LLM Model Prices

Glama chat pricing is calculated using the official rates from our model and service providers. These prices are passed through without any additional fees per token.

In the event that you discover a price discrepancy, please let us know at support@glama.ai. We will investigate and correct billing retroactively.

Last updated: 2024-11-21T02:02:14.601Z

Free Chat Cost Calculator API for LLMs or JSON.

Provider	Model	Max Tokens		USD / Token
Provider	Model	Input	Output	Input	Output
anthropic	claude-2	100000	8191	0.0000080000	0.0000240000
anthropic	claude-2.1	200000	8191	0.0000080000	0.0000240000
anthropic	claude-3-5-haiku-20241022	200000	8192	0.0000010000	0.0000050000
anthropic	claude-3-5-sonnet-20240620	200000	8192	0.0000030000	0.0000150000
anthropic	claude-3-5-sonnet-20241022	200000	8192	0.0000030000	0.0000150000
anthropic	claude-3-haiku-20240307	200000	4096	0.0000002500	0.0000012500
anthropic	claude-3-opus-20240229	200000	4096	0.0000150000	0.0000750000
anthropic	claude-3-sonnet-20240229	200000	4096	0.0000030000	0.0000150000
anthropic	claude-instant-1	100000	8191	0.0000016300	0.0000055100
anthropic	claude-instant-1.2	100000	8191	0.0000001630	0.0000005510
azure	command-r-plus	128000	4096	0.0000030000	0.0000150000
azure	global-standard/gpt-4o-2024-08-06	128000	16384	0.0000025000	0.0000100000
azure	global-standard/gpt-4o-mini	128000	16384	0.0000001500	0.0000006000
azure	gpt-35-turbo	4097	4096	0.0000005000	0.0000015000
azure	gpt-35-turbo-0125	16384	4096	0.0000005000	0.0000015000
azure	gpt-35-turbo-0301	4097	4096	0.0000002000	0.0000020000
azure	gpt-35-turbo-0613	4097	4096	0.0000015000	0.0000020000
azure	gpt-35-turbo-1106	16384	4096	0.0000010000	0.0000020000
azure	gpt-35-turbo-16k	16385	4096	0.0000030000	0.0000040000
azure	gpt-35-turbo-16k-0613	16385	4096	0.0000030000	0.0000040000
azure	gpt-4	8192	4096	0.0000300000	0.0000600000
azure	gpt-4-0125-preview	128000	4096	0.0000100000	0.0000300000
azure	gpt-4-0613	8192	4096	0.0000300000	0.0000600000
azure	gpt-4-1106-preview	128000	4096	0.0000100000	0.0000300000
azure	gpt-4-32k	32768	4096	0.0000600000	0.0001200000
azure	gpt-4-32k-0613	32768	4096	0.0000600000	0.0001200000
azure	gpt-4-turbo	128000	4096	0.0000100000	0.0000300000
azure	gpt-4-turbo-2024-04-09	128000	4096	0.0000100000	0.0000300000
azure	gpt-4-turbo-vision-preview	128000	4096	0.0000100000	0.0000300000
azure	gpt-4o	128000	4096	0.0000050000	0.0000150000
azure	gpt-4o-2024-05-13	128000	4096	0.0000050000	0.0000150000
azure	gpt-4o-2024-08-06	128000	16384	0.0000027500	0.0000110000
azure	gpt-4o-mini	128000	16384	0.0000001650	0.0000006600
azure	gpt-4o-mini-2024-07-18	128000	16384	0.0000001650	0.0000006600
azure	o1-mini	128000	65536	0.0000030000	0.0000120000
azure	o1-mini-2024-09-12	128000	65536	0.0000030000	0.0000120000
azure	o1-preview	128000	32768	0.0000150000	0.0000600000
