alihan/tokencost
1
0
Fork 0
mirror of https://github.com/AgentOps-AI/tokencost.git synced 2024-06-22 04:30:40 +03:00
Code Issues Packages Projects Releases Wiki Activity

update price table

Browse Source
This commit is contained in:
reibs
2024-01-27 14:07:22 +09:00
parent d8deebc9bc
commit 7edd16b2b3
1 changed files with 172 additions and 168 deletions
Download Patch File Download Diff File Expand all files Collapse all files

340
README.md
View File

@@ -97,175 +97,179 @@ print(count_string_tokens(prompt="Hello world", model="gpt-3.5-turbo"))
## Cost table
Units denominated in TPUs (Token Price Units = 1/10,000,000 USD). All prices can be located in `model_prices.yaml`.
| Model Name | Prompt Cost | Completion Cost | Max Prompt Tokens |
| Model Name | Prompt Cost (USD) | Completion Cost (USD) | Max Prompt Tokens |
| --- | --- | --- | --- |
| gpt-3.5-turbo | 15 | 20 | 4097 |
| gpt-3.5-turbo-instruct | 15 | 20 | 8192 |
| gpt-3.5-turbo-0301 | 15 | 20 | 4097 |
| gpt-3.5-turbo-0613 | 15 | 20 | 4097 |
| gpt-3.5-turbo-1106 | 10 | 20 | 16385 |
| gpt-3.5-turbo-16k | 30 | 40 | 16385 |
| gpt-3.5-turbo-16k-0613 | 30 | 40 | 16385 |
| gpt-4 | 300 | 600 | 8192 |
| gpt-4-0314 | 300 | 600 | 8192 |
| gpt-4-0613 | 300 | 600 | 8192 |
| gpt-4-32k | 600 | 1200 | 32768 |
| gpt-4-32k-0314 | 600 | 1200 | 32768 |
| gpt-4-32k-0613 | 600 | 1200 | 32768 |
| gpt-4-1106-preview | 100 | 300 | 128000 |
| gpt-4-vision-preview | 100 | 300 | 128000 |
| text-davinci-003 | 20 | 20 | 4097 |
| text-curie-001 | 20 | 20 | 2049 |
| text-babbage-001 | 4 | 4 | 2049 |
| text-ada-001 | 4 | 4 | 2049 |
| babbage-002 | 4 | 4 | 16384 |
| davinci-002 | 20 | 20 | 16384 |
| text-embedding-ada-002 | 1 | 0 | 8191 |
| azure/gpt-4-1106-preview | 100 | 300 | 128000 |
| azure/gpt-4-0613 | 300 | 600 | 8192 |
| azure/gpt-4-32k-0613 | 600 | 1200 | 32768 |
| azure/gpt-4-32k | 600 | 1200 | 32768 |
| azure/gpt-4 | 300 | 600 | 8192 |
| azure/gpt-35-turbo-16k-0613 | 30 | 40 | 16385 |
| azure/gpt-35-turbo-1106 | 15 | 20 | 16384 |
| azure/gpt-35-turbo-16k | 30 | 40 | 16385 |
| azure/gpt-35-turbo | 15 | 20 | 4097 |
| azure/text-embedding-ada-002 | 1 | 0 | 8191 |
| claude-instant-1 | 16 | 55 | 100000 |
| mistral/mistral-tiny | 1 | 4 | 8192 |
| mistral/mistral-small | 6 | 19 | 8192 |
| mistral/mistral-medium | 27 | 82 | 8192 |
| claude-instant-1.2 | 1 | 5 | 100000 |
| claude-2 | 80 | 240 | 100000 |
| claude-2.1 | 80 | 240 | 200000 |
| text-bison | 1 | 1 | 8192 |
| text-bison@001 | 1 | 1 | 8192 |
| text-unicorn | 100 | 280 | 8192 |
| text-unicorn@001 | 100 | 280 | 8192 |
| chat-bison | 1 | 1 | 4096 |
| chat-bison@001 | 1 | 1 | 4096 |
| chat-bison@002 | 1 | 1 | 4096 |
| chat-bison-32k | 1 | 1 | 32000 |
| code-bison | 1 | 1 | 6144 |
| code-bison@001 | 1 | 1 | 6144 |
| code-gecko@001 | 1 | 1 | 2048 |
| code-gecko@002 | 1 | 1 | 2048 |
| code-gecko | 1 | 1 | 2048 |
