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

2,001

Providers

Modes

Browse by Provider

View all models from a specific provider

All Models

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

Showing 100 of 2001 models

Model Name↑	Provider	Mode	InputCost (per 1M tokens)	OutputCost (per 1M tokens)	Max Input Tokens	Max Output Tokens	Capabilities
chat-bison palm/chat-bison	PaLM	Chat	$0.13	$0.13	8,192	4,096
chat-bison-001 palm/chat-bison-001	PaLM	Chat	$0.13	$0.13	8,192	4,096
claude-3.5-haiku replicate/anthropic/claude-3.5-haiku	Replicate	Chat	$1.00	$5.00	—	—	FunctionsVision
claude-3.5-sonnet replicate/anthropic/claude-3.5-sonnet	Replicate	Chat	$3.75	$18.75	—	—	FunctionsVision
claude-3.7-sonnet replicate/anthropic/claude-3.7-sonnet	Replicate	Chat	$3.00	$15.00	—	—	FunctionsVision
claude-4-sonnet replicate/anthropic/claude-4-sonnet	Replicate	Chat	$3.00	$15.00	—	—	FunctionsVision
claude-4.5-haiku replicate/anthropic/claude-4.5-haiku	Replicate	Chat	$1.00	$5.00	—	—	FunctionsVision
claude-4.5-sonnet replicate/anthropic/claude-4.5-sonnet	Replicate	Chat	$3.00	$15.00	—	—	FunctionsVision
codellama-34b-instruct perplexity/codellama-34b-instruct	Perplexity	Chat	$0.35	$1.40	16,384	16,384
codellama-70b-instruct perplexity/codellama-70b-instruct	Perplexity	Chat	$0.70	$2.80	16,384	16,384
deepseek-r1 replicate/deepseek-ai/deepseek-r1	Replicate	Chat	$3.75	$10.00	65,536	8,192	Reasoning
DeepSeek-R1 sambanova/DeepSeek-R1	SambaNova	Chat	$5.00	$7.00	32,768	32,768
DeepSeek-R1-Distill-Llama-70B sambanova/DeepSeek-R1-Distill-Llama-70B	SambaNova	Chat	$0.70	$1.40	131k	131k
deepseek-v3 replicate/deepseek-ai/deepseek-v3	Replicate	Chat	$1.45	$1.45	65,536	8,192	Functions
DeepSeek-V3-0324 sambanova/DeepSeek-V3-0324	SambaNova	Chat	$3.00	$4.50	32,768	32,768	FunctionsReasoning
deepseek-v3.1 replicate/deepseek-ai/deepseek-v3.1	Replicate	Chat	$0.67	$2.02	164k	164k	FunctionsReasoning
DeepSeek-V3.1 sambanova/DeepSeek-V3.1	SambaNova	Chat	$3.00	$4.50	32,768	32,768	FunctionsReasoning
gemini-2.5-flash replicate/google/gemini-2.5-flash	Replicate	Chat	$2.50	$2.50	—	—	FunctionsVision
gemini-3-pro replicate/google/gemini-3-pro	Replicate	Chat	$2.00	$12.00	—	—	FunctionsVision
gpt-4.1 replicate/openai/gpt-4.1	Replicate	Chat	$2.00	$8.00	—	—	FunctionsVision
gpt-4.1-mini replicate/openai/gpt-4.1-mini	Replicate	Chat	$0.40	$1.60	—	—	FunctionsVision
gpt-4.1-nano replicate/openai/gpt-4.1-nano	Replicate	Chat	$0.10	$0.40	—	—	Functions
gpt-4o replicate/openai/gpt-4o	Replicate	Chat	$2.50	$10.00	—	—	FunctionsVisionAudio InAudio Out
gpt-4o-mini replicate/openai/gpt-4o-mini	Replicate	Chat	$0.15	$0.60	—	—	FunctionsVision
gpt-5 replicate/openai/gpt-5	Replicate	Chat	$1.25	$10.00	—	—	FunctionsVision
gpt-5-mini replicate/openai/gpt-5-mini	Replicate	Chat	$0.25	$2.00	—	—	FunctionsVision
gpt-5-nano replicate/openai/gpt-5-nano	Replicate	Chat	$0.05	$0.40	—	—	Functions
gpt-oss-120b ovhcloud/gpt-oss-120b	Ovhcloud	Chat	$0.08	$0.40	131k	131k	Reasoning
gpt-oss-120b replicate/openai/gpt-oss-120b	Replicate	Chat	$0.18	$0.72	—	—	Functions
gpt-oss-120b sambanova/gpt-oss-120b	SambaNova	Chat	$3.00	$4.50	131k	131k	FunctionsReasoning
gpt-oss-20b ovhcloud/gpt-oss-20b	Ovhcloud	Chat	$0.04	$0.15	131k	131k	Reasoning
gpt-oss-20b replicateopenai/gpt-oss-20b	Replicate	Chat	$0.09	$0.36	—	—	Functions