azure	o1-preview-2024-09-12	128000	32768	0.0000150000	0.0000600000
google	gemini-1.0-pro	32760	8192	0.0000005000	0.0000015000
google	gemini-1.0-pro-001	32760	8192	0.0000005000	0.0000015000
google	gemini-1.0-pro-002	32760	8192	0.0000005000	0.0000015000
google	gemini-1.0-pro-vision	16384	2048	0.0000002500	0.0000005000
google	gemini-1.0-pro-vision-001	16384	2048	0.0000002500	0.0000005000
google	gemini-1.0-ultra	8192	2048	0.0000005000	0.0000015000
google	gemini-1.0-ultra-001	8192	2048	0.0000005000	0.0000015000
google	gemini-1.5-flash	1000000	8192	0.0000000750	0.0000003000
google	gemini-1.5-flash-001	1000000	8192	0.0000000750	0.0000003000
google	gemini-1.5-flash-002	1048576	8192	0.0000000750	0.0000003000
google	gemini-1.5-flash-exp-0827	1000000	8192	0.0000000047	0.0000000047
google	gemini-1.5-flash-preview-0514	1000000	8192	0.0000000750	0.0000000047
google	gemini-1.5-pro	2097152	8192	0.0000012500	0.0000050000
google	gemini-1.5-pro-001	1000000	8192	0.0000012500	0.0000050000
google	gemini-1.5-pro-002	2097152	8192	0.0000012500	0.0000050000
google	gemini-1.5-pro-preview-0215	1000000	8192	0.0000000781	0.0000003125
google	gemini-1.5-pro-preview-0409	1000000	8192	0.0000000781	0.0000003125
google	gemini-1.5-pro-preview-0514	1000000	8192	0.0000000781	0.0000003125
google	gemini-pro	32760	8192	0.0000005000	0.0000015000
google	gemini-pro-vision	16384	2048	0.0000002500	0.0000005000
groq	gemma-7b-it	8192	8192	0.0000000700	0.0000000700
groq	gemma2-9b-it	8192	8192	0.0000002000	0.0000002000
groq	llama-3.1-405b-reasoning	8192	8192	0.0000005900	0.0000007900
groq	llama-3.1-70b-versatile	8192	8192	0.0000005900	0.0000007900
groq	llama-3.1-8b-instant	8192	8192	0.0000000500	0.0000000800
groq	llama2-70b-4096	4096	4096	0.0000007000	0.0000008000
groq	llama3-70b-8192	8192	8192	0.0000005900	0.0000007900
groq	llama3-8b-8192	8192	8192	0.0000000500	0.0000000800
groq	llama3-groq-70b-8192-tool-use-preview	8192	8192	0.0000008900	0.0000008900
groq	llama3-groq-8b-8192-tool-use-preview	8192	8192	0.0000001900	0.0000001900
groq	mixtral-8x7b-32768	32768	32768	0.0000002400	0.0000002400
mistral	codestral-2405	32000	8191	0.0000010000	0.0000030000
mistral	codestral-latest	32000	8191	0.0000010000	0.0000030000
mistral	codestral-mamba-latest	256000	256000	0.0000002500	0.0000002500
mistral	mistral-large-2402	32000	8191	0.0000040000	0.0000120000
mistral	mistral-large-2407	128000	128000	0.0000030000	0.0000090000
mistral	mistral-large-latest	128000	128000	0.0000030000	0.0000090000
mistral	mistral-medium	32000	8191	0.0000027000	0.0000081000
mistral	mistral-medium-2312	32000	8191	0.0000027000	0.0000081000
mistral	mistral-medium-latest	32000	8191	0.0000027000	0.0000081000
mistral	mistral-small	32000	8191	0.0000010000	0.0000030000
mistral	mistral-small-latest	32000	8191	0.0000010000	0.0000030000
mistral	mistral-tiny	32000	8191	0.0000002500	0.0000002500
