Free price reference
LLM pricing, every model side by side
Cost per million tokens (input, output, and cache), plus context windows, for 2,527 models across every major provider. Prices sync daily from the open LiteLLM dataset. Pick a model for details and a workload cost calculator.
| Model | Provider ↑ | Input /Mtok | Output /Mtok | Cache read | Cache write | Context | Modality |
|---|---|---|---|---|---|---|---|
|
mistral/open-mixtral-8x22b
mistral/open-mixtral-8x22b
|
Mistral AI | $2.00 | $6.00 | — | — | 65,336 | text |
|
mistral/open-mixtral-8x7b
mistral/open-mixtral-8x7b
|
Mistral AI | $0.7000 | $0.7000 | — | — | 32,000 | text |
|
mistral/pixtral-12b-2409
mistral/pixtral-12b-2409
|
Mistral AI | $0.1500 | $0.1500 | — | — | 128,000 | text |
|
mistral/pixtral-large-2411
mistral/pixtral-large-2411
|
Mistral AI | $2.00 | $6.00 | — | — | 128,000 | text |
|
mistral/pixtral-large-latest
mistral/pixtral-large-latest
|
Mistral AI | $2.00 | $6.00 | — | — | 128,000 | text |
|
moonshot/kimi-k2-0711-preview
moonshot/kimi-k2-0711-preview
|
Moonshot | $0.6000 | $2.50 | $0.1500 | — | 131,072 | text |
|
moonshot/kimi-k2-0905-preview
moonshot/kimi-k2-0905-preview
|
Moonshot | $0.6000 | $2.50 | $0.1500 | — | 262,144 | text |
|
moonshot/kimi-k2-thinking
moonshot/kimi-k2-thinking
|
Moonshot | $0.6000 | $2.50 | $0.1500 | — | 262,144 | text |
|
moonshot/kimi-k2-thinking-turbo
moonshot/kimi-k2-thinking-turbo
|
Moonshot | $1.15 | $8.00 | $0.1500 | — | 262,144 | text |
|
moonshot/kimi-k2-turbo-preview
moonshot/kimi-k2-turbo-preview
|
Moonshot | $1.15 | $8.00 | $0.1500 | — | 262,144 | text |
|
moonshot/kimi-k2.5
moonshot/kimi-k2.5
|
Moonshot | $0.6000 | $3.00 | $0.1000 | — | 262,144 | text |
|
moonshot/kimi-k2.6
moonshot/kimi-k2.6
|
Moonshot | $0.9500 | $4.00 | $0.1600 | — | 262,144 | text |
|
moonshot/kimi-latest
moonshot/kimi-latest
|
Moonshot | $2.00 | $5.00 | $0.1500 | — | 131,072 | text |
|
moonshot/kimi-latest-128k
moonshot/kimi-latest-128k
|
Moonshot | $2.00 | $5.00 | $0.1500 | — | 131,072 | text |
|
moonshot/kimi-latest-32k
moonshot/kimi-latest-32k
|
Moonshot | $1.00 | $3.00 | $0.1500 | — | 32,768 | text |
|
moonshot/kimi-latest-8k
moonshot/kimi-latest-8k
|
Moonshot | $0.2000 | $2.00 | $0.1500 | — | 8,192 | text |
|
moonshot/kimi-thinking-preview
moonshot/kimi-thinking-preview
|
Moonshot | $0.6000 | $2.50 | $0.1500 | — | 131,072 | text |
|
moonshot/moonshot-v1-128k
moonshot/moonshot-v1-128k
|
Moonshot | $2.00 | $5.00 | — | — | 131,072 | text |
|
moonshot/moonshot-v1-128k-0430
moonshot/moonshot-v1-128k-0430
|
Moonshot | $2.00 | $5.00 | — | — | 131,072 | text |
