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 |
|---|---|---|---|---|---|---|---|
|
perplexity/mistral-7b-instruct
perplexity/mistral-7b-instruct
|
Perplexity | $0.0700 | $0.2800 | — | — | 4,096 | text |
|
perplexity/mixtral-8x7b-instruct
perplexity/mixtral-8x7b-instruct
|
Perplexity | $0.0700 | $0.2800 | — | — | 4,096 | text |
|
perplexity/openai/gpt-5
perplexity/openai/gpt-5
|
Perplexity | $1.25 | $10.00 | $0.1250 | — | — | text |
|
perplexity/openai/gpt-5-mini
perplexity/openai/gpt-5-mini
|
Perplexity | $0.2500 | $2.00 | $0.0250 | — | — | text |
|
perplexity/openai/gpt-5.1
perplexity/openai/gpt-5.1
|
Perplexity | $1.25 | $10.00 | $0.1250 | — | — | text |
|
perplexity/openai/gpt-5.2
perplexity/openai/gpt-5.2
|
Perplexity | $1.75 | $14.00 | $0.1750 | — | — | text |
|
perplexity/openai/gpt-5.4
perplexity/openai/gpt-5.4
|
Perplexity | $2.50 | $15.00 | $0.2500 | — | — | text |
|
perplexity/openai/gpt-5.4-mini
perplexity/openai/gpt-5.4-mini
|
Perplexity | $0.7500 | $4.50 | $0.0750 | — | — | text |
|
perplexity/openai/gpt-5.4-nano
perplexity/openai/gpt-5.4-nano
|
Perplexity | $0.2000 | $1.25 | $0.0200 | — | — | text |
|
perplexity/openai/gpt-5.5
perplexity/openai/gpt-5.5
|
Perplexity | $5.00 | $30.00 | $0.5000 | — | — | text |
|
perplexity/openai/gpt-5.6-luna
perplexity/openai/gpt-5.6-luna
|
Perplexity | $0.2000 | $1.20 | $0.0200 | — | — | text |
|
perplexity/openai/gpt-5.6-sol
perplexity/openai/gpt-5.6-sol
|
Perplexity | $5.00 | $30.00 | $0.5000 | — | — | text |
|
perplexity/openai/gpt-5.6-terra
perplexity/openai/gpt-5.6-terra
|
Perplexity | $2.00 | $12.00 | $0.2000 | — | — | text |
|
perplexity/perplexity/deepseek-v4-flash-0731
perplexity/perplexity/deepseek-v4-flash-0731
|
Perplexity | $0.1300 | $0.2600 | $0.0280 | — | — | text |
|
perplexity/perplexity/glm-5.2
perplexity/perplexity/glm-5.2
|
Perplexity | $1.40 | $4.40 | $0.1400 | — | — | text |
|
perplexity/perplexity/glm-5.3
perplexity/perplexity/glm-5.3
|
Perplexity | $1.40 | $4.40 | $0.2600 | — | — | text |
|
perplexity/perplexity/glm-5.3-flash
perplexity/perplexity/glm-5.3-flash
|
Perplexity | $0.1500 | $0.5000 | $0.0300 | — | — | text |
|
perplexity/perplexity/kimi-k2.7-code
perplexity/perplexity/kimi-k2.7-code
|
Perplexity | $0.9500 | $4.00 | $0.1900 | — | — | text |
|
perplexity/perplexity/kimi-k3
perplexity/perplexity/kimi-k3
|
Perplexity | $3.00 | $15.00 | $0.3000 | — | — | text |
|
perplexity/perplexity/nemotron-3-ultra-550b-a55b
perplexity/perplexity/nemotron-3-ultra-550b-a55b
|
Perplexity | $0.2500 | $2.50 | $0.2500 | — | — | text |
|