granite-3.3-8b-instruct replicate/ibm-granite/granite-3.3-8b-instruct	Replicate	Chat	$0.03	$0.25	—	—	Functions
grok-4 replicate/xai/grok-4	Replicate	Chat	$7.20	$36.00	—	—	Functions
llama-2-13b replicate/meta/llama-2-13b	Replicate	Chat	$0.10	$0.50	4,096	4,096
llama-2-13b-chat replicate/meta/llama-2-13b-chat	Replicate	Chat	$0.10	$0.50	4,096	4,096
llama-2-70b replicate/meta/llama-2-70b	Replicate	Chat	$0.65	$2.75	4,096	4,096
llama-2-70b-chat perplexity/llama-2-70b-chat	Perplexity	Chat	$0.70	$2.80	4,096	4,096
llama-2-70b-chat replicate/meta/llama-2-70b-chat	Replicate	Chat	$0.65	$2.75	4,096	4,096
llama-2-7b replicate/meta/llama-2-7b	Replicate	Chat	$0.05	$0.25	4,096	4,096
llama-2-7b-chat replicate/meta/llama-2-7b-chat	Replicate	Chat	$0.05	$0.25	4,096	4,096
llama-3-70b replicate/meta/llama-3-70b	Replicate	Chat	$0.65	$2.75	8,192	8,192
llama-3-70b-instruct replicate/meta/llama-3-70b-instruct	Replicate	Chat	$0.65	$2.75	8,192	8,192
llama-3-8b replicate/meta/llama-3-8b	Replicate	Chat	$0.05	$0.25	8,086	8,086
llama-3-8b-instruct replicate/meta/llama-3-8b-instruct	Replicate	Chat	$0.05	$0.25	8,086	8,086
llama-3.1-70b-instruct perplexity/llama-3.1-70b-instruct	Perplexity	Chat	$1.00	$1.00	131k	131k
llama-3.1-8b-instruct perplexity/llama-3.1-8b-instruct	Perplexity	Chat	$0.20	$0.20	131k	131k
Llama-4-Maverick-17B-128E-Instruct sambanova/Llama-4-Maverick-17B-128E-Instruct	SambaNova	Chat	$0.63	$1.80	131k	131k	FunctionsVision
Llama-4-Scout-17B-16E-Instruct sambanova/Llama-4-Scout-17B-16E-Instruct	SambaNova	Chat	$0.40	$0.70	8,192	8,192	Functions
llava-v1.6-mistral-7b-hf ovhcloud/llava-v1.6-mistral-7b-hf	Ovhcloud	Chat	$0.29	$0.29	32,000	32,000	Vision
mamba-codestral-7B-v0.1 ovhcloud/mamba-codestral-7B-v0.1	Ovhcloud	Chat	$0.19	$0.19	256k	256k
Meta-Llama-3.1-405B-Instruct sambanova/Meta-Llama-3.1-405B-Instruct	SambaNova	Chat	$5.00	$10.00	16,384	16,384	Functions
Meta-Llama-3.1-8B-Instruct sambanova/Meta-Llama-3.1-8B-Instruct	SambaNova	Chat	$0.10	$0.20	16,384	16,384	Functions
Meta-Llama-3.2-1B-Instruct sambanova/Meta-Llama-3.2-1B-Instruct	SambaNova	Chat	$0.04	$0.08	16,384	16,384
Meta-Llama-3.2-3B-Instruct sambanova/Meta-Llama-3.2-3B-Instruct	SambaNova	Chat	$0.08	$0.16	4,096	4,096
Meta-Llama-3.3-70B-Instruct sambanova/Meta-Llama-3.3-70B-Instruct	SambaNova	Chat	$0.60	$1.20	131k	131k	Functions
Meta-Llama-Guard-3-8B sambanova/Meta-Llama-Guard-3-8B	SambaNova	Chat	$0.30	$0.30	16,384	16,384
mistral-7b-instruct perplexity/mistral-7b-instruct	Perplexity	Chat	$0.07	$0.28	4,096	4,096
mistral-7b-instruct-v0.2 replicate/mistralai/mistral-7b-instruct-v0.2	Replicate	Chat	$0.05	$0.25	4,096	4,096
mistral-7b-v0.1 replicate/mistralai/mistral-7b-v0.1	Replicate	Chat	$0.05	$0.25	4,096	4,096
mixtral-8x7b-instruct perplexity/mixtral-8x7b-instruct	Perplexity	Chat	$0.07	$0.28	4,096	4,096
mixtral-8x7b-instruct-v0.1 replicate/mistralai/mixtral-8x7b-instruct-v0.1	Replicate	Chat	$0.30	$1.00	4,096	4,096
Mixtral-8x7B-Instruct-v0.1 ovhcloud/Mixtral-8x7B-Instruct-v0.1	Ovhcloud	Chat	$0.63	$0.63	32,000	32,000
o1 replicate/openai/o1	Replicate	Chat	$15.00	$60.00	—	—	Reasoning
o1-mini replicate/openai/o1-mini	Replicate	Chat	$1.10	$4.40	—	—	Reasoning
o4-mini replicate/openai/o4-mini	Replicate	Chat	$1.00	$4.00	—	—	Reasoning
