Free price reference
LLM pricing, every model side by side
Cost per million tokens (input, output, and cache), plus context windows, for 3,719 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 |
|---|---|---|---|---|---|---|---|
|
novita/qwen/qwen3-vl-30b-a3b-thinking
novita/qwen/qwen3-vl-30b-a3b-thinking
|
Novita | $0.2000 | $1.00 | — | — | 131,072 | text |
|
novita/qwen/qwen3-vl-8b-instruct
novita/qwen/qwen3-vl-8b-instruct
|
Novita | $0.0800 | $0.5000 | — | — | 131,072 | text |
|
novita/qwen/qwen3.5-122b-a10b
novita/qwen/qwen3.5-122b-a10b
|
Novita | $0.4000 | $3.20 | — | — | 262,144 | text |
|
novita/qwen/qwen3.5-27b
novita/qwen/qwen3.5-27b
|
Novita | $0.3000 | $2.40 | — | — | 262,144 | text |
|
novita/qwen/qwen3.5-35b-a3b
novita/qwen/qwen3.5-35b-a3b
|
Novita | $0.2500 | $2.00 | — | — | 262,144 | text |
|
novita/qwen/qwen3.5-397b-a17b
novita/qwen/qwen3.5-397b-a17b
|
Novita | $0.6000 | $3.60 | — | — | 262,144 | text |
|
novita/qwen/qwen3.6-27b
novita/qwen/qwen3.6-27b
|
Novita | $0.6000 | $3.60 | — | — | 262,144 | text |
|
novita/qwen/qwen3.6-35b-a3b
novita/qwen/qwen3.6-35b-a3b
|
Novita | $0.2480 | $1.49 | — | — | 262,144 | text |
|
novita/qwen/qwen3.7-max
novita/qwen/qwen3.7-max
|
Novita | $1.25 | $3.75 | $0.2500 | — | 1,000,000 | text |
|
novita/qwen/qwen3.8-max
novita/qwen/qwen3.8-max
|
Novita | $2.00 | $6.00 | $0.2500 | — | 1,000,000 | text |
|
novita/sao10k/l3-70b-euryale-v2.1
novita/sao10k/l3-70b-euryale-v2.1
|
Novita | $1.48 | $1.48 | — | — | 8,192 | text |
|
novita/sao10k/l3-8b-lunaris
novita/sao10k/l3-8b-lunaris
|
Novita | $0.0500 | $0.0500 | — | — | 8,192 | text |
|
novita/Sao10K/L3-8B-Stheno-v3.2
novita/Sao10K/L3-8B-Stheno-v3.2
|
Novita | $0.0500 | $0.0500 | — | — | 8,192 | text |
|
novita/sao10k/l31-70b-euryale-v2.2
novita/sao10k/l31-70b-euryale-v2.2
|
Novita | $1.48 | $1.48 | — | — | 8,192 | text |
|
novita/skywork/r1v4-lite
novita/skywork/r1v4-lite
|
Novita | $0.2000 | $0.6000 | — | — | 262,144 | text |
|
novita/stepfun/step-3.7-flash
novita/stepfun/step-3.7-flash
|
Novita | $0.2000 | $1.15 | $0.0400 | — | 262,144 | text |
|
novita/tencent/hy3
novita/tencent/hy3
|
Novita | $0.1400 | $0.5800 | $0.0350 | — | 262,144 | text |
|
novita/thudm/glm-4-32b-0414
novita/thudm/glm-4-32b-0414
|
Novita | $0.5500 | $1.66 | — | — | 32,000 | text |
|
novita/xiaomimimo/mimo-v2-flash
novita/xiaomimimo/mimo-v2-flash
|
Novita | $0.1100 | $0.3300 | $0.0240 | — | 262,144 | text |
|
novita/xiaomimimo/mimo-v2.5
novita/xiaomimimo/mimo-v2.5
|
Novita | $0.1680 | $0.3360 | $0.0034 | — | 1,048,576 | text |
|
novita/xiaomimimo/mimo-v2.5-pro
novita/xiaomimimo/mimo-v2.5-pro
|
Novita | $0.5220 | $1.04 | $0.0043 | — | 1,048,576 | text |
|
novita/zai-org/autoglm-phone-9b-multilingual
novita/zai-org/autoglm-phone-9b-multilingual
|
Novita | $0.0350 | $0.1380 | — | — | 65,536 | text |
|
novita/zai-org/glm-4.5
novita/zai-org/glm-4.5
|
Novita | $0.6000 | $2.20 | $0.1100 | — | 131,072 | text |
|
novita/zai-org/glm-4.5-air
novita/zai-org/glm-4.5-air
|