perplexity/perplexity/nemotron-3.5-lightning-30b-a3b
perplexity/perplexity/nemotron-3.5-lightning-30b-a3b
|
Perplexity | $0.0115 | $0.1700 | $0.0012 | — | — | text |
|
perplexity/perplexity/sonar
perplexity/perplexity/sonar
|
Perplexity | $0.2500 | $2.50 | $0.0625 | — | — | text |
|
perplexity/pplx-70b-chat
perplexity/pplx-70b-chat
|
Perplexity | $0.7000 | $2.80 | — | — | 4,096 | text |
|
perplexity/pplx-70b-online
perplexity/pplx-70b-online
|
Perplexity | $0.0000 | $2.80 | — | — | 4,096 | text |
|
perplexity/pplx-7b-chat
perplexity/pplx-7b-chat
|
Perplexity | $0.0700 | $0.2800 | — | — | 8,192 | text |
|
perplexity/pplx-7b-online
perplexity/pplx-7b-online
|
Perplexity | $0.0000 | $0.2800 | — | — | 4,096 | text |
|
perplexity/pplx-embed-context-v1-0.6b
perplexity/pplx-embed-context-v1-0.6b
|
Perplexity | $0.0080 | $0.0000 | — | — | 32,768 | embedding |
|
perplexity/pplx-embed-context-v1-4b
perplexity/pplx-embed-context-v1-4b
|
Perplexity | $0.0500 | $0.0000 | — | — | 32,768 | embedding |
|
perplexity/pplx-embed-v1-0.6b
perplexity/pplx-embed-v1-0.6b
|
Perplexity | $0.0040 | $0.0000 | — | — | 32,768 | embedding |
|
perplexity/pplx-embed-v1-4b
perplexity/pplx-embed-v1-4b
|
Perplexity | $0.0300 | $0.0000 | — | — | 32,768 | embedding |
|
perplexity/sonar
perplexity/sonar
|
Perplexity | $1.00 | $1.00 | — | — | 128,000 | text |
|
perplexity/sonar-deep-research
perplexity/sonar-deep-research
|
Perplexity | $2.00 | $8.00 | — | — | 128,000 | text |
|
perplexity/sonar-medium-chat
perplexity/sonar-medium-chat
|
Perplexity | $0.6000 | $1.80 | — | — | 16,384 | text |
|
perplexity/sonar-medium-online
perplexity/sonar-medium-online
|
Perplexity | $0.0000 | $1.80 | — | — | 12,000 | text |
|
perplexity/sonar-pro
perplexity/sonar-pro
|
Perplexity | $3.00 | $15.00 | — | — | 200,000 | text |
|
perplexity/sonar-reasoning
perplexity/sonar-reasoning
|
Perplexity | $1.00 | $5.00 | — | — | 128,000 | text |
|
perplexity/sonar-reasoning-pro
perplexity/sonar-reasoning-pro
|
Perplexity | $2.00 | $8.00 | — | — | 128,000 | text |
|
perplexity/sonar-small-chat
perplexity/sonar-small-chat
|
Perplexity | $0.0700 | $0.2800 | — | — | 16,384 | text |
|
perplexity/sonar-small-online
perplexity/sonar-small-online
|
Perplexity | $0.0000 | $0.2800 | — | — | 12,000 | text |
|
perplexity/xai/grok-4.20-multi-agent
perplexity/xai/grok-4.20-multi-agent
|
Perplexity | $1.25 | $2.50 | $0.2000 | — | — | text |
|
perplexity/xai/grok-4.20-non-reasoning
perplexity/xai/grok-4.20-non-reasoning
|
Perplexity | $1.25 | $2.50 | $0.2000 | — | — | text |
|
perplexity/xai/grok-4.20-reasoning