|
moonshot/moonshot-v1-128k-vision-preview
moonshot/moonshot-v1-128k-vision-preview
|
Moonshot | $2.00 | $5.00 | — | — | 131,072 | text |
|
moonshot/moonshot-v1-32k
moonshot/moonshot-v1-32k
|
Moonshot | $1.00 | $3.00 | — | — | 32,768 | text |
|
moonshot/moonshot-v1-32k-0430
moonshot/moonshot-v1-32k-0430
|
Moonshot | $1.00 | $3.00 | — | — | 32,768 | text |
|
moonshot/moonshot-v1-32k-vision-preview
moonshot/moonshot-v1-32k-vision-preview
|
Moonshot | $1.00 | $3.00 | — | — | 32,768 | text |
|
moonshot/moonshot-v1-8k
moonshot/moonshot-v1-8k
|
Moonshot | $0.2000 | $2.00 | — | — | 8,192 | text |
|
moonshot/moonshot-v1-8k-0430
moonshot/moonshot-v1-8k-0430
|
Moonshot | $0.2000 | $2.00 | — | — | 8,192 | text |
|
moonshot/moonshot-v1-8k-vision-preview
moonshot/moonshot-v1-8k-vision-preview
|
Moonshot | $0.2000 | $2.00 | — | — | 8,192 | text |
|
moonshot/moonshot-v1-auto
moonshot/moonshot-v1-auto
|
Moonshot | $2.00 | $5.00 | — | — | 131,072 | text |
|
morph/morph-v3-fast
morph/morph-v3-fast
|
Morph | $0.8000 | $1.20 | — | — | 16,000 | text |
|
morph/morph-v3-large
morph/morph-v3-large
|
Morph | $0.9000 | $1.90 | — | — | 16,000 | text |
|
nebius/BAAI/bge-en-icl
nebius/BAAI/bge-en-icl
|
Nebius | $0.0100 | $0.0000 | — | — | 32,768 | embedding |
|
nebius/BAAI/bge-multilingual-gemma2
nebius/BAAI/bge-multilingual-gemma2
|
Nebius | $0.0100 | $0.0000 | — | — | 8,192 | embedding |
|
nebius/deepseek-ai/DeepSeek-R1
nebius/deepseek-ai/DeepSeek-R1
|
Nebius | $0.8000 | $2.40 | — | — | 128,000 | text |
|
nebius/deepseek-ai/DeepSeek-R1-0528
nebius/deepseek-ai/DeepSeek-R1-0528
|
Nebius | $0.8000 | $2.40 | — | — | 164,000 | text |
|
nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
|
Nebius | $0.2500 | $0.7500 | — | — | 128,000 | text |
|
nebius/deepseek-ai/DeepSeek-V3
nebius/deepseek-ai/DeepSeek-V3
|
Nebius | $0.5000 | $1.50 | — | — | 128,000 | text |
|
nebius/deepseek-ai/DeepSeek-V3-0324
nebius/deepseek-ai/DeepSeek-V3-0324
|
Nebius | $0.5000 | $1.50 | — | — | 128,000 | text |
|
nebius/google/gemma-3-27b-it
nebius/google/gemma-3-27b-it
|
Nebius | $0.0600 | $0.2000 | — | — | 128,000 | text |
|
nebius/intfloat/e5-mistral-7b-instruct
nebius/intfloat/e5-mistral-7b-instruct
|
Nebius | $0.0100 | $0.0000 | — | — | 32,768 | embedding |
|
nebius/meta-llama/Llama-3.3-70B-Instruct
nebius/meta-llama/Llama-3.3-70B-Instruct
|
Nebius | $0.1300 | $0.4000 | — | — | 128,000 | text |
|
nebius/meta-llama/Llama-Guard-3-8B
nebius/meta-llama/Llama-Guard-3-8B
|
Nebius | $0.0200 | $0.0600 | — | — | 128,000 | text |
|
nebius/meta-llama/Meta-Llama-3.1-405B-Instruct