| codechat-bison | 1 | 1 | 6144 |
| codechat-bison@001 | 1 | 1 | 6144 |
| codechat-bison-32k | 1 | 1 | 32000 |
| gemini-pro | 2 | 5 | 30720 |
| gemini-pro-vision | 2 | 5 | 30720 |
| palm/chat-bison | 1 | 1 | 4096 |
| palm/chat-bison-001 | 1 | 1 | 4096 |
| palm/text-bison | 1 | 1 | 8196 |
| palm/text-bison-001 | 1 | 1 | 8196 |
| palm/text-bison-safety-off | 1 | 1 | 8196 |
| palm/text-bison-safety-recitation-off | 1 | 1 | 8196 |
| command-nightly | 150 | 150 | 4096 |
| command | 150 | 150 | 4096 |
| command-light | 150 | 150 | 4096 |
| command-medium-beta | 150 | 150 | 4096 |
| command-xlarge-beta | 150 | 150 | 4096 |
| openrouter/openai/gpt-3.5-turbo | 15 | 20 | 4095 |
| openrouter/openai/gpt-3.5-turbo-16k | 30 | 40 | 16383 |
| openrouter/openai/gpt-4 | 300 | 600 | 8192 |
| openrouter/anthropic/claude-instant-v1 | 16 | 55 | 100000 |
| openrouter/anthropic/claude-2 | 110 | 326 | 100000 |
| openrouter/google/palm-2-chat-bison | 5 | 5 | 8000 |
| openrouter/google/palm-2-codechat-bison | 5 | 5 | 8000 |
| openrouter/meta-llama/llama-2-13b-chat | 2 | 2 | 4096 |
| openrouter/meta-llama/llama-2-70b-chat | 15 | 15 | 4096 |
| openrouter/meta-llama/codellama-34b-instruct | 5 | 5 | 8096 |
| openrouter/nousresearch/nous-hermes-llama2-13b | 2 | 2 | 4096 |
| openrouter/mancer/weaver | 56 | 56 | 8000 |
| openrouter/gryphe/mythomax-l2-13b | 18 | 18 | 8192 |
| openrouter/jondurbin/airoboros-l2-70b-2.1 | 138 | 138 | 4096 |
| openrouter/undi95/remm-slerp-l2-13b | 18 | 18 | 6144 |
| openrouter/pygmalionai/mythalion-13b | 18 | 18 | 4096 |
| openrouter/mistralai/mistral-7b-instruct | 0 | 0 | 4096 |
| j2-ultra | 150 | 150 | 8192 |
| j2-mid | 100 | 100 | 8192 |
| j2-light | 30 | 30 | 8192 |
| dolphin | 200 | 200 | 4096 |
| chatdolphin | 200 | 200 | 4096 |
| luminous-base | 300 | 330 | 2048 |
| luminous-base-control | 374 | 412 | 2048 |
| luminous-extended | 450 | 494 | 2048 |
| luminous-extended-control | 562 | 618 | 2048 |
| luminous-supreme | 1750 | 1925 | 2048 |
| luminous-supreme-control | 2187 | 2406 | 2048 |
| ai21.j2-mid-v1 | 125 | 125 | 8191 |
| ai21.j2-ultra-v1 | 188 | 188 | 8191 |
| amazon.titan-text-lite-v1 | 3 | 4 | 8000 |
| amazon.titan-text-express-v1 | 13 | 17 | 8000 |
| anthropic.claude-v1 | 80 | 240 | 100000 |
| bedrock/us-east-1/anthropic.claude-v1 | 80 | 240 | 100000 |
| bedrock/us-west-2/anthropic.claude-v1 | 80 | 240 | 100000 |
| bedrock/ap-northeast-1/anthropic.claude-v1 | 80 | 240 | 100000 |
| bedrock/eu-central-1/anthropic.claude-v1 | 80 | 240 | 100000 |
| anthropic.claude-v2 | 80 | 240 | 100000 |
| bedrock/us-east-1/anthropic.claude-v2 | 80 | 240 | 100000 |
| bedrock/us-west-2/anthropic.claude-v2 | 80 | 240 | 100000 |
| bedrock/ap-northeast-1/anthropic.claude-v2 | 80 | 240 | 100000 |
| bedrock/eu-central-1/anthropic.claude-v2 | 80 | 240 | 100000 |
| anthropic.claude-v2:1 | 80 | 240 | 200000 |
