
Reasoning
DeepSeek-V4-Pro-0813
deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813
DeepInfraChat$1.30$2.60
Functions
gemini-3.5-flash
deepinfra/google/gemini-3.5-flash
DeepInfraChat$1.50$9.00
FunctionsVisionReasoning
gemma-4-26b-a4b-it
novita/google/gemma-4-26b-a4b-it
NovitaChat$0.13$0.40
FunctionsVisionReasoning
gemma-4-31b-it
novita/google/gemma-4-31b-it
NovitaChat$0.14$0.40
FunctionsVisionReasoning
gemma-4-31B-it
wandb/google/gemma-4-31B-it
WandbChat$0.10$0.34
VisionReasoning
gemma-4-31B-it-turbo
deepinfra/google/gemma-4-31B-it-turbo
DeepInfraChat$0.12$0.37
FunctionsVisionReasoning
gemma-4-31B-it-Ultra
deepinfra/google/gemma-4-31B-it-Ultra
DeepInfraChat$0.27$0.76
FunctionsVisionReasoning
glm-4-32b-0414
novita/thudm/glm-4-32b-0414
NovitaChat$0.55$1.66
Functions
GLM-4.6
deepinfra/zai-org/GLM-4.6
DeepInfraChat$0.43$1.74
FunctionsReasoning
glm-4.7-flash
novita/zai-org/glm-4.7-flash
NovitaChat$0.07$0.40
FunctionsReasoning
GLM-4.7-Flash
deepinfra/zai-org/GLM-4.7-Flash
DeepInfraChat$0.06$0.40
FunctionsReasoning
glm-4.7-h
novita/zai-org/glm-4.7-h
NovitaChat$0.60$2.20
FunctionsReasoning
glm-5
novita/zai-org/glm-5
NovitaChat$1.00$3.20
FunctionsReasoning
glm-5-turbo
novita/zai-org/glm-5-turbo
NovitaChat$1.20$4.00
FunctionsReasoning
glm-5.1
novita/zai-org/glm-5.1
NovitaChat$1.38$4.40
FunctionsReasoning
glm-5.2
novita/zai-org/glm-5.2
NovitaChat$1.40$4.40
FunctionsReasoning
GLM-5.2
wandb/zai-org/GLM-5.2
WandbChat$0.76$2.42
Reasoning
glm-5.3
novita/zai-org/glm-5.3
NovitaChat$1.40$4.40
FunctionsReasoning
glm-5v-turbo
novita/zai-org/glm-5v-turbo
NovitaChat$1.20$4.00
FunctionsVisionReasoning
gpt-oss-120b-Turbo
deepinfra/openai/gpt-oss-120b-Turbo
DeepInfraChat$0.15$0.60
FunctionsReasoning
granite-4.1-8b
wandb/ibm-granite/granite-4.1-8b
WandbChat$0.05$0.10
granite-4.2-8b
wandb/ibm-granite/granite-4.2-8b
WandbChat$0.10$0.15
Reasoning
hy3
novita/tencent/hy3
NovitaChat$0.14$0.58
FunctionsReasoning
Inkling
deepinfra/thinkingmachines/Inkling
DeepInfraChat$0.95$4.05
FunctionsVisionReasoning
Inkling-Small
deepinfra/thinkingmachines/Inkling-Small
DeepInfraChat$0.45$1.20
FunctionsVisionReasoning
kimi-k2.5
novita/moonshotai/kimi-k2.5
NovitaChat$0.60$3.00
FunctionsVisionReasoning
Kimi-K2.5
deepinfra/moonshotai/Kimi-K2.5
DeepInfraChat$0.45$2.25
FunctionsVisionReasoning
kimi-k2.6
novita/moonshotai/kimi-k2.6
NovitaChat$0.80$3.40
FunctionsVisionReasoning
Kimi-K2.6
wandb/moonshotai/Kimi-K2.6
WandbChat$0.65$3.41