nebius/meta-llama/Meta-Llama-3.1-405B-Instruct
|
Nebius | $1.00 | $3.00 | — | — | 128,000 | text |
|
nebius/meta-llama/Meta-Llama-3.1-70B-Instruct
nebius/meta-llama/Meta-Llama-3.1-70B-Instruct
|
Nebius | $0.1300 | $0.4000 | — | — | 128,000 | text |
|
nebius/meta-llama/Meta-Llama-3.1-8B-Instruct
nebius/meta-llama/Meta-Llama-3.1-8B-Instruct
|
Nebius | $0.0200 | $0.0600 | — | — | 128,000 | text |
|
nebius/mistralai/Mistral-Nemo-Instruct-2407
nebius/mistralai/Mistral-Nemo-Instruct-2407
|
Nebius | $0.0400 | $0.1200 | — | — | 128,000 | text |
|
nebius/NousResearch/Hermes-3-Llama-3.1-405B
nebius/NousResearch/Hermes-3-Llama-3.1-405B
|
Nebius | $1.00 | $3.00 | — | — | 128,000 | text |
|
nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1
nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1
|
Nebius | $0.6000 | $1.80 | — | — | 128,000 | text |
|
nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1
nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1
|
Nebius | $0.1000 | $0.4000 | — | — | 131,072 | text |
|
nebius/Qwen/Qwen2-VL-72B-Instruct
nebius/Qwen/Qwen2-VL-72B-Instruct
|
Nebius | $0.1300 | $0.4000 | — | — | 131,072 | text |
|
nebius/Qwen/Qwen2-VL-7B-Instruct
nebius/Qwen/Qwen2-VL-7B-Instruct
|
Nebius | $0.0200 | $0.0600 | — | — | 131,072 | text |
|
nebius/Qwen/Qwen2.5-32B-Instruct
nebius/Qwen/Qwen2.5-32B-Instruct
|
Nebius | $0.0600 | $0.2000 | — | — | 128,000 | text |
|
nebius/Qwen/Qwen2.5-72B-Instruct
nebius/Qwen/Qwen2.5-72B-Instruct
|
Nebius | $0.1300 | $0.4000 | — | — | 128,000 | text |
|
nebius/Qwen/Qwen2.5-Coder-7B
nebius/Qwen/Qwen2.5-Coder-7B
|
Nebius | $0.0100 | $0.0300 | — | — | 32,768 | text |
|
nebius/Qwen/Qwen2.5-VL-72B-Instruct
nebius/Qwen/Qwen2.5-VL-72B-Instruct
|
Nebius | $0.1300 | $0.4000 | — | — | 131,072 | text |
|
nebius/Qwen/Qwen3-14B
nebius/Qwen/Qwen3-14B
|
Nebius | $0.0800 | $0.2400 | — | — | 32,768 | text |
|
nebius/Qwen/Qwen3-235B-A22B
nebius/Qwen/Qwen3-235B-A22B
|
Nebius | $0.2000 | $0.6000 | — | — | 262,144 | text |
|
nebius/Qwen/Qwen3-30B-A3B
nebius/Qwen/Qwen3-30B-A3B
|
Nebius | $0.1000 | $0.3000 | — | — | 32,768 | text |
|
nebius/Qwen/Qwen3-32B
nebius/Qwen/Qwen3-32B
|
Nebius | $0.1000 | $0.3000 | — | — | 32,768 | text |
|
nebius/Qwen/Qwen3-4B
nebius/Qwen/Qwen3-4B
|
Nebius | $0.0800 | $0.2400 | — | — | 32,768 | text |
|
nebius/Qwen/QwQ-32B
nebius/Qwen/QwQ-32B
|
Nebius | $0.1500 | $0.4500 | — | — | 32,768 | text |
|
chatdolphin
chatdolphin
|
Nlp Cloud | $0.5000 | $0.5000 | — | — | 16,384 | text |
|
dolphin
dolphin
|
Nlp Cloud | $0.5000 | $0.5000 | — | — | 16,384 | text |
|
novita/baai/bge-m3