perplexity/xai/grok-4.20-reasoning
|
Perplexity | $1.25 | $2.50 | $0.2000 | — | — | text |
|
perplexity/xai/grok-4.3
perplexity/xai/grok-4.3
|
Perplexity | $1.25 | $2.50 | $0.2000 | — | — | text |
|
perplexity/xai/grok-4.5
perplexity/xai/grok-4.5
|
Perplexity | $2.00 | $6.00 | $0.3000 | — | — | text |
|
perplexity/xai/grok-4.6
perplexity/xai/grok-4.6
|
Perplexity | $2.00 | $6.00 | $0.5000 | — | — | text |
|
pinstripes/ps/deepseek-v4-flash
pinstripes/ps/deepseek-v4-flash
|
Pinstripes | $0.1000 | $0.2000 | — | — | 163,840 | text |
|
pinstripes/ps/glm-4.5-air
pinstripes/ps/glm-4.5-air
|
Pinstripes | $0.1250 | $0.4500 | — | — | 128,000 | text |
|
pinstripes/ps/minimax-m2.7
pinstripes/ps/minimax-m2.7
|
Pinstripes | $0.2550 | $0.5500 | — | — | 1,000,192 | text |
|
pinstripes/ps/qwen3-30b-a3b
pinstripes/ps/qwen3-30b-a3b
|
Pinstripes | $0.0900 | $0.2000 | — | — | 131,072 | text |
|
pinstripes/ps/qwen3-coder-30b-a3b
pinstripes/ps/qwen3-coder-30b-a3b
|
Pinstripes | $0.3000 | $0.6000 | — | — | 131,072 | text |
|
pinstripes/ps/qwen3.6-35b-a3b
pinstripes/ps/qwen3.6-35b-a3b
|
Pinstripes | $0.1400 | $0.4500 | — | — | 131,072 | text |
|
publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT
publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT
|
Publicai | $0.0000 | $0.0000 | — | — | 8,192 | text |
|
publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT
publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT
|
Publicai | $0.0000 | $0.0000 | — | — | 32,768 | text |
|
publicai/allenai/Olmo-3-32B-Think
publicai/allenai/Olmo-3-32B-Think
|
Publicai | $0.0000 | $0.0000 | — | — | 32,768 | text |
|
publicai/allenai/Olmo-3-7B-Instruct
publicai/allenai/Olmo-3-7B-Instruct
|
Publicai | $0.0000 | $0.0000 | — | — | 32,768 | text |
|
publicai/allenai/Olmo-3-7B-Think
publicai/allenai/Olmo-3-7B-Think
|
Publicai | $0.0000 | $0.0000 | — | — | 32,768 | text |
|
publicai/BSC-LT/ALIA-40b-instruct_Q8_0
publicai/BSC-LT/ALIA-40b-instruct_Q8_0
|
Publicai | $0.0000 | $0.0000 | — | — | 8,192 | text |
|
publicai/BSC-LT/salamandra-7b-instruct-tools-16k
publicai/BSC-LT/salamandra-7b-instruct-tools-16k
|
Publicai | $0.0000 | $0.0000 | — | — | 16,384 | text |
|
publicai/swiss-ai/apertus-70b-instruct
publicai/swiss-ai/apertus-70b-instruct
|
Publicai | $0.0000 | $0.0000 | — | — | 8,192 | text |
|
publicai/swiss-ai/apertus-8b-instruct
publicai/swiss-ai/apertus-8b-instruct
|
Publicai | $0.0000 | $0.0000 | — | — | 8,192 | text |
|
qwen_ai_platform/deepseek-v4-flash
qwen_ai_platform/deepseek-v4-flash
|
Qwen Ai Platform | $0.2000 | $0.4000 | $0.0400 | — | 1,000,000 | text |