| bedrock/us-east-1/anthropic.claude-v2:1 | 80 | 240 | 100000 |
| bedrock/us-west-2/anthropic.claude-v2:1 | 80 | 240 | 100000 |
| bedrock/ap-northeast-1/anthropic.claude-v2:1 | 80 | 240 | 100000 |
| bedrock/eu-central-1/anthropic.claude-v2:1 | 80 | 240 | 100000 |
| anthropic.claude-instant-v1 | 16 | 55 | 100000 |
| bedrock/us-east-1/anthropic.claude-instant-v1 | 8 | 24 | 100000 |
| bedrock/us-west-2/anthropic.claude-instant-v1 | 8 | 24 | 100000 |
| bedrock/ap-northeast-1/anthropic.claude-instant-v1 | 22 | 75 | 100000 |
| bedrock/eu-central-1/anthropic.claude-instant-v1 | 24 | 83 | 100000 |
| cohere.command-text-v14 | 15 | 20 | 4096 |
| cohere.command-light-text-v14 | 3 | 6 | 4000 |
| cohere.embed-english-v3 | 1 | 0 | 512 |
| cohere.embed-multilingual-v3 | 1 | 0 | 512 |
| meta.llama2-13b-chat-v1 | 7 | 10 | 4096 |
| meta.llama2-70b-chat-v1 | 19 | 25 | 4096 |
| sagemaker/meta-textgeneration-llama-2-7b | 0 | 0 | 4096 |
| sagemaker/meta-textgeneration-llama-2-7b-f | 0 | 0 | 4096 |
| sagemaker/meta-textgeneration-llama-2-13b | 0 | 0 | 4096 |
| sagemaker/meta-textgeneration-llama-2-13b-f | 0 | 0 | 4096 |
| sagemaker/meta-textgeneration-llama-2-70b | 0 | 0 | 4096 |
| sagemaker/meta-textgeneration-llama-2-70b-b-f | 0 | 0 | 4096 |
| together-ai-7.1b-20b | 4 | 4 | 1000 |
| ollama/llama2 | 0 | 0 | 4096 |
| ollama/llama2:13b | 0 | 0 | 4096 |
| ollama/llama2:70b | 0 | 0 | 4096 |
| ollama/llama2-uncensored | 0 | 0 | 4096 |
| ollama/mistral | 0 | 0 | 8192 |
| ollama/codellama | 0 | 0 | 4096 |
| ollama/orca-mini | 0 | 0 | 4096 |
| ollama/vicuna | 0 | 0 | 2048 |
| deepinfra/meta-llama/Llama-2-70b-chat-hf | 7 | 9 | 4096 |
| deepinfra/codellama/CodeLlama-34b-Instruct-hf | 6 | 6 | 4096 |
| deepinfra/meta-llama/Llama-2-13b-chat-hf | 3 | 3 | 4096 |
| deepinfra/meta-llama/Llama-2-7b-chat-hf | 2 | 2 | 4096 |
| deepinfra/mistralai/Mistral-7B-Instruct-v0.1 | 2 | 2 | 4096 |
| deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1 | 7 | 9 | 4096 |
| perplexity/pplx-7b-chat | 0 | 0 | 8192 |
| perplexity/pplx-70b-chat | 0 | 0 | 4096 |
| perplexity/pplx-7b-online | 0 | 5000 | 4096 |
| perplexity/pplx-70b-online | 0 | 5000 | 4096 |
| perplexity/llama-2-13b-chat | 0 | 0 | 4096 |
| perplexity/llama-2-70b-chat | 0 | 0 | 4096 |
| perplexity/mistral-7b-instruct | 0 | 0 | 4096 |
| perplexity/replit-code-v1.5-3b | 0 | 0 | 4096 |
| anyscale/mistralai/Mistral-7B-Instruct-v0.1 | 1 | 1 | 16384 |
| anyscale/HuggingFaceH4/zephyr-7b-beta | 1 | 1 | 16384 |
| anyscale/meta-llama/Llama-2-7b-chat-hf | 1 | 1 | 4096 |
| anyscale/meta-llama/Llama-2-13b-chat-hf | 2 | 2 | 4096 |
| anyscale/meta-llama/Llama-2-70b-chat-hf | 10 | 10 | 4096 |
| anyscale/codellama/CodeLlama-34b-Instruct-hf | 10 | 10 | 16384 |
| cloudflare/@cf/meta/llama-2-7b-chat-fp16 | 19 | 19 | 3072 |
| cloudflare/@cf/meta/llama-2-7b-chat-int8 | 19 | 19 | 2048 |
| cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 | 19 | 19 | 8192 |
| cloudflare/@hf/thebloke/codellama-7b-instruct-awq | 19 | 19 | 4096 |
| voyage/voyage-01 | 1 | 0 | 4096 |
| voyage/voyage-lite-01 | 1 | 0 | 4096 |
| gpt-4 | $0.00003000 | $0.00006000 | 8192 |
| gpt-4-0314 | $0.00003000 | $0.00006000 | 8192 |
| gpt-4-0613 | $0.00003000 | $0.00006000 | 8192 |
| gpt-4-32k | $0.00006000 | $0.00012000 | 32768 |
| gpt-4-32k-0314 | $0.00006000 | $0.00012000 | 32768 |
| gpt-4-32k-0613 | $0.00006000 | $0.00012000 | 32768 |
| gpt-4-1106-preview | $0.00001000 | $0.00003000 | 128000 |
| gpt-4-0125-preview | $0.00001000 | $0.00003000 | 128000 |
| gpt-4-vision-preview | $0.00001000 | $0.00003000 | 128000 |
| gpt-3.5-turbo | $0.00000150 | $0.00000200 | 4097 |
| gpt-3.5-turbo-0301 | $0.00000150 | $0.00000200 | 4097 |
| gpt-3.5-turbo-0613 | $0.00000150 | $0.00000200 | 4097 |
| gpt-3.5-turbo-1106 | $0.00000050 | $0.00000150 | 16385 |
| gpt-3.5-turbo-0125 | $0.00000050 | $0.00000150 | 16385 |
| gpt-3.5-turbo-16k | $0.00000300 | $0.00000400 | 16385 |
| gpt-3.5-turbo-16k-0613 | $0.00000300 | $0.00000400 | 16385 |
| text-embedding-ada-002 | $0.00000010 | $0.00000000 | 8191 |
| text-embedding-3-small | $0.00000002 | $0.00000000 | 8191 |
| text-embedding-3-large | $0.00000013 | $0.00000000 | 8191 |
| azure/gpt-4-1106-preview | $0.00001000 | $0.00003000 | 128000 |
| azure/gpt-4-0613 | $0.00003000 | $0.00006000 | 8192 |
| azure/gpt-4-32k-0613 | $0.00006000 | $0.00012000 | 32768 |
| azure/gpt-4-32k | $0.00006000 | $0.00012000 | 32768 |
| azure/gpt-4 | $0.00003000 | $0.00006000 | 8192 |
| azure/gpt-35-turbo-16k-0613 | $0.00000300 | $0.00000400 | 16385 |
| azure/gpt-35-turbo-1106 | $0.00000150 | $0.00000200 | 16384 |
| azure/gpt-35-turbo-16k | $0.00000300 | $0.00000400 | 16385 |
| azure/gpt-35-turbo | $0.00000150 | $0.00000200 | 4097 |
| azure/text-embedding-ada-002 | $0.00000010 | $0.00000000 | 8191 |
| text-davinci-003 | $0.00000200 | $0.00000200 | 4097 |
| text-curie-001 | $0.00000200 | $0.00000200 | 2049 |
| text-babbage-001 | $0.00000040 | $0.00000040 | 2049 |
| text-ada-001 | $0.00000040 | $0.00000040 | 2049 |
| babbage-002 | $0.00000040 | $0.00000040 | 16384 |
| davinci-002 | $0.00000200 | $0.00000200 | 16384 |
| gpt-3.5-turbo-instruct | $0.00000150 | $0.00000200 | 8192 |
| claude-instant-1 | $0.00000160 | $0.00000550 | 100000 |
| mistral/mistral-tiny | $0.00000010 | $0.00000040 | 8192 |
| mistral/mistral-small | $0.00000060 | $0.00000190 | 8192 |
| mistral/mistral-medium | $0.00000270 | $0.00000820 | 8192 |
| claude-instant-1.2 | $0.00000010 | $0.00000050 | 100000 |
| claude-2 | $0.00000800 | $0.00002400 | 100000 |
| claude-2.1 | $0.00000800 | $0.00002400 | 200000 |
| text-bison | $0.00000010 | $0.00000010 | 8192 |
| text-bison@001 | $0.00000010 | $0.00000010 | 8192 |
| text-unicorn | $0.00001000 | $0.00002800 | 8192 |