novita/baai/bge-m3
|
Novita | $0.0100 | $0.0100 | — | — | 8,192 | embedding |
|
novita/baai/bge-reranker-v2-m3
novita/baai/bge-reranker-v2-m3
|
Novita | $0.0100 | $0.0100 | — | — | 8,000 | rerank |
|
novita/baichuan/baichuan-m2-32b
novita/baichuan/baichuan-m2-32b
|
Novita | $0.0700 | $0.0700 | — | — | 131,072 | text |
|
novita/baidu/ernie-4.5-21B-a3b
novita/baidu/ernie-4.5-21B-a3b
|
Novita | $0.0700 | $0.2800 | — | — | 120,000 | text |
|
novita/baidu/ernie-4.5-21B-a3b-thinking
novita/baidu/ernie-4.5-21B-a3b-thinking
|
Novita | $0.0700 | $0.2800 | — | — | 131,072 | text |
|
novita/baidu/ernie-4.5-300b-a47b-paddle
novita/baidu/ernie-4.5-300b-a47b-paddle
|
Novita | $0.2800 | $1.10 | — | — | 123,000 | text |
|
novita/baidu/ernie-4.5-vl-28b-a3b
novita/baidu/ernie-4.5-vl-28b-a3b
|
Novita | $0.1400 | $0.5600 | — | — | 30,000 | text |
|
novita/baidu/ernie-4.5-vl-28b-a3b-thinking
novita/baidu/ernie-4.5-vl-28b-a3b-thinking
|
Novita | $0.3900 | $0.3900 | — | — | 131,072 | text |
|
novita/baidu/ernie-4.5-vl-424b-a47b
novita/baidu/ernie-4.5-vl-424b-a47b
|
Novita | $0.4200 | $1.25 | — | — | 123,000 | text |
|
novita/deepseek/deepseek-ocr
novita/deepseek/deepseek-ocr
|
Novita | $0.0300 | $0.0300 | — | — | 8,192 | text |
|
novita/deepseek/deepseek-prover-v2-671b
novita/deepseek/deepseek-prover-v2-671b
|
Novita | $0.7000 | $2.50 | — | — | 160,000 | text |
|
novita/deepseek/deepseek-r1-0528
novita/deepseek/deepseek-r1-0528
|
Novita | $0.7000 | $2.50 | $0.3500 | — | 163,840 | text |
|
novita/deepseek/deepseek-r1-0528-qwen3-8b
novita/deepseek/deepseek-r1-0528-qwen3-8b
|
Novita | $0.0600 | $0.0900 | — | — | 128,000 | text |
|
novita/deepseek/deepseek-r1-distill-llama-70b
novita/deepseek/deepseek-r1-distill-llama-70b
|
Novita | $0.8000 | $0.8000 | — | — | 8,192 | text |
|
novita/deepseek/deepseek-r1-distill-qwen-14b
novita/deepseek/deepseek-r1-distill-qwen-14b
|
Novita | $0.1500 | $0.1500 | — | — | 32,768 | text |
|
novita/deepseek/deepseek-r1-distill-qwen-32b
novita/deepseek/deepseek-r1-distill-qwen-32b
|
Novita | $0.3000 | $0.3000 | — | — | 64,000 | text |
|
novita/deepseek/deepseek-r1-turbo
novita/deepseek/deepseek-r1-turbo
|
Novita | $0.7000 | $2.50 | — | — | 64,000 | text |
|
novita/deepseek/deepseek-v3-0324
novita/deepseek/deepseek-v3-0324
|
Novita | $0.2700 | $1.12 | $0.1350 | — | 163,840 | text |
|
novita/deepseek/deepseek-v3-turbo
novita/deepseek/deepseek-v3-turbo
|
Novita | $0.4000 | $1.30 | — | — | 64,000 | text |
|
novita/deepseek/deepseek-v3.1
novita/deepseek/deepseek-v3.1
|
Novita | $0.2700 | $1.00 | $0.1350 | — | 131,072 | text |