|
qwen_ai_platform/deepseek-v4-flash-0731
qwen_ai_platform/deepseek-v4-flash-0731
|
Qwen Ai Platform | $0.2000 | $0.4000 | $0.0400 | — | 1,000,000 | text |
|
qwen_ai_platform/deepseek-v4-pro
qwen_ai_platform/deepseek-v4-pro
|
Qwen Ai Platform | $2.40 | $4.80 | $0.2000 | — | 1,000,000 | text |
|
qwen_ai_platform/glm-5.1
qwen_ai_platform/glm-5.1
|
Qwen Ai Platform | $1.40 | $4.40 | $0.2600 | — | 202,745 | text |
|
qwen_ai_platform/glm-5.2
qwen_ai_platform/glm-5.2
|
Qwen Ai Platform | $1.40 | $4.40 | $0.2800 | — | 1,048,576 | text |
|
qwen_ai_platform/kimi-k2.7-code
qwen_ai_platform/kimi-k2.7-code
|
Qwen Ai Platform | $0.9500 | $4.00 | $0.1900 | — | 229,376 | text |
|
qwen_ai_platform/qwen-coder
qwen_ai_platform/qwen-coder
|
Qwen Ai Platform | $0.3000 | $1.50 | — | — | 1,000,000 | text |
|
qwen_ai_platform/qwen-max
qwen_ai_platform/qwen-max
|
Qwen Ai Platform | $1.60 | $6.40 | — | — | 30,720 | text |
|
qwen_ai_platform/qwen-plus
qwen_ai_platform/qwen-plus
|
Qwen Ai Platform | $0.4000 | $1.20 | — | — | 129,024 | text |
|
qwen_ai_platform/qwen-plus-2025-01-25
qwen_ai_platform/qwen-plus-2025-01-25
|
Qwen Ai Platform | $0.4000 | $1.20 | — | — | 129,024 | text |
|
qwen_ai_platform/qwen-plus-2025-04-28
qwen_ai_platform/qwen-plus-2025-04-28
|
Qwen Ai Platform | $0.4000 | $1.20 | — | — | 129,024 | text |
|
qwen_ai_platform/qwen-plus-2025-07-14
qwen_ai_platform/qwen-plus-2025-07-14
|
Qwen Ai Platform | $0.4000 | $1.20 | — | — | 129,024 | text |
|
qwen_ai_platform/qwen-turbo
qwen_ai_platform/qwen-turbo
|
Qwen Ai Platform | $0.0500 | $0.2000 | — | — | 129,024 | text |
|
qwen_ai_platform/qwen-turbo-2024-11-01
qwen_ai_platform/qwen-turbo-2024-11-01
|
Qwen Ai Platform | $0.0500 | $0.2000 | — | — | 1,000,000 | text |
|
qwen_ai_platform/qwen-turbo-2025-04-28
qwen_ai_platform/qwen-turbo-2025-04-28
|
Qwen Ai Platform | $0.0500 | $0.2000 | — | — | 1,000,000 | text |
|
qwen_ai_platform/qwen-turbo-latest
qwen_ai_platform/qwen-turbo-latest
|
Qwen Ai Platform | $0.0500 | $0.2000 | — | — | 1,000,000 | text |
|
qwen_ai_platform/qwen3-next-80b-a3b-instruct
qwen_ai_platform/qwen3-next-80b-a3b-instruct
|
Qwen Ai Platform | $0.1500 | $1.20 | — | — | 262,144 | text |
|
qwen_ai_platform/qwen3-next-80b-a3b-thinking
qwen_ai_platform/qwen3-next-80b-a3b-thinking
|
Qwen Ai Platform | $0.1500 | $1.20 | — | — | 262,144 | text |
|
qwen_ai_platform/qwen3-vl-235b-a22b-instruct
qwen_ai_platform/qwen3-vl-235b-a22b-instruct
|
Qwen Ai Platform | $0.4000 | $1.60 | — | — | 131,072 | text |
|
qwen_ai_platform/qwen3-vl-235b-a22b-thinking