| text-unicorn@001 | $0.00001000 | $0.00002800 | 8192 |
| chat-bison | $0.00000010 | $0.00000010 | 4096 |
| chat-bison@001 | $0.00000010 | $0.00000010 | 4096 |
| chat-bison@002 | $0.00000010 | $0.00000010 | 4096 |
| chat-bison-32k | $0.00000010 | $0.00000010 | 32000 |
| code-bison | $0.00000010 | $0.00000010 | 6144 |
| code-bison@001 | $0.00000010 | $0.00000010 | 6144 |
| code-gecko@001 | $0.00000010 | $0.00000010 | 2048 |
| code-gecko@002 | $0.00000010 | $0.00000010 | 2048 |
| code-gecko | $0.00000010 | $0.00000010 | 2048 |
| codechat-bison | $0.00000010 | $0.00000010 | 6144 |
| codechat-bison@001 | $0.00000010 | $0.00000010 | 6144 |
| codechat-bison-32k | $0.00000010 | $0.00000010 | 32000 |
| gemini-pro | $0.00000020 | $0.00000050 | 30720 |
| gemini-pro-vision | $0.00000020 | $0.00000050 | 30720 |
| palm/chat-bison | $0.00000010 | $0.00000010 | 4096 |
| palm/chat-bison-001 | $0.00000010 | $0.00000010 | 4096 |
| palm/text-bison | $0.00000010 | $0.00000010 | 8196 |
| palm/text-bison-001 | $0.00000010 | $0.00000010 | 8196 |
| palm/text-bison-safety-off | $0.00000010 | $0.00000010 | 8196 |
| palm/text-bison-safety-recitation-off | $0.00000010 | $0.00000010 | 8196 |
| command-nightly | $0.00001500 | $0.00001500 | 4096 |
| command | $0.00001500 | $0.00001500 | 4096 |
| command-light | $0.00001500 | $0.00001500 | 4096 |
| command-medium-beta | $0.00001500 | $0.00001500 | 4096 |
| command-xlarge-beta | $0.00001500 | $0.00001500 | 4096 |
| openrouter/openai/gpt-3.5-turbo | $0.00000150 | $0.00000200 | 4095 |
| openrouter/openai/gpt-3.5-turbo-16k | $0.00000300 | $0.00000400 | 16383 |
| openrouter/openai/gpt-4 | $0.00003000 | $0.00006000 | 8192 |
| openrouter/anthropic/claude-instant-v1 | $0.00000160 | $0.00000550 | 100000 |
| openrouter/anthropic/claude-2 | $0.00001100 | $0.00003260 | 100000 |
| openrouter/google/palm-2-chat-bison | $0.00000050 | $0.00000050 | 8000 |
| openrouter/google/palm-2-codechat-bison | $0.00000050 | $0.00000050 | 8000 |
| openrouter/meta-llama/llama-2-13b-chat | $0.00000020 | $0.00000020 | 4096 |
| openrouter/meta-llama/llama-2-70b-chat | $0.00000150 | $0.00000150 | 4096 |
| openrouter/meta-llama/codellama-34b-instruct | $0.00000050 | $0.00000050 | 8096 |
| openrouter/nousresearch/nous-hermes-llama2-13b | $0.00000020 | $0.00000020 | 4096 |
| openrouter/mancer/weaver | $0.00000560 | $0.00000560 | 8000 |
| openrouter/gryphe/mythomax-l2-13b | $0.00000180 | $0.00000180 | 8192 |
| openrouter/jondurbin/airoboros-l2-70b-2.1 | $0.00001380 | $0.00001380 | 4096 |
| openrouter/undi95/remm-slerp-l2-13b | $0.00000180 | $0.00000180 | 6144 |
| openrouter/pygmalionai/mythalion-13b | $0.00000180 | $0.00000180 | 4096 |
| openrouter/mistralai/mistral-7b-instruct | $0.00000000 | $0.00000000 | 4096 |
| j2-ultra | $0.00001500 | $0.00001500 | 8192 |
| j2-mid | $0.00001000 | $0.00001000 | 8192 |