Novita | $0.1300 | $0.8500 | $0.0250 | — | 131,072 | text |
|
novita/zai-org/glm-4.5v
novita/zai-org/glm-4.5v
|
Novita | $0.6000 | $1.80 | $0.1100 | — | 65,536 | text |
|
novita/zai-org/glm-4.6
novita/zai-org/glm-4.6
|
Novita | $0.5500 | $2.20 | $0.1100 | — | 204,800 | text |
|
novita/zai-org/glm-4.6v
novita/zai-org/glm-4.6v
|
Novita | $0.3000 | $0.9000 | $0.0550 | — | 131,072 | text |
|
novita/zai-org/glm-4.7
novita/zai-org/glm-4.7
|
Novita | $0.6000 | $2.20 | $0.1100 | — | 204,800 | text |
|
novita/zai-org/glm-4.7-flash
novita/zai-org/glm-4.7-flash
|
Novita | $0.0700 | $0.4000 | $0.0100 | — | 200,000 | text |
|
novita/zai-org/glm-4.7-h
novita/zai-org/glm-4.7-h
|
Novita | $0.6000 | $2.20 | $0.1100 | — | 204,800 | text |
|
novita/zai-org/glm-5
novita/zai-org/glm-5
|
Novita | $1.00 | $3.20 | $0.2000 | — | 202,800 | text |
|
novita/zai-org/glm-5-turbo
novita/zai-org/glm-5-turbo
|
Novita | $1.20 | $4.00 | $0.2400 | — | 202,800 | text |
|
novita/zai-org/glm-5.1
novita/zai-org/glm-5.1
|
Novita | $1.38 | $4.40 | $0.2600 | — | 204,800 | text |
|
novita/zai-org/glm-5.2
novita/zai-org/glm-5.2
|
Novita | $1.40 | $4.40 | $0.2600 | — | 1,048,576 | text |
|
novita/zai-org/glm-5.3
novita/zai-org/glm-5.3
|
Novita | $1.40 | $4.40 | $0.2600 | — | 1,048,576 | text |
|
novita/zai-org/glm-5v-turbo
novita/zai-org/glm-5v-turbo
|
Novita | $1.20 | $4.00 | $0.2400 | — | 204,800 | text |
|
nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
|
Nscale | $0.3750 | $0.3750 | — | — | — | text |
|
nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B
nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
Nscale | $0.0250 | $0.0250 | — | — | — | text |
|
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
Nscale | $0.0900 | $0.0900 | — | — | — | text |
|
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
|
Nscale | $0.0700 | $0.0700 | — | — | — | text |
|
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
Nscale | $0.1500 | $0.1500 | — | — | — | text |
|
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
|
Nscale | $0.2000 | $0.2000 | — | — | — | text |
|
nscale/meta-llama/Llama-3.1-8B-Instruct
nscale/meta-llama/Llama-3.1-8B-Instruct
|
Nscale | $0.0300 | $0.0300 | — | — | — | text |
|
nscale/meta-llama/Llama-3.3-70B-Instruct
nscale/meta-llama/Llama-3.3-70B-Instruct
|
Nscale | $0.2000 | $0.2000 | — | — | — | text |
|
nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct
nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct
|
Nscale | $0.0900 | $0.2900 | — | — | — | text |
|
nscale/mistralai/mixtral-8x22b-instruct-v0.1
nscale/mistralai/mixtral-8x22b-instruct-v0.1
|
Nscale | $0.6000 | $0.6000 | — | — | — | text |
|
nscale/Qwen/Qwen2.5-Coder-32B-Instruct
nscale/Qwen/Qwen2.5-Coder-32B-Instruct
|
Nscale | $0.0600 | $0.2000 | — | — | — | text |
|
nscale/Qwen/Qwen2.5-Coder-3B-Instruct
nscale/Qwen/Qwen2.5-Coder-3B-Instruct
|
Nscale | $0.0100 | $0.0300 | — | — | — | text |
|
nscale/Qwen/Qwen2.5-Coder-7B-Instruct
nscale/Qwen/Qwen2.5-Coder-7B-Instruct
|
Nscale | $0.0100 | $0.0300 | — | — | — | text |
