📊 LLM Price Guide
Easily calculate the cost of using a language model for your needs.
Daily Cost
For 0 API calls
$0.00
Weekly Cost
For 0 API calls
$0.00
Monthly Cost
For 0 API calls
$0.00
| Provider | Model | Context | Input Cost / Token | Output Cost / Token | Total Cost |
|---|---|---|---|---|---|
| openai | gpt-4 | 4096 | 0.0000300 | 0.0000600 | $90.00 |
| openai | gpt-4o | 4096 | 0.0000050 | 0.0000150 | $20.00 |
| openai | gpt-4o-2024-05-13 | 4096 | 0.0000050 | 0.0000150 | $20.00 |
| openai | gpt-4-turbo-preview | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| openai | gpt-4-0314 | 4096 | 0.0000300 | 0.0000600 | $90.00 |
| openai | gpt-4-0613 | 4096 | 0.0000300 | 0.0000600 | $90.00 |
| openai | gpt-4-32k | 4096 | 0.0000600 | 0.0001200 | $180.00 |
| openai | gpt-4-32k-0314 | 4096 | 0.0000600 | 0.0001200 | $180.00 |
| openai | gpt-4-32k-0613 | 4096 | 0.0000600 | 0.0001200 | $180.00 |
| openai | gpt-4-turbo | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| openai | gpt-4-turbo-2024-04-09 | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| openai | gpt-4-1106-preview | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| openai | gpt-4-0125-preview | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| openai | gpt-4-vision-preview | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| openai | gpt-4-1106-vision-preview | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| openai | gpt-3.5-turbo | 4097 | 0.0000015 | 0.0000020 | $3.50 |
| openai | gpt-3.5-turbo-0301 | 4097 | 0.0000015 | 0.0000020 | $3.50 |
| openai | gpt-3.5-turbo-0613 | 4097 | 0.0000015 | 0.0000020 | $3.50 |
| openai | gpt-3.5-turbo-1106 | 16385 | 0.0000010 | 0.0000020 | $3.00 |
| openai | gpt-3.5-turbo-0125 | 16385 | 0.0000005 | 0.0000015 | $2.00 |
| openai | gpt-3.5-turbo-16k | 16385 | 0.0000030 | 0.0000040 | $7.00 |
| openai | gpt-3.5-turbo-16k-0613 | 16385 | 0.0000030 | 0.0000040 | $7.00 |
| openai | ft:gpt-3.5-turbo | 4097 | 0.0000030 | 0.0000060 | $9.00 |
| azure | azure/gpt-4-turbo-2024-04-09 | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| azure | azure/gpt-4-0125-preview | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| azure | azure/gpt-4-1106-preview | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| azure | azure/gpt-4-0613 | 4096 | 0.0000300 | 0.0000600 | $90.00 |
| azure | azure/gpt-4-32k-0613 | 4096 | 0.0000600 | 0.0001200 | $180.00 |
| azure | azure/gpt-4-32k | 4096 | 0.0000600 | 0.0001200 | $180.00 |
| azure | azure/gpt-4 | 4096 | 0.0000300 | 0.0000600 | $90.00 |
| azure | azure/gpt-4-turbo | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| azure | azure/gpt-4-turbo-vision-preview | 4096 | 0.0000100 | 0.0000300 | $40.00 |
| azure | azure/gpt-35-turbo-16k-0613 | 4096 | 0.0000030 | 0.0000040 | $7.00 |
| azure | azure/gpt-35-turbo-1106 | 4096 | 0.0000015 | 0.0000020 | $3.50 |
| azure | azure/gpt-35-turbo-0125 | 4096 | 0.0000005 | 0.0000015 | $2.00 |
| azure | azure/gpt-35-turbo-16k | 4096 | 0.0000030 | 0.0000040 | $7.00 |
| azure | azure/gpt-35-turbo | 4096 | 0.0000015 | 0.0000020 | $3.50 |
| azure | azure/mistral-large-latest | 32000 | 0.0000080 | 0.0000240 | $32.00 |
| azure | azure/mistral-large-2402 | 32000 | 0.0000080 | 0.0000240 | $32.00 |