mistral	open-codestral-mamba	256000	256000	0.0000002500	0.0000002500
mistral	open-mistral-7b	32000	8191	0.0000002500	0.0000002500
mistral	open-mistral-nemo	128000	128000	0.0000003000	0.0000003000
mistral	open-mistral-nemo-2407	128000	128000	0.0000003000	0.0000003000
mistral	open-mixtral-8x22b	64000	8191	0.0000020000	0.0000060000
mistral	open-mixtral-8x7b	32000	8191	0.0000007000	0.0000007000
mistral	pixtral-12b-2409	128000	128000	0.0000001500	0.0000001500
openai	gpt-3.5-turbo	16385	4096	0.0000015000	0.0000020000
openai	gpt-3.5-turbo-0125	16385	4096	0.0000005000	0.0000015000
openai	gpt-3.5-turbo-0301	4097	4096	0.0000015000	0.0000020000
openai	gpt-3.5-turbo-0613	4097	4096	0.0000015000	0.0000020000
openai	gpt-3.5-turbo-1106	16385	4096	0.0000010000	0.0000020000
openai	gpt-3.5-turbo-16k	16385	4096	0.0000030000	0.0000040000
openai	gpt-3.5-turbo-16k-0613	16385	4096	0.0000030000	0.0000040000
openai	gpt-4	8192	4096	0.0000300000	0.0000600000
openai	gpt-4-0125-preview	128000	4096	0.0000100000	0.0000300000
openai	gpt-4-0314	8192	4096	0.0000300000	0.0000600000
openai	gpt-4-0613	8192	4096	0.0000300000	0.0000600000
openai	gpt-4-1106-preview	128000	4096	0.0000100000	0.0000300000
openai	gpt-4-1106-vision-preview	128000	4096	0.0000100000	0.0000300000
openai	gpt-4-32k	32768	4096	0.0000600000	0.0001200000
openai	gpt-4-32k-0314	32768	4096	0.0000600000	0.0001200000
openai	gpt-4-32k-0613	32768	4096	0.0000600000	0.0001200000
openai	gpt-4-turbo	128000	4096	0.0000100000	0.0000300000
openai	gpt-4-turbo-2024-04-09	128000	4096	0.0000100000	0.0000300000
openai	gpt-4-turbo-preview	128000	4096	0.0000100000	0.0000300000
openai	gpt-4-vision-preview	128000	4096	0.0000100000	0.0000300000
openai	gpt-4o	128000	16384	0.0000025000	0.0000100000
openai	gpt-4o-2024-05-13	128000	4096	0.0000050000	0.0000150000
openai	gpt-4o-2024-08-06	128000	16384	0.0000025000	0.0000100000
openai	gpt-4o-audio-preview	128000	16384	0.0000025000	0.0000100000
openai	gpt-4o-audio-preview-2024-10-01	128000	16384	0.0000025000	0.0000100000
openai	gpt-4o-mini	128000	16384	0.0000001500	0.0000006000
openai	gpt-4o-mini-2024-07-18	128000	16384	0.0000001500	0.0000006000
openai	o1-mini	128000	65536	0.0000030000	0.0000120000
openai	o1-mini-2024-09-12	128000	65536	0.0000030000	0.0000120000
openai	o1-preview	128000	32768	0.0000150000	0.0000600000
openai	o1-preview-2024-09-12	128000	32768	0.0000150000	0.0000600000
perplexity	codellama-34b-instruct	16384	16384	0.0000003500	0.0000014000
perplexity	codellama-70b-instruct	16384	16384	0.0000007000	0.0000028000
perplexity	llama-2-70b-chat	4096	4096	0.0000007000	0.0000028000
perplexity	llama-3.1-70b-instruct	131072	131072	0.0000010000	0.0000010000
perplexity	llama-3.1-8b-instruct	131072	131072	0.0000002000	0.0000002000
perplexity	llama-3.1-sonar-huge-128k-online	127072	127072	0.0000050000	0.0000050000