VisionReasoning
Kimi-K2.6
deepinfra/moonshotai/Kimi-K2.6
DeepInfraChat$0.75$3.50
FunctionsVisionReasoning
kimi-k2.7-code
novita/moonshotai/kimi-k2.7-code
NovitaChat$0.95$4.00
FunctionsVisionReasoning
Kimi-K2.7-Code
wandb/moonshotai/Kimi-K2.7-Code
WandbChat$0.71$3.50
VisionReasoning
kimi-k3
novita/moonshotai/kimi-k3
NovitaChat$3.00$15.00
FunctionsVisionReasoning
kimi-k3-fast
fireworks_ai/accounts/fireworks/routers/kimi-k3-fast
Fireworks AIChat$4.50$22.50
FunctionsVisionReasoning
kimi-k3-us
fireworks_ai/accounts/fireworks/routers/kimi-k3-us
Fireworks AIChat$3.30$16.50
FunctionsVisionReasoning
ling-3.0-flash
novita/inclusionai/ling-3.0-flash
NovitaChat$0.06$0.18
FunctionsReasoning
ling-3.0-flash-fast
novita/inclusionai/ling-3.0-flash-fast
NovitaChat$0.06$0.18
FunctionsReasoning
Llama-3.1-70B-Instruct
wandb/meta-llama/Llama-3.1-70B-Instruct
WandbChat$0.80$0.80
llama-3.2-1b-instruct
novita/meta-llama/llama-3.2-1b-instruct
NovitaChat$0.02$0.02
macaron-v1-tall
novita/mindai/macaron-v1-tall
NovitaChat$0.45$2.60
FunctionsReasoning
macaron-v1-venti
novita/mindai/macaron-v1-venti
NovitaChat$1.50$4.50
FunctionsReasoning
Mellum2-12B-A2.5B-Instruct
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
WandbChat$0.05$0.10
mimo-v2.5
novita/xiaomimimo/mimo-v2.5
NovitaChat$0.17$0.34
FunctionsVisionReasoning
MiMo-V2.5
deepinfra/XiaomiMiMo/MiMo-V2.5
DeepInfraChat$0.14$0.28
FunctionsVisionReasoning
mimo-v2.5-pro
novita/xiaomimimo/mimo-v2.5-pro
NovitaChat$0.52$1.04
FunctionsReasoning
minimax-m2.5
novita/minimax/minimax-m2.5
NovitaChat$0.30$1.20
FunctionsReasoning
minimax-m2.5-highspeed
novita/minimax/minimax-m2.5-highspeed
NovitaChat$0.60$2.40
FunctionsReasoning
minimax-m2.7
novita/minimax/minimax-m2.7
NovitaChat$0.30$1.20
FunctionsReasoning
MiniMax-M2.7
deepinfra/MiniMaxAI/MiniMax-M2.7
DeepInfraChat$0.25$1.00
FunctionsReasoning
minimax-m2.7-highspeed
novita/minimax/minimax-m2.7-highspeed
NovitaChat$0.60$2.40
FunctionsReasoning
minimax-m3
novita/minimax/minimax-m3
NovitaChat$0.30$1.20
FunctionsVisionReasoning
MiniMax-M3
wandb/MiniMaxAI/MiniMax-M3
WandbChat$0.23$0.96
VisionReasoning
Muse-Glimmer-30B
deepinfra/meta-models/Muse-Glimmer-30B
DeepInfraChat$0.30$1.20
FunctionsVisionReasoning
nemotron-3-nano-30b-a3b
novita/nvidia/nemotron-3-nano-30b-a3b
NovitaChat$0.05$0.20
FunctionsReasoning
Nemotron-Content-Safety-3.5
deepinfra/nvidia/Nemotron-Content-Safety-3.5
DeepInfraChat$0.20$0.20
Vision