| azure | azure/command-r-plus | 4096 | 0.0000030 | 0.0000150 | $18.00 |
| anthropic | claude-instant-1 | 8191 | 0.0000016 | 0.0000055 | $7.14 |
| mistral | mistral/mistral-tiny | 8191 | 0.0000001 | 0.0000005 | $0.61 |
| mistral | mistral/mistral-small | 8191 | 0.0000020 | 0.0000060 | $8.00 |
| mistral | mistral/mistral-small-latest | 8191 | 0.0000020 | 0.0000060 | $8.00 |
| mistral | mistral/mistral-medium | 8191 | 0.0000027 | 0.0000081 | $10.80 |
| mistral | mistral/mistral-medium-latest | 8191 | 0.0000027 | 0.0000081 | $10.80 |
| mistral | mistral/mistral-medium-2312 | 8191 | 0.0000027 | 0.0000081 | $10.80 |
| mistral | mistral/mistral-large-latest | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| mistral | mistral/mistral-large-2402 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| mistral | mistral/open-mixtral-8x7b | 8191 | 0.0000020 | 0.0000060 | $8.00 |
| deepseek | deepseek-chat | 4096 | 0.0000001 | 0.0000003 | $0.42 |
| deepseek | deepseek-coder | 4096 | 0.0000001 | 0.0000003 | $0.42 |
| groq | groq/llama2-70b-4096 | 4096 | 0.0000007 | 0.0000008 | $1.50 |
| groq | groq/llama3-8b-8192 | 8192 | 0.0000001 | 0.0000001 | $0.20 |
| groq | groq/llama3-70b-8192 | 8192 | 0.0000006 | 0.0000008 | $1.44 |
| groq | groq/mixtral-8x7b-32768 | 32768 | 0.0000003 | 0.0000003 | $0.54 |
| groq | groq/gemma-7b-it | 8192 | 0.0000001 | 0.0000001 | $0.20 |
| anthropic | claude-instant-1.2 | 8191 | 0.0000002 | 0.0000006 | $0.71 |
| anthropic | claude-2 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| anthropic | claude-2.1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| anthropic | claude-3-haiku-20240307 | 4096 | 0.0000002 | 0.0000013 | $1.50 |
| anthropic | claude-3-opus-20240229 | 4096 | 0.0000150 | 0.0000750 | $90.00 |
| anthropic | claude-3-sonnet-20240229 | 4096 | 0.0000030 | 0.0000150 | $18.00 |
| vertex_ai-chat-models | chat-bison | 4096 | 0.0000001 | 0.0000001 | $0.25 |
| vertex_ai-chat-models | chat-bison@001 | 4096 | 0.0000001 | 0.0000001 | $0.25 |
| vertex_ai-chat-models | chat-bison@002 | 4096 | 0.0000001 | 0.0000001 | $0.25 |
| vertex_ai-chat-models | chat-bison-32k | 8192 | 0.0000001 | 0.0000001 | $0.25 |
| vertex_ai-code-text-models | code-bison | 1024 | 0.0000001 | 0.0000001 | $0.25 |
| vertex_ai-code-chat-models | codechat-bison | 1024 | 0.0000001 | 0.0000001 | $0.25 |
| vertex_ai-code-chat-models | codechat-bison@001 | 1024 | 0.0000001 | 0.0000001 | $0.25 |
| vertex_ai-code-chat-models | codechat-bison-32k | 8192 | 0.0000001 | 0.0000001 | $0.25 |
| vertex_ai-language-models | gemini-pro | 8192 | 0.0000002 | 0.0000005 | $0.75 |
| vertex_ai-language-models | gemini-1.0-pro | 8192 | 0.0000002 | 0.0000005 | $0.75 |
| vertex_ai-language-models | gemini-1.0-pro-001 | 8192 | 0.0000002 | 0.0000005 | $0.75 |
| vertex_ai-language-models | gemini-1.0-pro-002 | 8192 | 0.0000002 | 0.0000005 | $0.75 |
| vertex_ai-language-models | gemini-1.5-pro | 8192 | 0.0000006 | 0.0000019 | $2.50 |
| vertex_ai-language-models | gemini-1.5-pro-preview-0215 | 8192 | 0.0000006 | 0.0000019 | $2.50 |
| vertex_ai-language-models | gemini-1.5-pro-preview-0409 | 8192 | 0.0000006 | 0.0000019 | $2.50 |
| vertex_ai-vision-models | gemini-pro-vision | 2048 | 0.0000002 | 0.0000005 | $0.75 |