| j2-light | $0.00000300 | $0.00000300 | 8192 |
| dolphin | $0.00002000 | $0.00002000 | 4096 |
| chatdolphin | $0.00002000 | $0.00002000 | 4096 |
| luminous-base | $0.00003000 | $0.00003300 | 2048 |
| luminous-base-control | $0.00003740 | $0.00004120 | 2048 |
| luminous-extended | $0.00004500 | $0.00004940 | 2048 |
| luminous-extended-control | $0.00005620 | $0.00006180 | 2048 |
| luminous-supreme | $0.00017500 | $0.00019250 | 2048 |
| luminous-supreme-control | $0.00021870 | $0.00024060 | 2048 |
| ai21.j2-mid-v1 | $0.00001250 | $0.00001250 | 8191 |
| ai21.j2-ultra-v1 | $0.00001880 | $0.00001880 | 8191 |
| amazon.titan-text-lite-v1 | $0.00000030 | $0.00000040 | 8000 |
| amazon.titan-text-express-v1 | $0.00000130 | $0.00000170 | 8000 |
| anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/us-east-1/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/us-west-2/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/ap-northeast-1/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/eu-central-1/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100000 |
| anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/us-east-1/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/us-west-2/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/ap-northeast-1/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/eu-central-1/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100000 |
| anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 200000 |
| bedrock/us-east-1/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/us-west-2/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/ap-northeast-1/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100000 |
| bedrock/eu-central-1/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100000 |
| anthropic.claude-instant-v1 | $0.00000160 | $0.00000550 | 100000 |
| bedrock/us-east-1/anthropic.claude-instant-v1 | $0.00000080 | $0.00000240 | 100000 |
| bedrock/us-west-2/anthropic.claude-instant-v1 | $0.00000080 | $0.00000240 | 100000 |
| bedrock/ap-northeast-1/anthropic.claude-instant-v1 | $0.00000220 | $0.00000750 | 100000 |
| bedrock/eu-central-1/anthropic.claude-instant-v1 | $0.00000240 | $0.00000830 | 100000 |
| cohere.command-text-v14 | $0.00000150 | $0.00000200 | 4096 |
| cohere.command-light-text-v14 | $0.00000030 | $0.00000060 | 4000 |
| cohere.embed-english-v3 | $0.00000010 | $0.00000000 | 512 |
| cohere.embed-multilingual-v3 | $0.00000010 | $0.00000000 | 512 |
| meta.llama2-13b-chat-v1 | $0.00000070 | $0.00000100 | 4096 |
| meta.llama2-70b-chat-v1 | $0.00000190 | $0.00000250 | 4096 |
| sagemaker/meta-textgeneration-llama-2-7b | $0.00000000 | $0.00000000 | 4096 |
| sagemaker/meta-textgeneration-llama-2-7b-f | $0.00000000 | $0.00000000 | 4096 |
| sagemaker/meta-textgeneration-llama-2-13b | $0.00000000 | $0.00000000 | 4096 |