NVIDIA-Nemotron-3-Ultra-550B-A55B
wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
WandbChat$0.50$2.15
Reasoning
NVIDIA-Nemotron-3.5-Lightning-30B-A3B
wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
WandbChat$0.07$0.20
Reasoning
Qwen3-14B-Instruct
wandb/OpenPipe/Qwen3-14B-Instruct
WandbChat$0.05$0.22
Qwen3-30B-A3B-Instruct-2507
wandb/Qwen/Qwen3-30B-A3B-Instruct-2507
WandbChat$0.10$0.30
qwen3-coder-next
novita/qwen/qwen3-coder-next
NovitaChat$0.20$1.50
Functions
Qwen3-Max
deepinfra/Qwen/Qwen3-Max
DeepInfraChat$1.20$6.00
Functions
Qwen3-Max-Thinking
deepinfra/Qwen/Qwen3-Max-Thinking
DeepInfraChat$1.20$6.00
Functions
Qwen3-VL-235B-A22B-Instruct
deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct
DeepInfraChat$0.20$0.88
FunctionsVision
Qwen3-VL-30B-A3B-Instruct
deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct
DeepInfraChat$0.15$0.60
FunctionsVision
qwen3.5-122b-a10b
novita/qwen/qwen3.5-122b-a10b
NovitaChat$0.40$3.20
FunctionsVisionReasoning
qwen3.5-27b
novita/qwen/qwen3.5-27b
NovitaChat$0.30$2.40
FunctionsVisionReasoning
Qwen3.5-27B
deepinfra/Qwen/Qwen3.5-27B
DeepInfraChat$0.26$2.60
FunctionsVisionReasoning
qwen3.5-35b-a3b
novita/qwen/qwen3.5-35b-a3b
NovitaChat$0.25$2.00
FunctionsVisionReasoning
Qwen3.5-35B-A3B
wandb/Qwen/Qwen3.5-35B-A3B
WandbChat$0.25$1.25
VisionReasoning
qwen3.5-397b-a17b
novita/qwen/qwen3.5-397b-a17b
NovitaChat$0.60$3.60
FunctionsVisionReasoning
qwen3.6-27b
novita/qwen/qwen3.6-27b
NovitaChat$0.60$3.60
FunctionsVisionReasoning
Qwen3.6-27B
wandb/Qwen/Qwen3.6-27B
WandbChat$0.60$3.60
VisionReasoning
qwen3.6-35b-a3b
novita/qwen/qwen3.6-35b-a3b
NovitaChat$0.25$1.49
FunctionsVisionReasoning
Qwen3.6-35B-A3B
wandb/Qwen/Qwen3.6-35B-A3B
WandbChat$0.25$1.25
VisionReasoning
Qwen3.6-35B-A3B
deepinfra/Qwen/Qwen3.6-35B-A3B
DeepInfraChat$0.10$0.95
FunctionsVisionReasoning
qwen3.7-max
novita/qwen/qwen3.7-max
NovitaChat$1.25$3.75
FunctionsReasoning
Qwen3.7-Max
deepinfra/Qwen/Qwen3.7-Max
DeepInfraChat$2.50$7.50
Functions
Qwen3.8-27B
wandb/Qwen/Qwen3.8-27B
WandbChat$0.40$3.00
VisionReasoning
Qwen3.8-27B
deepinfra/Qwen/Qwen3.8-27B
DeepInfraChat$0.20$2.50
FunctionsVisionReasoning
qwen3.8-max
novita/qwen/qwen3.8-max
NovitaChat$2.00$6.00
FunctionsVisionReasoning
Seed-2.0-mini
deepinfra/ByteDance/Seed-2.0-mini
DeepInfraChat$0.10$0.40
FunctionsVisionReasoning
step-3.7-flash
novita/stepfun/step-3.7-flash
NovitaChat$0.20$1.15
FunctionsVisionReasoning
Showing 2,7012,800 of 4,079