| vertex_ai-vision-models | gemini-1.0-pro-vision | 2048 | 0.0000002 | 0.0000005 | $0.75 |
| vertex_ai-vision-models | gemini-1.0-pro-vision-001 | 2048 | 0.0000002 | 0.0000005 | $0.75 |
| vertex_ai-anthropic_models | vertex_ai/claude-3-sonnet@20240229 | 4096 | 0.0000030 | 0.0000150 | $18.00 |
| vertex_ai-anthropic_models | vertex_ai/claude-3-haiku@20240307 | 4096 | 0.0000002 | 0.0000013 | $1.50 |
| vertex_ai-anthropic_models | vertex_ai/claude-3-opus@20240229 | 4096 | 0.0000015 | 0.0000075 | $9.00 |
| palm | palm/chat-bison | 4096 | 0.0000001 | 0.0000001 | $0.25 |
| palm | palm/chat-bison-001 | 4096 | 0.0000001 | 0.0000001 | $0.25 |
| cohere_chat | command-r | 4096 | 0.0000005 | 0.0000015 | $2.00 |
| cohere_chat | command-light | 4096 | 0.0000150 | 0.0000150 | $30.00 |
| cohere_chat | command-r-plus | 4096 | 0.0000030 | 0.0000150 | $18.00 |
| replicate | replicate/meta/llama-2-13b | 4096 | 0.0000001 | 0.0000005 | $0.60 |
| replicate | replicate/meta/llama-2-13b-chat | 4096 | 0.0000001 | 0.0000005 | $0.60 |
| replicate | replicate/meta/llama-2-70b | 4096 | 0.0000007 | 0.0000027 | $3.40 |
| replicate | replicate/meta/llama-2-70b-chat | 4096 | 0.0000007 | 0.0000027 | $3.40 |
| replicate | replicate/meta/llama-2-7b | 4096 | 0.0000000 | 0.0000002 | $0.30 |
| replicate | replicate/meta/llama-2-7b-chat | 4096 | 0.0000000 | 0.0000002 | $0.30 |
| replicate | replicate/meta/llama-3-70b | 4096 | 0.0000007 | 0.0000027 | $3.40 |
| replicate | replicate/meta/llama-3-70b-instruct | 4096 | 0.0000007 | 0.0000027 | $3.40 |
| replicate | replicate/meta/llama-3-8b | 4096 | 0.0000000 | 0.0000002 | $0.30 |
| replicate | replicate/meta/llama-3-8b-instruct | 4096 | 0.0000000 | 0.0000002 | $0.30 |
| replicate | replicate/mistralai/mistral-7b-v0.1 | 4096 | 0.0000000 | 0.0000002 | $0.30 |
| replicate | replicate/mistralai/mistral-7b-instruct-v0.2 | 4096 | 0.0000000 | 0.0000002 | $0.30 |
| replicate | replicate/mistralai/mixtral-8x7b-instruct-v0.1 | 4096 | 0.0000003 | 0.0000010 | $1.30 |
| openrouter | openrouter/microsoft/wizardlm-2-8x22b:nitro | 65536 | 0.0000010 | 0.0000010 | $2.00 |
| openrouter | openrouter/google/gemini-pro-1.5 | 8192 | 0.0000025 | 0.0000075 | $10.00 |
| openrouter | openrouter/mistralai/mixtral-8x22b-instruct | 65536 | 0.0000007 | 0.0000007 | $1.30 |
| openrouter | openrouter/cohere/command-r-plus | 128000 | 0.0000030 | 0.0000150 | $18.00 |
| openrouter | openrouter/databricks/dbrx-instruct | 32768 | 0.0000006 | 0.0000006 | $1.20 |
| openrouter | openrouter/anthropic/claude-3-haiku | 200000 | 0.0000002 | 0.0000013 | $1.50 |
| openrouter | openrouter/anthropic/claude-3-sonnet | 200000 | 0.0000030 | 0.0000150 | $18.00 |
| openrouter | openrouter/mistralai/mistral-large | 32000 | 0.0000080 | 0.0000240 | $32.00 |
| openrouter | openrouter/cognitivecomputations/dolphin-mixtral-8x7b | 32769 | 0.0000005 | 0.0000005 | $1.00 |
| openrouter | openrouter/google/gemini-pro-vision | 45875 | 0.0000001 | 0.0000004 | $0.50 |
| openrouter | openrouter/fireworks/firellava-13b | 4096 | 0.0000002 | 0.0000002 | $0.40 |
| openrouter | openrouter/meta-llama/llama-3-8b-instruct:extended | 16384 | 0.0000002 | 0.0000023 | $2.48 |