|
nscale/Qwen/QwQ-32B
nscale/Qwen/QwQ-32B
|
Nscale | $0.1800 | $0.2000 | — | — | — | text |
|
nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2
nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2
|
Nvidia Nim | $0.0000 | $0.0000 | — | — | — | rerank |
|
nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3
nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3
|
Nvidia Nim | $0.0000 | $0.0000 | — | — | — | rerank |
|
nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2
nvidia_nim/ranking/nvidia/llama-3.2-nv-rerankqa-1b-v2
|
Nvidia Nim | $0.0000 | $0.0000 | — | — | — | rerank |
|
oci/cohere.command-a-03-2025
oci/cohere.command-a-03-2025
|
Oci | $1.56 | $1.56 | — | — | 256,000 | text |
|
oci/cohere.command-a-reasoning
oci/cohere.command-a-reasoning
|
Oci | $1.56 | $1.56 | — | — | 256,000 | text |
|
oci/cohere.command-a-reasoning-08-2025
oci/cohere.command-a-reasoning-08-2025
|
Oci | $1.56 | $1.56 | — | — | 256,000 | text |
|
oci/cohere.command-a-translate-08-2025
oci/cohere.command-a-translate-08-2025
|
Oci | $0.0900 | $0.0900 | — | — | 256,000 | text |
|
oci/cohere.command-a-vision
oci/cohere.command-a-vision
|
Oci | $1.56 | $1.56 | — | — | 256,000 | text |
|
oci/cohere.command-a-vision-07-2025
oci/cohere.command-a-vision-07-2025
|
Oci | $1.56 | $1.56 | — | — | 128,000 | text |
|
oci/cohere.command-latest
oci/cohere.command-latest
|
Oci | $1.56 | $1.56 | — | — | 128,000 | text |
|
oci/cohere.command-plus-latest
oci/cohere.command-plus-latest
|
Oci | $1.56 | $1.56 | — | — | 128,000 | text |
|
oci/cohere.command-r-08-2024
oci/cohere.command-r-08-2024
|
Oci | $0.1500 | $0.1500 | — | — | 128,000 | text |
|
oci/cohere.command-r-plus-08-2024
oci/cohere.command-r-plus-08-2024
|
Oci | $1.56 | $1.56 | — | — | 128,000 | text |
|
oci/cohere.embed-english-image-v3.0
oci/cohere.embed-english-image-v3.0
|
Oci | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
oci/cohere.embed-english-light-image-v3.0
oci/cohere.embed-english-light-image-v3.0
|
Oci | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
oci/cohere.embed-english-light-v3.0
oci/cohere.embed-english-light-v3.0
|
Oci | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
oci/cohere.embed-english-v3.0
oci/cohere.embed-english-v3.0
|
Oci | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
oci/cohere.embed-multilingual-image-v3.0
oci/cohere.embed-multilingual-image-v3.0
|
Oci | $0.1000 | — | — | — | 512 | embedding |
|
oci/cohere.embed-multilingual-light-image-v3.0
oci/cohere.embed-multilingual-light-image-v3.0
|
Oci | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
oci/cohere.embed-multilingual-light-v3.0
oci/cohere.embed-multilingual-light-v3.0
|
Oci | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
oci/cohere.embed-multilingual-v3.0
oci/cohere.embed-multilingual-v3.0
|
Oci | $0.1000 | $0.0000 | — | — | 512 | embedding |
|
oci/cohere.embed-v4.0
oci/cohere.embed-v4.0
|
Oci | $0.1200 | $0.0000 | — | — | 128,000 | embedding |
|
oci/google.gemini-2.5-flash
oci/google.gemini-2.5-flash