| sagemaker/meta-textgeneration-llama-2-13b-f | $0.00000000 | $0.00000000 | 4096 |
| sagemaker/meta-textgeneration-llama-2-70b | $0.00000000 | $0.00000000 | 4096 |
| sagemaker/meta-textgeneration-llama-2-70b-b-f | $0.00000000 | $0.00000000 | 4096 |
| together-ai-7.1b-20b | $0.00000040 | $0.00000040 | 1000 |
| ollama/llama2 | $0.00000000 | $0.00000000 | 4096 |
| ollama/llama2:13b | $0.00000000 | $0.00000000 | 4096 |
| ollama/llama2:70b | $0.00000000 | $0.00000000 | 4096 |
| ollama/llama2-uncensored | $0.00000000 | $0.00000000 | 4096 |
| ollama/mistral | $0.00000000 | $0.00000000 | 8192 |
| ollama/codellama | $0.00000000 | $0.00000000 | 4096 |
| ollama/orca-mini | $0.00000000 | $0.00000000 | 4096 |
| ollama/vicuna | $0.00000000 | $0.00000000 | 2048 |
| deepinfra/meta-llama/Llama-2-70b-chat-hf | $0.00000070 | $0.00000090 | 4096 |
| deepinfra/codellama/CodeLlama-34b-Instruct-hf | $0.00000060 | $0.00000060 | 4096 |
| deepinfra/meta-llama/Llama-2-13b-chat-hf | $0.00000030 | $0.00000030 | 4096 |
| deepinfra/meta-llama/Llama-2-7b-chat-hf | $0.00000020 | $0.00000020 | 4096 |
| deepinfra/mistralai/Mistral-7B-Instruct-v0.1 | $0.00000020 | $0.00000020 | 4096 |
| deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1 | $0.00000070 | $0.00000090 | 4096 |
| perplexity/pplx-7b-chat | $0.00000000 | $0.00000000 | 8192 |
| perplexity/pplx-70b-chat | $0.00000000 | $0.00000000 | 4096 |
| perplexity/pplx-7b-online | $0.00000000 | $0.00050000 | 4096 |
| perplexity/pplx-70b-online | $0.00000000 | $0.00050000 | 4096 |
| perplexity/llama-2-13b-chat | $0.00000000 | $0.00000000 | 4096 |
| perplexity/llama-2-70b-chat | $0.00000000 | $0.00000000 | 4096 |
| perplexity/mistral-7b-instruct | $0.00000000 | $0.00000000 | 4096 |
| perplexity/replit-code-v1.5-3b | $0.00000000 | $0.00000000 | 4096 |
| anyscale/mistralai/Mistral-7B-Instruct-v0.1 | $0.00000010 | $0.00000010 | 16384 |
| anyscale/HuggingFaceH4/zephyr-7b-beta | $0.00000010 | $0.00000010 | 16384 |
| anyscale/meta-llama/Llama-2-7b-chat-hf | $0.00000010 | $0.00000010 | 4096 |
| anyscale/meta-llama/Llama-2-13b-chat-hf | $0.00000020 | $0.00000020 | 4096 |
| anyscale/meta-llama/Llama-2-70b-chat-hf | $0.00000100 | $0.00000100 | 4096 |
| anyscale/codellama/CodeLlama-34b-Instruct-hf | $0.00000100 | $0.00000100 | 16384 |
| cloudflare/@cf/meta/llama-2-7b-chat-fp16 | $0.00000190 | $0.00000190 | 3072 |
| cloudflare/@cf/meta/llama-2-7b-chat-int8 | $0.00000190 | $0.00000190 | 2048 |
| cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 | $0.00000190 | $0.00000190 | 8192 |
| cloudflare/@hf/thebloke/codellama-7b-instruct-awq | $0.00000190 | $0.00000190 | 4096 |
| voyage/voyage-01 | $0.00000010 | $0.00000000 | 4096 |
| voyage/voyage-lite-01 | $0.00000010 | $0.00000000 | 4096 |
### Callback handlers
You may also calculate token costs in LLM wrapper/framework libraries using callbacks.