| openrouter | openrouter/meta-llama/llama-3-70b-instruct:nitro | 8192 | 0.0000009 | 0.0000009 | $1.80 |
| openrouter | openrouter/meta-llama/llama-3-70b-instruct | 8192 | 0.0000006 | 0.0000008 | $1.38 |
| openrouter | openrouter/openai/gpt-4-vision-preview | 130000 | 0.0000100 | 0.0000300 | $40.00 |
| openrouter | openrouter/openai/gpt-3.5-turbo | 4095 | 0.0000015 | 0.0000020 | $3.50 |
| openrouter | openrouter/openai/gpt-3.5-turbo-16k | 16383 | 0.0000030 | 0.0000040 | $7.00 |
| openrouter | openrouter/openai/gpt-4 | 8192 | 0.0000300 | 0.0000600 | $90.00 |
| openrouter | openrouter/anthropic/claude-instant-v1 | 100000 | 0.0000016 | 0.0000055 | $7.14 |
| openrouter | openrouter/anthropic/claude-2 | 100000 | 0.0000110 | 0.0000327 | $43.70 |
| openrouter | openrouter/anthropic/claude-3-opus | 4096 | 0.0000150 | 0.0000750 | $90.00 |
| openrouter | openrouter/google/palm-2-chat-bison | 25804 | 0.0000005 | 0.0000005 | $1.00 |
| openrouter | openrouter/google/palm-2-codechat-bison | 20070 | 0.0000005 | 0.0000005 | $1.00 |
| openrouter | openrouter/meta-llama/llama-2-13b-chat | 4096 | 0.0000002 | 0.0000002 | $0.40 |
| openrouter | openrouter/meta-llama/llama-2-70b-chat | 4096 | 0.0000015 | 0.0000015 | $3.00 |
| openrouter | openrouter/meta-llama/codellama-34b-instruct | 8096 | 0.0000005 | 0.0000005 | $1.00 |
| openrouter | openrouter/nousresearch/nous-hermes-llama2-13b | 4096 | 0.0000002 | 0.0000002 | $0.40 |
| openrouter | openrouter/mancer/weaver | 8000 | 0.0000056 | 0.0000056 | $11.25 |
| openrouter | openrouter/gryphe/mythomax-l2-13b | 8192 | 0.0000019 | 0.0000019 | $3.75 |
| openrouter | openrouter/jondurbin/airoboros-l2-70b-2.1 | 4096 | 0.0000139 | 0.0000139 | $27.75 |
| openrouter | openrouter/undi95/remm-slerp-l2-13b | 6144 | 0.0000019 | 0.0000019 | $3.75 |
| openrouter | openrouter/pygmalionai/mythalion-13b | 4096 | 0.0000019 | 0.0000019 | $3.75 |
| openrouter | openrouter/mistralai/mistral-7b-instruct | 8192 | 0.0000001 | 0.0000001 | $0.26 |
| nlp_cloud | chatdolphin | 16384 | 0.0000005 | 0.0000005 | $1.00 |
| aleph_alpha | luminous-base-control | 2048 | 0.0000375 | 0.0000412 | $78.75 |
| aleph_alpha | luminous-extended-control | 2048 | 0.0000562 | 0.0000619 | $118.13 |
| aleph_alpha | luminous-supreme-control | 2048 | 0.0002188 | 0.0002406 | $459.38 |
| bedrock | ai21.j2-mid-v1 | 8191 | 0.0000125 | 0.0000125 | $25.00 |
| bedrock | ai21.j2-ultra-v1 | 8191 | 0.0000188 | 0.0000188 | $37.60 |
| bedrock | amazon.titan-text-lite-v1 | 4000 | 0.0000003 | 0.0000004 | $0.70 |
| bedrock | amazon.titan-text-express-v1 | 8000 | 0.0000013 | 0.0000017 | $3.00 |
| bedrock | mistral.mistral-7b-instruct-v0:2 | 8191 | 0.0000001 | 0.0000002 | $0.35 |
| bedrock | mistral.mixtral-8x7b-instruct-v0:1 | 8191 | 0.0000004 | 0.0000007 | $1.15 |
| bedrock | mistral.mistral-large-2402-v1:0 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1 | 8191 | 0.0000004 | 0.0000007 | $1.15 |
| bedrock | bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1 | 8191 | 0.0000004 | 0.0000007 | $1.15 |
| bedrock | bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1 | 8191 | 0.0000006 | 0.0000009 | $1.50 |
| bedrock | bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2 | 8191 | 0.0000001 | 0.0000002 | $0.35 |