|
Oci | $0.1500 | $0.6000 | — | — | 1,048,576 | text |
|
oci/google.gemini-2.5-flash-lite
oci/google.gemini-2.5-flash-lite
|
Oci | $0.0750 | $0.3000 | — | — | 1,048,576 | text |
|
oci/google.gemini-2.5-pro
oci/google.gemini-2.5-pro
|
Oci | $1.25 | $10.00 | — | — | 1,048,576 | text |
|
oci/meta.llama-3.1-405b-instruct
oci/meta.llama-3.1-405b-instruct
|
Oci | $10.68 | $10.68 | — | — | 128,000 | text |
|
oci/meta.llama-3.1-70b-instruct
oci/meta.llama-3.1-70b-instruct
|
Oci | $0.7200 | $0.7200 | — | — | 128,000 | text |
|
oci/meta.llama-3.1-8b-instruct
oci/meta.llama-3.1-8b-instruct
|
Oci | $0.7200 | $0.7200 | — | — | 128,000 | text |
|
oci/meta.llama-3.2-11b-vision-instruct
oci/meta.llama-3.2-11b-vision-instruct
|
Oci | $2.00 | $2.00 | — | — | 128,000 | text |
|
oci/meta.llama-3.2-90b-vision-instruct
oci/meta.llama-3.2-90b-vision-instruct
|
Oci | $2.00 | $2.00 | — | — | 128,000 | text |
|
oci/meta.llama-3.3-70b-instruct
oci/meta.llama-3.3-70b-instruct
|
Oci | $0.7200 | $0.7200 | — | — | 128,000 | text |
|
oci/meta.llama-3.3-70b-instruct-fp8-dynamic
oci/meta.llama-3.3-70b-instruct-fp8-dynamic
|
Oci | $0.7200 | $0.7200 | — | — | 128,000 | text |
|
oci/meta.llama-4-maverick-17b-128e-instruct-fp8
oci/meta.llama-4-maverick-17b-128e-instruct-fp8
|
Oci | $0.7200 | $0.7200 | — | — | 1,048,576 | text |
|
oci/meta.llama-4-scout-17b-16e-instruct
oci/meta.llama-4-scout-17b-16e-instruct
|
Oci | $0.7200 | $0.7200 | — | — | 10,485,760 | text |
|
oci/openai.gpt-5
oci/openai.gpt-5
|
Oci | $1.25 | $10.00 | — | — | 272,000 | text |
|
oci/openai.gpt-5-mini
oci/openai.gpt-5-mini
|
Oci | $0.2500 | $2.00 | — | — | 272,000 | text |
|
oci/openai.gpt-5-nano
oci/openai.gpt-5-nano
|
Oci | $0.0500 | $0.4000 | — | — | 272,000 | text |
|
oci/xai.grok-3
oci/xai.grok-3
|
Oci | $3.00 | $15.00 | — | — | 131,072 | text |
|
oci/xai.grok-3-fast
oci/xai.grok-3-fast
|
Oci | $5.00 | $25.00 | — | — | 131,072 | text |
|
oci/xai.grok-3-mini
oci/xai.grok-3-mini
|
Oci | $0.3000 | $0.5000 | — | — | 131,072 | text |
|
oci/xai.grok-3-mini-fast
oci/xai.grok-3-mini-fast
|
Oci | $0.6000 | $4.00 | — | — | 131,072 | text |
|
oci/xai.grok-4
oci/xai.grok-4
|
Oci | $3.00 | $15.00 | — | — | 128,000 | text |
|
oci/xai.grok-4-fast
oci/xai.grok-4-fast
|
Oci | $5.00 | $25.00 | — | — | 131,072 | text |
|
oci/xai.grok-4.1-fast
oci/xai.grok-4.1-fast
|
Oci | $5.00 | $25.00 | — | — | 131,072 | text |
|
oci/xai.grok-4.20
oci/xai.grok-4.20
|
Oci | $3.00 | $15.00 | — | — | 131,072 | text |
|
oci/xai.grok-4.20-multi-agent
oci/xai.grok-4.20-multi-agent
|
Oci | $3.00 | $15.00 | — | — | 131,072 | text |
|
oci/xai.grok-code-fast-1
oci/xai.grok-code-fast-1
|
Oci | $5.00 | $25.00 | — | — | 131,072 | text |
|
ollama/codegeex4
ollama/codegeex4
|
Ollama | $0.0000 | $0.0000 | — | — | 32,768 | text |
|
ollama/codegemma
ollama/codegemma
|
Ollama | $0.0000 | $0.0000 | — | — | 8,192 | text |
|
ollama/codellama
ollama/codellama
|
Ollama | $0.0000 | $0.0000 | — | — | 4,096 | 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.