qwen_ai_platform/qwen3-vl-235b-a22b-thinking
|
Qwen Ai Platform | $0.4000 | $4.00 | — | — | 131,072 | text |
|
qwen_ai_platform/qwen3-vl-32b-instruct
qwen_ai_platform/qwen3-vl-32b-instruct
|
Qwen Ai Platform | $0.1600 | $0.6400 | — | — | 131,072 | text |
|
qwen_ai_platform/qwen3-vl-32b-thinking
qwen_ai_platform/qwen3-vl-32b-thinking
|
Qwen Ai Platform | $0.1600 | $2.87 | — | — | 131,072 | text |
|
qwen_ai_platform/qwen3.7-max
qwen_ai_platform/qwen3.7-max
|
Qwen Ai Platform | $2.50 | $7.50 | $0.5000 | — | 991,808 | text |
|
qwen_ai_platform/qwen3.8-flash
qwen_ai_platform/qwen3.8-flash
|
Qwen Ai Platform | $0.1500 | $0.4700 | $0.0160 | $0.2000 | 991,808 | text |
|
qwen_ai_platform/qwen3.8-max
qwen_ai_platform/qwen3.8-max
|
Qwen Ai Platform | $2.00 | $6.00 | $0.2500 | — | 991,808 | text |
|
qwen_ai_platform/qwen3.8-omni-flash
qwen_ai_platform/qwen3.8-omni-flash
|
Qwen Ai Platform | $0.1500 | $0.4700 | $0.0160 | — | 991,808 | text |
|
qwen_ai_platform/qwq-plus
qwen_ai_platform/qwq-plus
|
Qwen Ai Platform | $0.8000 | $2.40 | — | — | 98,304 | text |
|
qwencloud/deepseek-v4-flash
qwencloud/deepseek-v4-flash
|
Qwencloud | $0.2000 | $0.4000 | $0.0400 | — | 1,000,000 | text |
|
qwencloud/deepseek-v4-flash-0731
qwencloud/deepseek-v4-flash-0731
|
Qwencloud | $0.2000 | $0.4000 | $0.0400 | — | 1,000,000 | text |
|
qwencloud/deepseek-v4-pro
qwencloud/deepseek-v4-pro
|
Qwencloud | $2.40 | $4.80 | $0.2000 | — | 1,000,000 | text |
|
qwencloud/glm-5.1
qwencloud/glm-5.1
|
Qwencloud | $1.40 | $4.40 | $0.2600 | — | 202,745 | text |
|
qwencloud/glm-5.2
qwencloud/glm-5.2
|
Qwencloud | $1.40 | $4.40 | $0.2800 | — | 1,048,576 | text |
|
qwencloud/kimi-k2.7-code
qwencloud/kimi-k2.7-code
|
Qwencloud | $0.9500 | $4.00 | $0.1900 | — | 229,376 | text |
|
qwencloud/qwen-coder
qwencloud/qwen-coder
|
Qwencloud | $0.3000 | $1.50 | — | — | 1,000,000 | text |
|
qwencloud/qwen-max
qwencloud/qwen-max
|
Qwencloud | $1.60 | $6.40 | — | — | 30,720 | text |
|
qwencloud/qwen-plus
qwencloud/qwen-plus
|
Qwencloud | $0.4000 | $1.20 | — | — | 129,024 | text |
|
qwencloud/qwen-plus-2025-01-25
qwencloud/qwen-plus-2025-01-25
|
Qwencloud | $0.4000 | $1.20 | — | — | 129,024 | text |
|
qwencloud/qwen-plus-2025-04-28
qwencloud/qwen-plus-2025-04-28
|
Qwencloud | $0.4000 | $1.20 | — | — | 129,024 | text |
|
qwencloud/qwen-plus-2025-07-14
qwencloud/qwen-plus-2025-07-14
|
Qwencloud | $0.4000 | $1.20 | — | — | 129,024 | text |
|
qwencloud/qwen-turbo
qwencloud/qwen-turbo
|
Qwencloud | $0.0500 | $0.2000 | — | — | 129,024 | 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.