| bedrock | bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2 | 8191 | 0.0000001 | 0.0000002 | $0.35 |
| bedrock | bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2 | 8191 | 0.0000002 | 0.0000003 | $0.46 |
| bedrock | bedrock/us-east-1/mistral.mistral-large-2402-v1:0 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/us-west-2/mistral.mistral-large-2402-v1:0 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/eu-west-3/mistral.mistral-large-2402-v1:0 | 8191 | 0.0000104 | 0.0000312 | $41.60 |
| bedrock | anthropic.claude-3-sonnet-20240229-v1:0 | 4096 | 0.0000030 | 0.0000150 | $18.00 |
| bedrock | anthropic.claude-3-haiku-20240307-v1:0 | 4096 | 0.0000002 | 0.0000013 | $1.50 |
| bedrock | anthropic.claude-3-opus-20240229-v1:0 | 4096 | 0.0000150 | 0.0000750 | $90.00 |
| bedrock | anthropic.claude-v1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/us-east-1/anthropic.claude-v1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/us-west-2/anthropic.claude-v1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/ap-northeast-1/anthropic.claude-v1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/eu-central-1/anthropic.claude-v1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | anthropic.claude-v2 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/us-east-1/anthropic.claude-v2 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/us-west-2/anthropic.claude-v2 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/ap-northeast-1/anthropic.claude-v2 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/eu-central-1/anthropic.claude-v2 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | anthropic.claude-v2:1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/us-east-1/anthropic.claude-v2:1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/us-west-2/anthropic.claude-v2:1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/ap-northeast-1/anthropic.claude-v2:1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | bedrock/eu-central-1/anthropic.claude-v2:1 | 8191 | 0.0000080 | 0.0000240 | $32.00 |
| bedrock | anthropic.claude-instant-v1 | 8191 | 0.0000016 | 0.0000055 | $7.14 |
| bedrock | bedrock/us-east-1/anthropic.claude-instant-v1 | 8191 | 0.0000008 | 0.0000024 | $3.20 |
| bedrock | bedrock/us-west-2/anthropic.claude-instant-v1 | 8191 | 0.0000008 | 0.0000024 | $3.20 |
| bedrock | bedrock/ap-northeast-1/anthropic.claude-instant-v1 | 8191 | 0.0000022 | 0.0000075 | $9.78 |
| bedrock | bedrock/eu-central-1/anthropic.claude-instant-v1 | 8191 | 0.0000025 | 0.0000084 | $10.86 |
| bedrock | cohere.command-text-v14 | 4096 | 0.0000015 | 0.0000020 | $3.50 |
| bedrock | cohere.command-light-text-v14 | 4096 | 0.0000003 | 0.0000006 | $0.90 |
| bedrock | cohere.command-r-plus-v1:0 | 4096 | 0.0000030 | 0.0000150 | $18.00 |
| bedrock | cohere.command-r-v1:0 | 4096 | 0.0000005 | 0.0000015 | $2.00 |
| bedrock | meta.llama2-13b-chat-v1 | 4096 | 0.0000008 | 0.0000010 | $1.75 |
| bedrock | meta.llama2-70b-chat-v1 | 4096 | 0.0000019 | 0.0000026 | $4.51 |
| bedrock | meta.llama3-8b-instruct-v1:0 | 8192 | 0.0000004 | 0.0000006 | $1.00 |
| bedrock | meta.llama3-70b-instruct-v1:0 | 8192 | 0.0000027 | 0.0000035 | $6.15 |
| deepinfra | deepinfra/lizpreciatior/lzlv_70b_fp16_hf | 4096 | 0.0000007 | 0.0000009 | $1.60 |