|
novita/deepseek/deepseek-v3.1-terminus
novita/deepseek/deepseek-v3.1-terminus
|
Novita | $0.2700 | $1.00 | $0.1350 | — | 131,072 | text |
|
novita/deepseek/deepseek-v3.2
novita/deepseek/deepseek-v3.2
|
Novita | $0.2690 | $0.4000 | $0.1345 | — | 163,840 | text |
|
novita/deepseek/deepseek-v3.2-exp
novita/deepseek/deepseek-v3.2-exp
|
Novita | $0.2700 | $0.4100 | — | — | 163,840 | text |
|
novita/google/gemma-3-12b-it
novita/google/gemma-3-12b-it
|
Novita | $0.0500 | $0.1000 | — | — | 131,072 | text |
|
novita/google/gemma-3-27b-it
novita/google/gemma-3-27b-it
|
Novita | $0.1190 | $0.2000 | — | — | 98,304 | text |
|
novita/gryphe/mythomax-l2-13b
novita/gryphe/mythomax-l2-13b
|
Novita | $0.0900 | $0.0900 | — | — | 4,096 | text |
|
novita/kwaipilot/kat-coder-pro
novita/kwaipilot/kat-coder-pro
|
Novita | $0.3000 | $1.20 | $0.0600 | — | 256,000 | text |
|
novita/meta-llama/llama-3-70b-instruct
novita/meta-llama/llama-3-70b-instruct
|
Novita | $0.5100 | $0.7400 | — | — | 8,192 | text |
|
novita/meta-llama/llama-3-8b-instruct
novita/meta-llama/llama-3-8b-instruct
|
Novita | $0.0400 | $0.0400 | — | — | 8,192 | text |
|
novita/meta-llama/llama-3.1-8b-instruct
novita/meta-llama/llama-3.1-8b-instruct
|
Novita | $0.0200 | $0.0500 | — | — | 16,384 | text |
|
novita/meta-llama/llama-3.2-3b-instruct
novita/meta-llama/llama-3.2-3b-instruct
|
Novita | $0.0300 | $0.0500 | — | — | 32,768 | text |
|
novita/meta-llama/llama-3.3-70b-instruct
novita/meta-llama/llama-3.3-70b-instruct
|
Novita | $0.1350 | $0.4000 | — | — | 131,072 | text |
|
novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
|
Novita | $0.2700 | $0.8500 | — | — | 1,048,576 | text |
|
novita/meta-llama/llama-4-scout-17b-16e-instruct
novita/meta-llama/llama-4-scout-17b-16e-instruct
|
Novita | $0.1800 | $0.5900 | — | — | 131,072 | text |
|
novita/microsoft/wizardlm-2-8x22b
novita/microsoft/wizardlm-2-8x22b
|
Novita | $0.6200 | $0.6200 | — | — | 65,535 | text |
|
novita/minimax/minimax-m2
novita/minimax/minimax-m2
|
Novita | $0.3000 | $1.20 | $0.0300 | — | 204,800 | text |
|
novita/minimax/minimax-m2.1
novita/minimax/minimax-m2.1
|
Novita | $0.3000 | $1.20 | $0.0300 | — | 204,800 | text |
|
novita/minimaxai/minimax-m1-80k
novita/minimaxai/minimax-m1-80k
|
Novita | $0.5500 | $2.20 | — | — | 1,000,000 | text |
|
novita/mistralai/mistral-nemo
novita/mistralai/mistral-nemo
|
Novita | $0.0400 | $0.1700 | — | — | 60,288 | text |
Prices are sourced from the open LiteLLM dataset and may lag provider changes. Always confirm against the provider's official pricing before relying on a figure.