perplexity	llama-3.1-sonar-large-128k-chat	131072	131072	0.0000010000	0.0000010000
perplexity	llama-3.1-sonar-large-128k-online	127072	127072	0.0000010000	0.0000010000
perplexity	llama-3.1-sonar-small-128k-chat	131072	131072	0.0000002000	0.0000002000
perplexity	llama-3.1-sonar-small-128k-online	127072	127072	0.0000002000	0.0000002000
perplexity	mistral-7b-instruct	4096	4096	0.0000000700	0.0000002800
perplexity	mixtral-8x7b-instruct	4096	4096	0.0000000700	0.0000002800
perplexity	pplx-70b-chat	4096	4096	0.0000007000	0.0000028000
perplexity	pplx-7b-chat	8192	8192	0.0000000700	0.0000002800
perplexity	sonar-medium-chat	16384	16384	0.0000006000	0.0000018000
perplexity	sonar-small-chat	16384	16384	0.0000000700	0.0000002800
replicate	meta/llama-2-13b	4096	4096	0.0000001000	0.0000005000
replicate	meta/llama-2-13b-chat	4096	4096	0.0000001000	0.0000005000
replicate	meta/llama-2-70b	4096	4096	0.0000006500	0.0000027500
replicate	meta/llama-2-70b-chat	4096	4096	0.0000006500	0.0000027500
replicate	meta/llama-2-7b	4096	4096	0.0000000500	0.0000002500
replicate	meta/llama-2-7b-chat	4096	4096	0.0000000500	0.0000002500
replicate	meta/llama-3-70b	8192	8192	0.0000006500	0.0000027500
replicate	meta/llama-3-70b-instruct	8192	8192	0.0000006500	0.0000027500
replicate	meta/llama-3-8b	8086	8086	0.0000000500	0.0000002500
replicate	meta/llama-3-8b-instruct	8086	8086	0.0000000500	0.0000002500
replicate	mistralai/mistral-7b-instruct-v0.2	4096	4096	0.0000000500	0.0000002500
replicate	mistralai/mistral-7b-v0.1	4096	4096	0.0000000500	0.0000002500
replicate	mistralai/mixtral-8x7b-instruct-v0.1	4096	4096	0.0000003000	0.0000010000
vertex_ai	claude-3-5-haiku@20241022	200000	8192	0.0000010000	0.0000050000
vertex_ai	claude-3-5-sonnet-v2@20241022	200000	8192	0.0000030000	0.0000150000
vertex_ai	claude-3-5-sonnet@20240620	200000	8192	0.0000030000	0.0000150000
vertex_ai	claude-3-haiku@20240307	200000	4096	0.0000002500	0.0000012500
vertex_ai	claude-3-opus@20240229	200000	4096	0.0000150000	0.0000750000
vertex_ai	claude-3-sonnet@20240229	200000	4096	0.0000030000	0.0000150000
vertex_ai	codestral@2405	128000	128000	0.0000010000	0.0000030000
vertex_ai	codestral@latest	128000	128000	0.0000010000	0.0000030000
vertex_ai	jamba-1.5	256000	256000	0.0000002000	0.0000004000
vertex_ai	jamba-1.5-large	256000	256000	0.0000020000	0.0000080000
vertex_ai	jamba-1.5-large@001	256000	256000	0.0000020000	0.0000080000
vertex_ai	jamba-1.5-mini	256000	256000	0.0000002000	0.0000004000
vertex_ai	jamba-1.5-mini@001	256000	256000	0.0000002000	0.0000004000
vertex_ai	mistral-large@2407	128000	8191	0.0000030000	0.0000090000
vertex_ai	mistral-large@latest	128000	8191	0.0000030000	0.0000090000
vertex_ai	mistral-nemo@2407	128000	128000	0.0000030000	0.0000030000
vertex_ai	mistral-nemo@latest	128000	128000	0.0000030000	0.0000030000
xai	grok-beta	131072	131072	0.0000050000	0.0000150000