| deepinfra | deepinfra/Gryphe/MythoMax-L2-13b | 4096 | 0.0000002 | 0.0000002 | $0.44 |
| deepinfra | deepinfra/mistralai/Mistral-7B-Instruct-v0.1 | 8191 | 0.0000001 | 0.0000001 | $0.26 |
| deepinfra | deepinfra/meta-llama/Llama-2-70b-chat-hf | 4096 | 0.0000007 | 0.0000009 | $1.60 |
| deepinfra | deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b | 8191 | 0.0000003 | 0.0000003 | $0.54 |
| deepinfra | deepinfra/codellama/CodeLlama-34b-Instruct-hf | 4096 | 0.0000006 | 0.0000006 | $1.20 |
| deepinfra | deepinfra/Phind/Phind-CodeLlama-34B-v2 | 4096 | 0.0000006 | 0.0000006 | $1.20 |
| deepinfra | deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1 | 8191 | 0.0000003 | 0.0000003 | $0.54 |
| deepinfra | deepinfra/deepinfra/airoboros-70b | 4096 | 0.0000007 | 0.0000009 | $1.60 |
| deepinfra | deepinfra/01-ai/Yi-34B-Chat | 4096 | 0.0000006 | 0.0000006 | $1.20 |
| deepinfra | deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1 | 4096 | 0.0000007 | 0.0000009 | $1.60 |
| deepinfra | deepinfra/meta-llama/Llama-2-13b-chat-hf | 4096 | 0.0000002 | 0.0000002 | $0.44 |
| deepinfra | deepinfra/amazon/MistralLite | 8191 | 0.0000002 | 0.0000002 | $0.40 |
| deepinfra | deepinfra/meta-llama/Llama-2-7b-chat-hf | 4096 | 0.0000001 | 0.0000001 | $0.26 |
| deepinfra | deepinfra/openchat/openchat_3.5 | 4096 | 0.0000001 | 0.0000001 | $0.26 |
| perplexity | perplexity/codellama-34b-instruct | 16384 | 0.0000003 | 0.0000014 | $1.75 |
| perplexity | perplexity/codellama-70b-instruct | 16384 | 0.0000007 | 0.0000028 | $3.50 |
| perplexity | perplexity/pplx-7b-chat | 8192 | 0.0000001 | 0.0000003 | $0.35 |
| perplexity | perplexity/pplx-70b-chat | 4096 | 0.0000007 | 0.0000028 | $3.50 |
| perplexity | perplexity/llama-2-70b-chat | 4096 | 0.0000007 | 0.0000028 | $3.50 |
| perplexity | perplexity/mistral-7b-instruct | 4096 | 0.0000001 | 0.0000003 | $0.35 |
| perplexity | perplexity/mixtral-8x7b-instruct | 4096 | 0.0000001 | 0.0000003 | $0.35 |
| perplexity | perplexity/sonar-small-chat | 16384 | 0.0000001 | 0.0000003 | $0.35 |
| perplexity | perplexity/sonar-medium-chat | 16384 | 0.0000006 | 0.0000018 | $2.40 |
| anyscale | anyscale/mistralai/Mistral-7B-Instruct-v0.1 | 16384 | 0.0000001 | 0.0000001 | $0.30 |
| anyscale | anyscale/Mixtral-8x7B-Instruct-v0.1 | 16384 | 0.0000001 | 0.0000001 | $0.30 |
| anyscale | anyscale/HuggingFaceH4/zephyr-7b-beta | 16384 | 0.0000001 | 0.0000001 | $0.30 |
| anyscale | anyscale/meta-llama/Llama-2-7b-chat-hf | 4096 | 0.0000001 | 0.0000001 | $0.30 |
| anyscale | anyscale/meta-llama/Llama-2-13b-chat-hf | 4096 | 0.0000002 | 0.0000002 | $0.50 |
| anyscale | anyscale/meta-llama/Llama-2-70b-chat-hf | 4096 | 0.0000010 | 0.0000010 | $2.00 |
| anyscale | anyscale/codellama/CodeLlama-34b-Instruct-hf | 4096 | 0.0000010 | 0.0000010 | $2.00 |
| cloudflare | cloudflare/@cf/meta/llama-2-7b-chat-fp16 | 3072 | 0.0000019 | 0.0000019 | $3.85 |
| cloudflare | cloudflare/@cf/meta/llama-2-7b-chat-int8 | 2048 | 0.0000019 | 0.0000019 | $3.85 |
| cloudflare | cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 | 8192 | 0.0000019 | 0.0000019 | $3.85 |
| cloudflare | cloudflare/@hf/thebloke/codellama-7b-instruct-awq | 4096 | 0.0000019 | 0.0000019 | $3.85 |