pplx-70b-chat perplexity/pplx-70b-chat	Perplexity	Chat	$0.70	$2.80	4,096	4,096
pplx-70b-online perplexity/pplx-70b-online	Perplexity	Chat	—	$2.80	4,096	4,096
pplx-7b-chat perplexity/pplx-7b-chat	Perplexity	Chat	$0.07	$0.28	8,192	8,192
pplx-7b-online perplexity/pplx-7b-online	Perplexity	Chat	—	$0.28	4,096	4,096
pplx-embed-v1-4b perplexity/pplx-embed-v1-4b	Perplexity	Embedding	$0.03	—	32,768	—
qwen.qwen3-235b-a22b-2507-v1:0 qwen.qwen3-235b-a22b-2507-v1:0	AWS Bedrock	Chat	$0.22	$0.88	262k	131k	FunctionsReasoning
qwen.qwen3-32b-v1:0 qwen.qwen3-32b-v1:0	AWS Bedrock	Chat	$0.15	$0.60	131k	16,384	FunctionsReasoning
qwen.qwen3-coder-30b-a3b-v1:0 qwen.qwen3-coder-30b-a3b-v1:0	AWS Bedrock	Chat	$0.15	$0.60	262k	131k	FunctionsReasoning
qwen.qwen3-coder-480b-a35b-v1:0 qwen.qwen3-coder-480b-a35b-v1:0	AWS Bedrock	Chat	$0.22	$1.80	262k	65,536	FunctionsReasoning
qwen.qwen3-coder-next qwen.qwen3-coder-next	AWS Bedrock	Chat	$0.50	$1.20	262k	8,192	Functions
qwen.qwen3-next-80b-a3b qwen.qwen3-next-80b-a3b	AWS Bedrock	Chat	$0.15	$1.20	128k	8,192	Functions
qwen.qwen3-vl-235b-a22b qwen.qwen3-vl-235b-a22b	AWS Bedrock	Chat	$0.53	$2.66	128k	8,192	FunctionsVision
Qwen2-Audio-7B-Instruct sambanova/Qwen2-Audio-7B-Instruct	SambaNova	Chat	$0.50	$100.00	4,096	4,096	Audio In
Qwen2.5-Coder-32B-Instruct ovhcloud/Qwen2.5-Coder-32B-Instruct	Ovhcloud	Chat	$0.87	$0.87	32,000	32,000
Qwen2.5-VL-72B-Instruct ovhcloud/Qwen2.5-VL-72B-Instruct	Ovhcloud	Chat	$0.91	$0.91	32,000	32,000	Vision
qwen3-235b-a22b-instruct-2507 replicate/qwen/qwen3-235b-a22b-instruct-2507	Replicate	Chat	$0.26	$1.06	—	—	Functions
Qwen3-32B ovhcloud/Qwen3-32B	Ovhcloud	Chat	$0.08	$0.23	32,000	32,000	FunctionsReasoning
Qwen3-32B sambanova/Qwen3-32B	SambaNova	Chat	$0.40	$0.80	8,192	8,192	FunctionsReasoning
QwQ-32B sambanova/QwQ-32B	SambaNova	Chat	$0.50	$1.00	16,384	16,384
sonar perplexity/sonar	Perplexity	Chat	$1.00	$1.00	128k	—	Web Search
sonar-deep-research perplexity/sonar-deep-research	Perplexity	Chat	$2.00	$8.00	128k	—	ReasoningWeb Search
sonar-medium-chat perplexity/sonar-medium-chat	Perplexity	Chat	$0.60	$1.80	16,384	16,384
sonar-medium-online perplexity/sonar-medium-online	Perplexity	Chat	—	$1.80	12,000	12,000
sonar-pro perplexity/sonar-pro	Perplexity	Chat	$3.00	$15.00	200k	8,000	Web Search
sonar-reasoning perplexity/sonar-reasoning	Perplexity	Chat	$1.00	$5.00	128k	—	ReasoningWeb Search
sonar-reasoning-pro perplexity/sonar-reasoning-pro	Perplexity	Chat	$2.00	$8.00	128k	—	ReasoningWeb Search
sonar-small-chat perplexity/sonar-small-chat	Perplexity	Chat	$0.07	$0.28	16,384	16,384
sonar-small-online perplexity/sonar-small-online	Perplexity	Chat	—	$0.28	12,000	12,000
text-bison palm/text-bison	PaLM	Completion	$0.13	$0.13	8,192	1,024
text-bison-001 palm/text-bison-001	PaLM	Completion	$0.13	$0.13	8,192	1,024
text-bison-safety-off palm/text-bison-safety-off	PaLM	Completion	$0.13	$0.13	8,192	1,024
text-bison-safety-recitation-off palm/text-bison-safety-recitation-off	PaLM	Completion	$0.13	$0.13	8,192	1,024
text-embedding-004 text-embedding-004	Vertex AI	Embedding	$0.10	—	2,048	—
text-embedding-005 text-embedding-005	Vertex AI	Embedding	$0.10	—	2,048	—

Showing 1,201–1,300 of 2,001

Calculate LLM API Costs

Browse by Provider

All Models

[ Features ]

[ Developers ]

[ Resources ]

[ Company ]