From 4baba4ab001f56a66a1aea6a890e9be73713c839 Mon Sep 17 00:00:00 2001 From: charles Date: Mon, 25 Aug 2025 20:31:05 -0700 Subject: [PATCH] Fix the model pricing and add lambda model pricing --- .../c9f3e548adef_add_lambda_model_pricing.py | 118 ++ tools/data/lambda_model_pricing_init.csv | 18 + tools/data/model_pricing_init.csv | 1054 ++++++++--------- 3 files changed, 663 insertions(+), 527 deletions(-) create mode 100644 alembic/versions/c9f3e548adef_add_lambda_model_pricing.py create mode 100644 tools/data/lambda_model_pricing_init.csv diff --git a/alembic/versions/c9f3e548adef_add_lambda_model_pricing.py b/alembic/versions/c9f3e548adef_add_lambda_model_pricing.py new file mode 100644 index 0000000..ed167cf --- /dev/null +++ b/alembic/versions/c9f3e548adef_add_lambda_model_pricing.py @@ -0,0 +1,118 @@ +"""add lambda model pricing + +Revision ID: c9f3e548adef +Revises: 39bcedfae4fe +Create Date: 2025-08-25 19:53:57.606298 + +""" +from csv import DictReader +from decimal import Decimal +import os +from alembic import op +import sqlalchemy as sa +from datetime import datetime, timedelta, UTC + + +# revision identifiers, used by Alembic. +revision = 'c9f3e548adef' +down_revision = '39bcedfae4fe' +branch_labels = None +depends_on = None + + +def upgrade() -> None: + # insert the lambda data + effective_date = datetime.now(UTC) - timedelta(days=1) + csv_path = os.path.join(os.path.dirname(__file__), "..", "..", "tools", "data", "lambda_model_pricing_init.csv") + with open(csv_path, "r") as f: + reader = DictReader(f) + rows_to_insert = [] + for row in reader: + rows_to_insert.append({ + "provider_name": row["provider_name"], + "model_name": row["model_name"], + "effective_date": effective_date, + "input_token_price": Decimal(str(row["input_token_price"])).normalize(), + "output_token_price": Decimal(str(row["output_token_price"])).normalize(), + "price_source": "manual" + }) + + if rows_to_insert: + connection = op.get_bind() + connection.execute( + sa.text(""" + INSERT INTO model_pricing (provider_name, model_name, effective_date, input_token_price, output_token_price, cached_token_price, price_source) + VALUES (:provider_name, :model_name, :effective_date, :input_token_price, :output_token_price, :input_token_price, 'manual') + """), + rows_to_insert, + ) + connection.execute( + sa.text(""" + INSERT INTO fallback_pricing (provider_name, model_name, effective_date, input_token_price, output_token_price, cached_token_price, fallback_type) + VALUES (:provider_name, :model_name, :effective_date, :input_token_price, :output_token_price, :input_token_price, 'model_default') + """), + rows_to_insert, + ) + + # Fix the cached_token_price for all the other models + csv_path = os.path.join(os.path.dirname(__file__), "..", "..", "tools", "data", "model_pricing_init.csv") + with open(csv_path, "r") as f: + reader = DictReader(f) + rows_to_update = [] + for row in reader: + rows_to_update.append({ + "provider_name": row["provider_name"], + "model_name": row["model_name"], + "input_token_price": Decimal(str(row["input_token_price"])).normalize(), + "output_token_price": Decimal(str(row["output_token_price"])).normalize(), + "cached_token_price": Decimal(str(row["cached_token_price"])).normalize(), + }) + + if rows_to_update: + connection = op.get_bind() + connection.execute( + sa.text(""" + update model_pricing set cached_token_price = :cached_token_price + where provider_name = :provider_name and model_name = :model_name + """), + rows_to_update, + ) + connection.execute( + sa.text(""" + update fallback_pricing set cached_token_price = :cached_token_price + where provider_name = :provider_name and model_name = :model_name + """), + rows_to_update, + ) + + # backfill the cached_token_price for all the other models + connection = op.get_bind() + connection.execute( + sa.text(""" + with updated_model_pricing as ( + update model_pricing set cached_token_price = input_token_price + where cached_token_price = 0 + ) + update fallback_pricing set cached_token_price = input_token_price + where cached_token_price = 0 + """), + rows_to_insert, + ) + + # remove the default value for cached_token_price + op.alter_column('model_pricing', 'cached_token_price', server_default=None) + op.alter_column('fallback_pricing', 'cached_token_price', server_default=None) + + +def downgrade() -> None: + connection = op.get_bind() + connection.execute( + sa.text(""" + DELETE FROM model_pricing WHERE provider_name = 'lambda' + """), + ) + connection.execute( + sa.text(""" + DELETE FROM fallback_pricing WHERE provider_name = 'lambda' + """), + ) diff --git a/tools/data/lambda_model_pricing_init.csv b/tools/data/lambda_model_pricing_init.csv new file mode 100644 index 0000000..574f242 --- /dev/null +++ b/tools/data/lambda_model_pricing_init.csv @@ -0,0 +1,18 @@ +provider_name,model_name,input_token_price,output_token_price +lambda,deepseek-r1-0528,0.0005,0.00218 +lambda,deepseek-v3-0324,0.00034,0.00088 +lambda,qwen-3-32b,0.0001,0.0003 +lambda,llama-4-maverick-17b-128e-instruct-fp8,0.00018,0.0006 +lambda,llama-4-scout-17b-16e-instruct,0.00008,0.0003 +lambda,llama-3.1-8b-instruct,0.000025,0.00004 +lambda,llama-3.1-70b-instruct,0.00012,0.0003 +lambda,llama-3.1-405b-instruct,0.0008,0.0008 +lambda,deepseek-llama3.3-70b,0.0002,0.0006 +lambda,llama-3.3-70b-instruct,0.00012,0.0003 +lambda,llama-3.2-3b-instruct,0.000015,0.000025 +lambda,hermes-3-llama-3.1-8b,0.000025,0.00004 +lambda,hermes-3-llama-3.1-70b (fp8),0.00012,0.0003 +lambda,hermes-3-llama-3.1-405b (fp8),0.0008,0.0008 +lambda,lfm-40b,0.00015,0.00015 +lambda,llama3.1-nemotron-70b-instruct,0.00012,0.0003 +lambda,qwen2.5-coder-32b,0.00007,0.00016 diff --git a/tools/data/model_pricing_init.csv b/tools/data/model_pricing_init.csv index 4095a56..3bfcb13 100644 --- a/tools/data/model_pricing_init.csv +++ b/tools/data/model_pricing_init.csv @@ -1,527 +1,527 @@ -provider_name,model_name,input_token_price,output_token_price -openai,gpt-4,0.03,0.06 -openai,gpt-4.1,0.002,0.008 -openai,gpt-4.1-2025-04-14,0.002,0.008 -openai,gpt-4.1-mini,0.0004,0.0016 -openai,gpt-4.1-mini-2025-04-14,0.0004,0.0016 -openai,gpt-4.1-nano,0.0001,0.0004 -openai,gpt-4.1-nano-2025-04-14,0.0001,0.0004 -openai,gpt-4o,0.0025,0.01 -openai,gpt-4o-search-preview-2025-03-11,0.0025,0.01 -openai,gpt-4o-search-preview,0.0025,0.01 -openai,gpt-4.5-preview,0.075,0.15 -openai,gpt-4.5-preview-2025-02-27,0.075,0.15 -openai,gpt-4o-audio-preview,0.0025,0.01 -openai,gpt-4o-audio-preview-2024-12-17,0.0025,0.01 -openai,gpt-4o-audio-preview-2024-10-01,0.0025,0.01 -openai,gpt-4o-audio-preview-2025-06-03,0.0025,0.01 -openai,gpt-4o-mini-audio-preview,0.00015,0.0006 -openai,gpt-4o-mini-audio-preview-2024-12-17,0.00015,0.0006 -openai,gpt-4o-mini,0.00015,0.0006 -openai,gpt-4o-mini-search-preview-2025-03-11,0.00015,0.0006 -openai,gpt-4o-mini-search-preview,0.00015,0.0006 -openai,gpt-4o-mini-2024-07-18,0.00015,0.0006 -openai,gpt-5,0.00125,0.01 -openai,gpt-5-mini,0.00025,0.002 -openai,gpt-5-nano,0.00005,0.0004 -openai,gpt-5-chat,0.00125,0.01 -openai,gpt-5-chat-latest,0.00125,0.01 -openai,gpt-5-2025-08-07,0.00125,0.01 -openai,gpt-5-mini-2025-08-07,0.00025,0.002 -openai,gpt-5-nano-2025-08-07,0.00005,0.0004 -openai,codex-mini-latest,0.0015,0.006 -openai,o1-pro,0.15,0.6 -openai,o1-pro-2025-03-19,0.15,0.6 -openai,o1,0.015,0.06 -openai,o1-mini,0.0011,0.0044 -azure,computer-use-preview,0.003,0.012 -openai,o3-deep-research,0.01,0.04 -openai,o3-deep-research-2025-06-26,0.01,0.04 -openai,o3-pro,0.02,0.08 -openai,o3-pro-2025-06-10,0.02,0.08 -openai,o3,0.002,0.008 -openai,o3-2025-04-16,0.002,0.008 -openai,o3-mini,0.0011,0.0044 -openai,o3-mini-2025-01-31,0.0011,0.0044 -openai,o4-mini,0.0011,0.0044 -openai,o4-mini-deep-research,0.002,0.008 -openai,o4-mini-deep-research-2025-06-26,0.002,0.008 -openai,o4-mini-2025-04-16,0.0011,0.0044 -openai,o1-mini-2024-09-12,0.003,0.012 -openai,o1-preview,0.015,0.06 -openai,o1-preview-2024-09-12,0.015,0.06 -openai,o1-2024-12-17,0.015,0.06 -openai,chatgpt-4o-latest,0.005,0.015 -openai,gpt-4o-2024-05-13,0.005,0.015 -openai,gpt-4o-2024-08-06,0.0025,0.01 -openai,gpt-4o-2024-11-20,0.0025,0.01 -openai,gpt-4o-realtime-preview-2024-10-01,0.005,0.02 -openai,gpt-4o-realtime-preview,0.005,0.02 -openai,gpt-4o-realtime-preview-2024-12-17,0.005,0.02 -openai,gpt-4o-realtime-preview-2025-06-03,0.005,0.02 -openai,gpt-4o-mini-realtime-preview,0.0006,0.0024 -openai,gpt-4o-mini-realtime-preview-2024-12-17,0.0006,0.0024 -openai,gpt-4-turbo-preview,0.01,0.03 -openai,gpt-4-0314,0.03,0.06 -openai,gpt-4-0613,0.03,0.06 -openai,gpt-4-32k,0.06,0.12 -openai,gpt-4-32k-0314,0.06,0.12 -openai,gpt-4-32k-0613,0.06,0.12 -openai,gpt-4-turbo,0.01,0.03 -openai,gpt-4-turbo-2024-04-09,0.01,0.03 -openai,gpt-4-1106-preview,0.01,0.03 -openai,gpt-4-0125-preview,0.01,0.03 -openai,gpt-4-vision-preview,0.01,0.03 -openai,gpt-4-1106-vision-preview,0.01,0.03 -openai,gpt-3.5-turbo,0.0015,0.002 -openai,gpt-3.5-turbo-0301,0.0015,0.002 -openai,gpt-3.5-turbo-0613,0.0015,0.002 -openai,gpt-3.5-turbo-1106,0.001,0.002 -openai,gpt-3.5-turbo-0125,0.0005,0.0015 -openai,gpt-3.5-turbo-16k,0.003,0.004 -openai,gpt-3.5-turbo-16k-0613,0.003,0.004 -openai,ft:gpt-3.5-turbo,0.003,0.006 -openai,ft:gpt-3.5-turbo-0125,0.003,0.006 -openai,ft:gpt-3.5-turbo-1106,0.003,0.006 -openai,ft:gpt-3.5-turbo-0613,0.003,0.006 -openai,ft:gpt-4-0613,0.03,0.06 -openai,ft:gpt-4o-2024-08-06,0.00375,0.015 -openai,ft:gpt-4o-2024-11-20,0.00375,0.015 -openai,ft:gpt-4o-mini-2024-07-18,0.0003,0.0012 -openai,gpt-4o-transcribe,0.0025,0.01 -openai,gpt-4o-mini-transcribe,0.00125,0.005 -openai,gpt-4o-mini-tts,0.0025,0.01 -azure,gpt-5,0.00125,0.01 -azure,gpt-5-2025-08-07,0.00125,0.01 -azure,gpt-5-mini,0.00025,0.002 -azure,gpt-5-mini-2025-08-07,0.00025,0.002 -azure,gpt-5-nano-2025-08-07,0.00005,0.0004 -azure,gpt-5-nano,0.00005,0.0004 -azure,gpt-5-chat,0.00125,0.01 -azure,gpt-5-chat-latest,0.00125,0.01 -azure,gpt-4o-mini-tts,0.0025,0.01 -azure,gpt-4o-audio-preview-2024-12-17,0.0025,0.01 -azure,gpt-4o-mini-audio-preview-2024-12-17,0.0025,0.01 -azure,gpt-4.1,0.002,0.008 -azure,gpt-4.1-2025-04-14,0.002,0.008 -azure,gpt-4.1-mini,0.0004,0.0016 -azure,gpt-4.1-mini-2025-04-14,0.0004,0.0016 -azure,gpt-4.1-nano,0.0001,0.0004 -azure,gpt-4.1-nano-2025-04-14,0.0001,0.0004 -azure,o3-pro,0.02,0.08 -azure,o3-pro-2025-06-10,0.02,0.08 -azure,o3,0.002,0.008 -azure,o3-2025-04-16,0.01,0.04 -azure,o3-deep-research,0.01,0.04 -azure,o4-mini,0.0011,0.0044 -azure,gpt-4o-mini-realtime-preview-2024-12-17,0.0006,0.0024 -azure,gpt-4o-realtime-preview-2024-12-17,0.005,0.02 -azure,gpt-4o-realtime-preview-2024-10-01,0.005,0.02 -azure,o4-mini-2025-04-16,0.0011,0.0044 -azure,o3-mini-2025-01-31,0.0011,0.0044 -azure,gpt-4o-transcribe,0.0025,0.01 -azure,gpt-4o-mini-transcribe,0.00125,0.005 -azure,o3-mini,0.0011,0.0044 -azure,o1-mini,0.00121,0.00484 -azure,o1-mini-2024-09-12,0.0011,0.0044 -azure,o1,0.015,0.06 -azure,o1-2024-12-17,0.015,0.06 -azure,codex-mini,0.0015,0.006 -azure,o1-preview,0.015,0.06 -azure,o1-preview-2024-09-12,0.015,0.06 -azure,gpt-4.5-preview,0.075,0.15 -azure,gpt-4o,0.0025,0.01 -azure,gpt-4o-2024-08-06,0.0025,0.01 -azure,gpt-4o-2024-11-20,0.00275,0.011 -azure,gpt-4o-2024-05-13,0.005,0.015 -azure,gpt-4o-mini,0.000165,0.00066 -azure,gpt-4o-mini-2024-07-18,0.000165,0.00066 -azure,gpt-4-turbo-2024-04-09,0.01,0.03 -azure,gpt-4-0125-preview,0.01,0.03 -azure,gpt-4-1106-preview,0.01,0.03 -azure,gpt-4-0613,0.03,0.06 -azure,gpt-4-32k-0613,0.06,0.12 -azure,gpt-4-32k,0.06,0.12 -azure,gpt-4,0.03,0.06 -azure,gpt-4-turbo,0.01,0.03 -azure,gpt-4-turbo-vision-preview,0.01,0.03 -azure,gpt-35-turbo-16k-0613,0.003,0.004 -azure,gpt-35-turbo-1106,0.001,0.002 -azure,gpt-35-turbo-0613,0.0015,0.002 -azure,gpt-35-turbo-0301,0.0002,0.002 -azure,gpt-35-turbo-0125,0.0005,0.0015 -azure,gpt-3.5-turbo-0125,0.0005,0.0015 -azure,gpt-35-turbo-16k,0.003,0.004 -azure,gpt-35-turbo,0.0005,0.0015 -azure,gpt-3.5-turbo,0.0005,0.0015 -azure,mistral-large-latest,0.008,0.024 -azure,mistral-large-2402,0.008,0.024 -azure,command-r-plus,0.003,0.015 -azure,grok-3,0.0033,0.0165 -azure,grok-3-mini,0.000275,0.00138 -azure,deepseek-r1,0.00135,0.0054 -azure,deepseek-v3,0.00114,0.00456 -azure,deepseek-v3-0324,0.00114,0.00456 -azure,jamba-instruct,0.0005,0.0007 -azure,jais-30b-chat,3.2,9.71 -azure,mistral-nemo,0.00015,0.00015 -azure,mistral-medium-2505,0.0004,0.002 -azure,mistral-large,0.004,0.012 -azure,mistral-small,0.001,0.003 -azure,mistral-small-2503,0.001,0.003 -azure,mistral-large-2407,0.002,0.006 -azure,ministral-3b,0.00004,0.00004 -azure,llama-3.2-11b-vision-instruct,0.00037,0.00037 -azure,llama-3.3-70b-instruct,0.00071,0.00071 -azure,llama-4-scout-17b-16e-instruct,0.0002,0.00078 -azure,llama-4-maverick-17b-128e-instruct-fp8,0.00141,0.00035 -azure,llama-3.2-90b-vision-instruct,0.00204,0.00204 -azure,meta-llama-3-70b-instruct,0.0011,0.00037 -azure,meta-llama-3.1-8b-instruct,0.0003,0.00061 -azure,meta-llama-3.1-70b-instruct,0.00268,0.00354 -azure,meta-llama-3.1-405b-instruct,0.00533,0.016 -azure,phi-4-mini-instruct,0.000075,0.0003 -azure,phi-4-multimodal-instruct,0.00008,0.00032 -azure,phi-4,0.000125,0.0005 -azure,phi-3.5-mini-instruct,0.00013,0.00052 -azure,phi-3.5-vision-instruct,0.00013,0.00052 -azure,phi-3.5-moe-instruct,0.00016,0.00064 -azure,phi-3-mini-4k-instruct,0.00013,0.00052 -azure,phi-3-mini-128k-instruct,0.00013,0.00052 -azure,phi-3-small-8k-instruct,0.00015,0.0006 -azure,phi-3-small-128k-instruct,0.00015,0.0006 -azure,phi-3-medium-4k-instruct,0.00017,0.00068 -azure,phi-3-medium-128k-instruct,0.00017,0.00068 -mistral,mistral-tiny,0.00025,0.00025 -mistral,mistral-small,0.0001,0.0003 -mistral,mistral-small-latest,0.0001,0.0003 -mistral,mistral-medium,0.0027,0.0081 -mistral,mistral-medium-latest,0.0004,0.002 -mistral,mistral-medium-2505,0.0004,0.002 -mistral,mistral-medium-2312,0.0027,0.0081 -mistral,mistral-large-latest,0.002,0.006 -mistral,mistral-large-2411,0.002,0.006 -mistral,mistral-large-2402,0.004,0.012 -mistral,mistral-large-2407,0.003,0.009 -mistral,pixtral-large-latest,0.002,0.006 -mistral,pixtral-large-2411,0.002,0.006 -mistral,pixtral-12b-2409,0.00015,0.00015 -mistral,open-mistral-7b,0.00025,0.00025 -mistral,open-mixtral-8x7b,0.0007,0.0007 -mistral,open-mixtral-8x22b,0.002,0.006 -mistral,codestral-latest,0.001,0.003 -mistral,codestral-2405,0.001,0.003 -mistral,open-mistral-nemo,0.0003,0.0003 -mistral,open-mistral-nemo-2407,0.0003,0.0003 -mistral,open-codestral-mamba,0.00025,0.00025 -mistral,codestral-mamba-latest,0.00025,0.00025 -mistral,devstral-small-2505,0.0001,0.0003 -mistral,devstral-small-2507,0.0001,0.0003 -mistral,devstral-medium-2507,0.0004,0.002 -mistral,magistral-medium-latest,0.002,0.005 -mistral,magistral-medium-2506,0.002,0.005 -mistral,magistral-small-latest,0.0005,0.0015 -mistral,magistral-small-2506,0.0005,0.0015 -deepseek,deepseek-reasoner,0.00055,0.00219 -deepseek,deepseek-chat,0.00027,0.0011 -deepseek,deepseek-r1,0.00055,0.00219 -deepseek,deepseek-v3,0.00027,0.0011 -xai,grok-beta,0.005,0.015 -xai,grok-2-vision-1212,0.002,0.01 -xai,grok-2-vision-latest,0.002,0.01 -xai,grok-2-vision,0.002,0.01 -xai,grok-3,0.003,0.015 -xai,grok-3-latest,0.003,0.015 -xai,grok-3-beta,0.003,0.015 -xai,grok-3-fast-beta,0.005,0.025 -xai,grok-3-fast-latest,0.005,0.025 -xai,grok-3-mini,0.0003,0.0005 -xai,grok-3-mini-latest,0.0003,0.0005 -xai,grok-3-mini-fast,0.0006,0.004 -xai,grok-3-mini-fast-latest,0.0006,0.004 -xai,grok-3-mini-beta,0.0003,0.0005 -xai,grok-3-mini-fast-beta,0.0006,0.004 -xai,grok-vision-beta,0.005,0.015 -xai,grok-2-1212,0.002,0.01 -xai,grok-2,0.002,0.01 -xai,grok-2-latest,0.002,0.01 -xai,grok-4,0.003,0.015 -xai,grok-4-0709,0.003,0.015 -xai,grok-4-latest,0.003,0.015 -deepseek,deepseek-coder,0.00014,0.00028 -groq,deepseek-r1-distill-llama-70b,0.00075,0.00099 -groq,llama-3.3-70b-versatile,0.00059,0.00079 -groq,llama-3.3-70b-specdec,0.00059,0.00099 -groq,llama-guard-3-8b,0.0002,0.0002 -groq,llama2-70b-4096,0.0007,0.0008 -groq,llama3-8b-8192,0.00005,0.00008 -groq,llama-3.2-1b-preview,0.00004,0.00004 -groq,llama-3.2-3b-preview,0.00006,0.00006 -groq,llama-3.2-11b-text-preview,0.00018,0.00018 -groq,llama-3.2-11b-vision-preview,0.00018,0.00018 -groq,llama-3.2-90b-text-preview,0.0009,0.0009 -groq,llama-3.2-90b-vision-preview,0.0009,0.0009 -groq,llama3-70b-8192,0.00059,0.00079 -groq,llama-3.1-8b-instant,0.00005,0.00008 -groq,llama-3.1-70b-versatile,0.00059,0.00079 -groq,llama-3.1-405b-reasoning,0.00059,0.00079 -groq,mistral-saba-24b,0.00079,0.00079 -groq,mixtral-8x7b-32768,0.00024,0.00024 -groq,gemma-7b-it,0.00007,0.00007 -groq,gemma2-9b-it,0.0002,0.0002 -groq,llama3-groq-70b-8192-tool-use-preview,0.00089,0.00089 -groq,llama3-groq-8b-8192-tool-use-preview,0.00019,0.00019 -cerebras,llama3.1-8b,0.0001,0.0001 -cerebras,llama3.1-70b,0.0006,0.0006 -cerebras,llama-3.3-70b,0.00085,0.0012 -cerebras,qwen-3-32b,0.0004,0.0008 -anthropic,claude-3-haiku-20240307,0.00025,0.00125 -anthropic,claude-3-5-haiku-20241022,0.0008,0.004 -anthropic,claude-3-5-haiku-latest,0.001,0.005 -anthropic,claude-3-opus-latest,0.015,0.075 -anthropic,claude-3-opus-20240229,0.015,0.075 -anthropic,claude-3-5-sonnet-latest,0.003,0.015 -anthropic,claude-3-5-sonnet-20240620,0.003,0.015 -anthropic,claude-opus-4-20250514,0.015,0.075 -anthropic,claude-opus-4-1,0.015,0.075 -anthropic,claude-opus-4-1-20250805,0.015,0.075 -anthropic,claude-sonnet-4-20250514,0.003,0.015 -anthropic,claude-4-opus-20250514,0.015,0.075 -anthropic,claude-4-sonnet-20250514,0.003,0.015 -anthropic,claude-3-7-sonnet-latest,0.003,0.015 -anthropic,claude-3-7-sonnet-20250219,0.003,0.015 -anthropic,claude-3-5-sonnet-20241022,0.003,0.015 -vertex,text-bison32k,0.000125,0.000125 -vertex,text-bison32k@002,0.000125,0.000125 -vertex,text-unicorn,0.01,0.028 -vertex,text-unicorn@001,0.01,0.028 -vertex,chat-bison,0.000125,0.000125 -vertex,chat-bison@001,0.000125,0.000125 -vertex,chat-bison@002,0.000125,0.000125 -vertex,chat-bison-32k,0.000125,0.000125 -vertex,chat-bison-32k@002,0.000125,0.000125 -vertex,code-bison,0.000125,0.000125 -vertex,code-bison@001,0.000125,0.000125 -vertex,code-bison@002,0.000125,0.000125 -vertex,code-bison32k,0.000125,0.000125 -vertex,code-bison-32k@002,0.000125,0.000125 -vertex,code-gecko@001,0.000125,0.000125 -vertex,code-gecko@002,0.000125,0.000125 -vertex,code-gecko,0.000125,0.000125 -vertex,code-gecko-latest,0.000125,0.000125 -vertex,codechat-bison@latest,0.000125,0.000125 -vertex,codechat-bison,0.000125,0.000125 -vertex,codechat-bison@001,0.000125,0.000125 -vertex,codechat-bison@002,0.000125,0.000125 -vertex,codechat-bison-32k,0.000125,0.000125 -vertex,codechat-bison-32k@002,0.000125,0.000125 -vertex,gemini-pro,0.0005,0.0015 -vertex,gemini-1.0-pro,0.0005,0.0015 -vertex,gemini-1.0-pro-001,0.0005,0.0015 -vertex,gemini-1.0-ultra,0.0005,0.0015 -vertex,gemini-1.0-ultra-001,0.0005,0.0015 -vertex,gemini-1.0-pro-002,0.0005,0.0015 -vertex,gemini-1.5-pro,0.00125,0.005 -vertex,gemini-1.5-pro-002,0.00125,0.005 -vertex,gemini-1.5-pro-001,0.00125,0.005 -vertex,gemini-1.5-pro-preview-0514,0.000078125,0.0003125 -vertex,gemini-1.5-pro-preview-0215,0.000078125,0.0003125 -vertex,gemini-1.5-pro-preview-0409,0.000078125,0.0003125 -vertex,gemini-1.5-flash,0.000075,0.0003 -vertex,gemini-1.5-flash-exp-0827,0.000004688,0.0000046875 -vertex,gemini-1.5-flash-002,0.000075,0.0003 -vertex,gemini-1.5-flash-001,0.000075,0.0003 -vertex,gemini-1.5-flash-preview-0514,0.000075,0.0000046875 -vertex,gemini-pro-vision,0.0005,0.0015 -vertex,gemini-1.0-pro-vision,0.0005,0.0015 -vertex,gemini-1.0-pro-vision-001,0.0005,0.0015 -vertex,gemini-2.5-pro-exp-03-25,0.00125,0.01 -vertex,gemini-2.0-pro-exp-02-05,0.00125,0.01 -vertex,gemini-2.0-flash-exp,0.00015,0.0006 -vertex,gemini-2.0-flash-001,0.00015,0.0006 -vertex,gemini-2.5-pro,0.00125,0.01 -gemini,models/gemini-2.5-pro,0.00125,0.01 -gemini,models/gemini-2.5-flash,0.0003,0.0025 -vertex,gemini-2.5-flash,0.0003,0.0025 -gemini,models/gemini-2.0-flash-live-001,0.00035,0.0015 -gemini,models/gemini-2.5-flash-preview-tts,0.00015,0.0006 -gemini,models/gemini-2.5-flash-preview-05-20,0.0003,0.0025 -gemini,models/gemini-2.5-flash-preview-04-17,0.00015,0.0006 -gemini,models/gemini-2.5-flash-lite-preview-06-17,0.0001,0.0004 -gemini,models/gemini-2.5-flash-lite,0.0001,0.0004 -vertex,gemini-2.5-flash-preview-05-20,0.0003,0.0025 -vertex,gemini-2.5-flash-preview-04-17,0.00015,0.0006 -vertex,gemini-2.5-flash-lite-preview-06-17,0.0001,0.0004 -vertex,gemini-2.5-flash-lite,0.0001,0.0004 -vertex,gemini-2.0-flash,0.0001,0.0004 -vertex,gemini-2.0-flash-lite,0.000075,0.0003 -vertex,gemini-2.0-flash-lite-001,0.000075,0.0003 -vertex,gemini-2.5-pro-preview-06-05,0.00125,0.01 -vertex,gemini-2.5-pro-preview-05-06,0.00125,0.01 -vertex,gemini-2.5-pro-preview-03-25,0.00125,0.01 -vertex,gemini-2.0-flash-preview-image-generation,0.0001,0.0004 -vertex,gemini-2.5-pro-preview-tts,0.00125,0.01 -gemini,models/gemini-2.0-flash-preview-image-generation,0.0001,0.0004 -gemini,models/gemini-2.0-flash,0.0001,0.0004 -gemini,models/gemini-2.0-flash-lite,0.000075,0.0003 -gemini,models/gemini-2.0-flash-001,0.0001,0.0004 -gemini,models/gemini-2.5-pro-preview-tts,0.00125,0.01 -gemini,models/gemini-2.5-pro-preview-06-05,0.00125,0.01 -gemini,models/gemini-2.5-pro-preview-05-06,0.00125,0.01 -gemini,models/gemini-2.5-pro-preview-03-25,0.00125,0.01 -gemini,models/gemini-2.0-flash-lite-preview-02-05,0.000075,0.0003 -vertex,gemini-2.0-flash-live-preview-04-09,0.0005,0.002 -gemini,models/gemini-1.5-flash-002,0.000075,0.0003 -gemini,models/gemini-1.5-flash-001,0.000075,0.0003 -gemini,models/gemini-1.5-flash,0.000075,0.0003 -gemini,models/gemini-1.5-flash-latest,0.000075,0.0003 -gemini,models/gemini-pro,0.00035,0.00105 -gemini,models/gemini-1.5-pro,0.0035,0.0105 -gemini,models/gemini-1.5-pro-002,0.0035,0.0105 -gemini,models/gemini-1.5-pro-001,0.0035,0.0105 -gemini,models/gemini-1.5-pro-exp-0801,0.0035,0.0105 -gemini,models/gemini-1.5-pro-latest,0.0035,0.00105 -gemini,models/gemini-pro-vision,0.00035,0.00105 -gemini,models/gemini-gemma-2-27b-it,0.00035,0.00105 -gemini,models/gemini-gemma-2-9b-it,0.00035,0.00105 -cohere,command-a-03-2025,0.0025,0.01 -cohere,command-r,0.00015,0.0006 -cohere,command-r-08-2024,0.00015,0.0006 -cohere,command-r7b-12-2024,0.00015,0.0000375 -cohere,command-light,0.0003,0.0006 -cohere,command-r-plus,0.0025,0.01 -cohere,command-r-plus-08-2024,0.0025,0.01 -cohere,command-nightly,0.001,0.002 -cohere,command,0.001,0.002 -bedrock,ai21.j2-mid-v1,0.0125,0.0125 -bedrock,ai21.j2-ultra-v1,0.0188,0.0188 -bedrock,ai21.jamba-instruct-v1:0,0.0005,0.0007 -bedrock,ai21.jamba-1-5-large-v1:0,0.002,0.008 -bedrock,ai21.jamba-1-5-mini-v1:0,0.0002,0.0004 -bedrock,amazon.titan-text-lite-v1,0.0003,0.0004 -bedrock,amazon.titan-text-express-v1,0.0013,0.0017 -bedrock,amazon.titan-text-premier-v1:0,0.0005,0.0015 -bedrock,mistral.mistral-7b-instruct-v0:2,0.00015,0.0002 -bedrock,mistral.mixtral-8x7b-instruct-v0:1,0.00045,0.0007 -bedrock,mistral.mistral-large-2402-v1:0,0.008,0.024 -bedrock,mistral.mistral-large-2407-v1:0,0.003,0.009 -bedrock,mistral.mistral-small-2402-v1:0,0.001,0.003 -bedrock,eu.mistral.pixtral-large-2502-v1:0,0.002,0.006 -bedrock,us.mistral.pixtral-large-2502-v1:0,0.002,0.006 -bedrock,amazon.nova-micro-v1:0,0.000035,0.00014 -bedrock,us.amazon.nova-micro-v1:0,0.000035,0.00014 -bedrock,eu.amazon.nova-micro-v1:0,0.000046,0.000184 -bedrock,amazon.nova-lite-v1:0,0.00006,0.00024 -bedrock,us.amazon.nova-lite-v1:0,0.00006,0.00024 -bedrock,eu.amazon.nova-lite-v1:0,0.000078,0.000312 -bedrock,amazon.nova-pro-v1:0,0.0008,0.0032 -bedrock,us.amazon.nova-pro-v1:0,0.0008,0.0032 -bedrock,eu.amazon.nova-pro-v1:0,0.00105,0.0042 -bedrock,apac.amazon.nova-micro-v1:0,0.000037,0.000148 -bedrock,apac.amazon.nova-lite-v1:0,0.000063,0.000252 -bedrock,apac.amazon.nova-pro-v1:0,0.00084,0.00336 -bedrock,us.amazon.nova-premier-v1:0,0.0025,0.0125 -bedrock,anthropic.claude-3-sonnet-20240229-v1:0,0.003,0.015 -bedrock,anthropic.claude-3-5-sonnet-20240620-v1:0,0.003,0.015 -bedrock,openai.gpt-oss-20b-1:0,0.00007,0.0003 -bedrock,openai.gpt-oss-120b-1:0,0.00015,0.0006 -bedrock,anthropic.claude-opus-4-1-20250805-v1:0,0.015,0.075 -bedrock,anthropic.claude-opus-4-20250514-v1:0,0.015,0.075 -bedrock,anthropic.claude-sonnet-4-20250514-v1:0,0.003,0.015 -bedrock,anthropic.claude-3-7-sonnet-20250219-v1:0,0.003,0.015 -bedrock,anthropic.claude-3-5-sonnet-20241022-v2:0,0.003,0.015 -bedrock,anthropic.claude-3-haiku-20240307-v1:0,0.00025,0.00125 -bedrock,anthropic.claude-3-5-haiku-20241022-v1:0,0.0008,0.004 -bedrock,anthropic.claude-3-opus-20240229-v1:0,0.015,0.075 -bedrock,us.anthropic.claude-3-sonnet-20240229-v1:0,0.003,0.015 -bedrock,us.anthropic.claude-3-5-sonnet-20240620-v1:0,0.003,0.015 -bedrock,us.anthropic.claude-3-5-sonnet-20241022-v2:0,0.003,0.015 -bedrock,us.anthropic.claude-3-7-sonnet-20250219-v1:0,0.003,0.015 -bedrock,us.anthropic.claude-opus-4-1-20250805-v1:0,0.015,0.075 -bedrock,us.anthropic.claude-opus-4-20250514-v1:0,0.015,0.075 -bedrock,us.anthropic.claude-sonnet-4-20250514-v1:0,0.003,0.015 -bedrock,us.anthropic.claude-3-haiku-20240307-v1:0,0.00025,0.00125 -bedrock,us.anthropic.claude-3-5-haiku-20241022-v1:0,0.0008,0.004 -bedrock,us.anthropic.claude-3-opus-20240229-v1:0,0.015,0.075 -bedrock,eu.anthropic.claude-3-sonnet-20240229-v1:0,0.003,0.015 -bedrock,eu.anthropic.claude-3-5-sonnet-20240620-v1:0,0.003,0.015 -bedrock,eu.anthropic.claude-3-5-sonnet-20241022-v2:0,0.003,0.015 -bedrock,eu.anthropic.claude-3-7-sonnet-20250219-v1:0,0.003,0.015 -bedrock,eu.anthropic.claude-3-haiku-20240307-v1:0,0.00025,0.00125 -bedrock,eu.anthropic.claude-opus-4-1-20250805-v1:0,0.015,0.075 -bedrock,eu.anthropic.claude-opus-4-20250514-v1:0,0.015,0.075 -bedrock,eu.anthropic.claude-sonnet-4-20250514-v1:0,0.003,0.015 -bedrock,apac.anthropic.claude-3-haiku-20240307-v1:0,0.00025,0.00125 -bedrock,apac.anthropic.claude-3-sonnet-20240229-v1:0,0.003,0.015 -bedrock,apac.anthropic.claude-3-5-sonnet-20240620-v1:0,0.003,0.015 -bedrock,apac.anthropic.claude-3-5-sonnet-20241022-v2:0,0.003,0.015 -bedrock,apac.anthropic.claude-sonnet-4-20250514-v1:0,0.003,0.015 -bedrock,eu.anthropic.claude-3-5-haiku-20241022-v1:0,0.00025,0.00125 -bedrock,eu.anthropic.claude-3-opus-20240229-v1:0,0.015,0.075 -bedrock,anthropic.claude-v1,0.008,0.024 -bedrock,anthropic.claude-v2,0.008,0.024 -bedrock,anthropic.claude-v2:1,0.008,0.024 -bedrock,anthropic.claude-instant-v1,0.0008,0.0024 -bedrock,cohere.command-text-v14,0.0015,0.002 -bedrock,cohere.command-light-text-v14,0.0003,0.0006 -bedrock,cohere.command-r-plus-v1:0,0.003,0.015 -bedrock,cohere.command-r-v1:0,0.0005,0.0015 -bedrock,us.deepseek.r1-v1:0,0.00135,0.0054 -bedrock,meta.llama3-3-70b-instruct-v1:0,0.00072,0.00072 -bedrock,meta.llama2-13b-chat-v1,0.00075,0.001 -bedrock,meta.llama2-70b-chat-v1,0.00195,0.00256 -bedrock,meta.llama3-8b-instruct-v1:0,0.0003,0.0006 -bedrock,meta.llama3-70b-instruct-v1:0,0.00265,0.0035 -bedrock,meta.llama3-1-8b-instruct-v1:0,0.00022,0.00022 -bedrock,us.meta.llama3-1-8b-instruct-v1:0,0.00022,0.00022 -bedrock,meta.llama3-1-70b-instruct-v1:0,0.00099,0.00099 -bedrock,us.meta.llama3-1-70b-instruct-v1:0,0.00099,0.00099 -bedrock,meta.llama3-1-405b-instruct-v1:0,0.00532,0.016 -bedrock,us.meta.llama3-1-405b-instruct-v1:0,0.00532,0.016 -bedrock,meta.llama3-2-1b-instruct-v1:0,0.0001,0.0001 -bedrock,us.meta.llama3-2-1b-instruct-v1:0,0.0001,0.0001 -bedrock,eu.meta.llama3-2-1b-instruct-v1:0,0.00013,0.00013 -bedrock,meta.llama3-2-3b-instruct-v1:0,0.00015,0.00015 -bedrock,us.meta.llama3-2-3b-instruct-v1:0,0.00015,0.00015 -bedrock,eu.meta.llama3-2-3b-instruct-v1:0,0.00019,0.00019 -bedrock,meta.llama3-2-11b-instruct-v1:0,0.00035,0.00035 -bedrock,us.meta.llama3-2-11b-instruct-v1:0,0.00035,0.00035 -bedrock,meta.llama3-2-90b-instruct-v1:0,0.002,0.002 -bedrock,us.meta.llama3-2-90b-instruct-v1:0,0.002,0.002 -bedrock,us.meta.llama3-3-70b-instruct-v1:0,0.00072,0.00072 -bedrock,meta.llama4-maverick-17b-instruct-v1:0,0.00024,0.00097 -bedrock,us.meta.llama4-maverick-17b-instruct-v1:0,0.00024,0.00097 -bedrock,meta.llama4-scout-17b-instruct-v1:0,0.00017,0.00066 -bedrock,us.meta.llama4-scout-17b-instruct-v1:0,0.00017,0.00066 -together,together-ai-up-to-4b,0.0001,0.0001 -together,together-ai-4.1b-8b,0.0002,0.0002 -together,together-ai-8.1b-21b,0.0003,0.0003 -together,together-ai-21.1b-41b,0.0008,0.0008 -together,together-ai-41.1b-80b,0.0009,0.0009 -together,together-ai-81.1b-110b,0.0018,0.0018 -perplexity,codellama-34b-instruct,0.00035,0.0014 -perplexity,codellama-70b-instruct,0.0007,0.0028 -perplexity,llama-3.1-70b-instruct,0.001,0.001 -perplexity,llama-3.1-8b-instruct,0.0002,0.0002 -perplexity,llama-3.1-sonar-huge-128k-online,0.005,0.005 -perplexity,llama-3.1-sonar-large-128k-online,0.001,0.001 -perplexity,llama-3.1-sonar-large-128k-chat,0.001,0.001 -perplexity,llama-3.1-sonar-small-128k-chat,0.0002,0.0002 -perplexity,llama-3.1-sonar-small-128k-online,0.0002,0.0002 -perplexity,pplx-7b-chat,0.00007,0.00028 -perplexity,pplx-70b-chat,0.0007,0.0028 -perplexity,llama-2-70b-chat,0.0007,0.0028 -perplexity,mistral-7b-instruct,0.00007,0.00028 -perplexity,mixtral-8x7b-instruct,0.00007,0.00028 -perplexity,sonar-small-chat,0.00007,0.00028 -perplexity,sonar-medium-chat,0.0006,0.0018 -perplexity,sonar,0.001,0.001 -perplexity,sonar-pro,0.003,0.015 -perplexity,sonar-reasoning,0.001,0.005 -perplexity,sonar-reasoning-pro,0.002,0.008 -perplexity,sonar-deep-research,0.002,0.008 -fireworks,fireworks-ai-up-to-4b,0.0002,0.0002 -fireworks,fireworks-ai-4.1b-to-16b,0.0002,0.0002 -fireworks,fireworks-ai-above-16b,0.0009,0.0009 -fireworks,fireworks-ai-moe-up-to-56b,0.0005,0.0005 -fireworks,fireworks-ai-56b-to-176b,0.0012,0.0012 +provider_name,model_name,input_token_price,output_token_price,cached_token_price +openai,gpt-4,0.03,0.06,0.03 +openai,gpt-4.1,0.002,0.008,0.0005 +openai,gpt-4.1-2025-04-14,0.002,0.008,0.0005 +openai,gpt-4.1-mini,0.0004,0.0016,0.0001 +openai,gpt-4.1-mini-2025-04-14,0.0004,0.0016,0.0001 +openai,gpt-4.1-nano,0.0001,0.0004,0.000025 +openai,gpt-4.1-nano-2025-04-14,0.0001,0.0004,0.000025 +openai,gpt-4o,0.0025,0.01,0.00125 +openai,gpt-4o-search-preview-2025-03-11,0.0025,0.01,0.00125 +openai,gpt-4o-search-preview,0.0025,0.01,0.00125 +openai,gpt-4.5-preview,0.075,0.15,0.0375 +openai,gpt-4.5-preview-2025-02-27,0.075,0.15,0.0375 +openai,gpt-4o-audio-preview,0.0025,0.01,0.0025 +openai,gpt-4o-audio-preview-2024-12-17,0.0025,0.01,0.0025 +openai,gpt-4o-audio-preview-2024-10-01,0.0025,0.01,0.0025 +openai,gpt-4o-audio-preview-2025-06-03,0.0025,0.01,0.0025 +openai,gpt-4o-mini-audio-preview,0.00015,0.0006,0.00015 +openai,gpt-4o-mini-audio-preview-2024-12-17,0.00015,0.0006,0.00015 +openai,gpt-4o-mini,0.00015,0.0006,0.000075 +openai,gpt-4o-mini-search-preview-2025-03-11,0.00015,0.0006,0.000075 +openai,gpt-4o-mini-search-preview,0.00015,0.0006,0.000075 +openai,gpt-4o-mini-2024-07-18,0.00015,0.0006,0.000075 +openai,gpt-5,0.00125,0.01,0.000125 +openai,gpt-5-mini,0.00025,0.002,0.000025 +openai,gpt-5-nano,0.00005,0.0004,0.000005 +openai,gpt-5-chat,0.00125,0.01,0.000125 +openai,gpt-5-chat-latest,0.00125,0.01,0.000125 +openai,gpt-5-2025-08-07,0.00125,0.01,0.000125 +openai,gpt-5-mini-2025-08-07,0.00025,0.002,0.000025 +openai,gpt-5-nano-2025-08-07,0.00005,0.0004,0.000005 +openai,codex-mini-latest,0.0015,0.006,0.000375 +openai,o1-pro,0.15,0.6,0.15 +openai,o1-pro-2025-03-19,0.15,0.6,0.15 +openai,o1,0.015,0.06,0.0075 +openai,o1-mini,0.0011,0.0044,0.00055 +azure,computer-use-preview,0.003,0.012,0.003 +openai,o3-deep-research,0.01,0.04,0.0025 +openai,o3-deep-research-2025-06-26,0.01,0.04,0.0025 +openai,o3-pro,0.02,0.08,0.02 +openai,o3-pro-2025-06-10,0.02,0.08,0.02 +openai,o3,0.002,0.008,0.0005 +openai,o3-2025-04-16,0.002,0.008,0.0005 +openai,o3-mini,0.0011,0.0044,0.00055 +openai,o3-mini-2025-01-31,0.0011,0.0044,0.00055 +openai,o4-mini,0.0011,0.0044,0.000275 +openai,o4-mini-deep-research,0.002,0.008,0.0005 +openai,o4-mini-deep-research-2025-06-26,0.002,0.008,0.0005 +openai,o4-mini-2025-04-16,0.0011,0.0044,0.000275 +openai,o1-mini-2024-09-12,0.003,0.012,0.0015 +openai,o1-preview,0.015,0.06,0.0075 +openai,o1-preview-2024-09-12,0.015,0.06,0.0075 +openai,o1-2024-12-17,0.015,0.06,0.0075 +openai,chatgpt-4o-latest,0.005,0.015,0.005 +openai,gpt-4o-2024-05-13,0.005,0.015,0.005 +openai,gpt-4o-2024-08-06,0.0025,0.01,0.00125 +openai,gpt-4o-2024-11-20,0.0025,0.01,0.00125 +openai,gpt-4o-realtime-preview-2024-10-01,0.005,0.02,0.0025 +openai,gpt-4o-realtime-preview,0.005,0.02,0.0025 +openai,gpt-4o-realtime-preview-2024-12-17,0.005,0.02,0.0025 +openai,gpt-4o-realtime-preview-2025-06-03,0.005,0.02,0.0025 +openai,gpt-4o-mini-realtime-preview,0.0006,0.0024,0.0003 +openai,gpt-4o-mini-realtime-preview-2024-12-17,0.0006,0.0024,0.0003 +openai,gpt-4-turbo-preview,0.01,0.03,0.01 +openai,gpt-4-0314,0.03,0.06,0.03 +openai,gpt-4-0613,0.03,0.06,0.03 +openai,gpt-4-32k,0.06,0.12,0.06 +openai,gpt-4-32k-0314,0.06,0.12,0.06 +openai,gpt-4-32k-0613,0.06,0.12,0.06 +openai,gpt-4-turbo,0.01,0.03,0.01 +openai,gpt-4-turbo-2024-04-09,0.01,0.03,0.01 +openai,gpt-4-1106-preview,0.01,0.03,0.01 +openai,gpt-4-0125-preview,0.01,0.03,0.01 +openai,gpt-4-vision-preview,0.01,0.03,0.01 +openai,gpt-4-1106-vision-preview,0.01,0.03,0.01 +openai,gpt-3.5-turbo,0.0015,0.002,0.0015 +openai,gpt-3.5-turbo-0301,0.0015,0.002,0.0015 +openai,gpt-3.5-turbo-0613,0.0015,0.002,0.0015 +openai,gpt-3.5-turbo-1106,0.001,0.002,0.001 +openai,gpt-3.5-turbo-0125,0.0005,0.0015,0.0005 +openai,gpt-3.5-turbo-16k,0.003,0.004,0.003 +openai,gpt-3.5-turbo-16k-0613,0.003,0.004,0.003 +openai,ft:gpt-3.5-turbo,0.003,0.006,0.003 +openai,ft:gpt-3.5-turbo-0125,0.003,0.006,0.003 +openai,ft:gpt-3.5-turbo-1106,0.003,0.006,0.003 +openai,ft:gpt-3.5-turbo-0613,0.003,0.006,0.003 +openai,ft:gpt-4-0613,0.03,0.06,0.03 +openai,ft:gpt-4o-2024-08-06,0.00375,0.015,0.00375 +openai,ft:gpt-4o-2024-11-20,0.00375,0.015,0.00375 +openai,ft:gpt-4o-mini-2024-07-18,0.0003,0.0012,0.00015 +openai,gpt-4o-transcribe,0.0025,0.01,0.0025 +openai,gpt-4o-mini-transcribe,0.00125,0.005,0.00125 +openai,gpt-4o-mini-tts,0.0025,0.01,0.0025 +azure,gpt-5,0.00125,0.01,0.000125 +azure,gpt-5-2025-08-07,0.00125,0.01,0.000125 +azure,gpt-5-mini,0.00025,0.002,0.000025 +azure,gpt-5-mini-2025-08-07,0.00025,0.002,0.000025 +azure,gpt-5-nano-2025-08-07,0.00005,0.0004,0.000005 +azure,gpt-5-nano,0.00005,0.0004,0.000005 +azure,gpt-5-chat,0.00125,0.01,0.000125 +azure,gpt-5-chat-latest,0.00125,0.01,0.000125 +azure,gpt-4o-mini-tts,0.0025,0.01,0.0025 +azure,gpt-4o-audio-preview-2024-12-17,0.0025,0.01,0.0025 +azure,gpt-4o-mini-audio-preview-2024-12-17,0.0025,0.01,0.0025 +azure,gpt-4.1,0.002,0.008,0.0005 +azure,gpt-4.1-2025-04-14,0.002,0.008,0.0005 +azure,gpt-4.1-mini,0.0004,0.0016,0.0001 +azure,gpt-4.1-mini-2025-04-14,0.0004,0.0016,0.0001 +azure,gpt-4.1-nano,0.0001,0.0004,0.000025 +azure,gpt-4.1-nano-2025-04-14,0.0001,0.0004,0.000025 +azure,o3-pro,0.02,0.08,0.02 +azure,o3-pro-2025-06-10,0.02,0.08,0.02 +azure,o3,0.002,0.008,0.0005 +azure,o3-2025-04-16,0.01,0.04,0.0025 +azure,o3-deep-research,0.01,0.04,0.0025 +azure,o4-mini,0.0011,0.0044,0.000275 +azure,gpt-4o-mini-realtime-preview-2024-12-17,0.0006,0.0024,0.0003 +azure,gpt-4o-realtime-preview-2024-12-17,0.005,0.02,0.0025 +azure,gpt-4o-realtime-preview-2024-10-01,0.005,0.02,0.0025 +azure,o4-mini-2025-04-16,0.0011,0.0044,0.000275 +azure,o3-mini-2025-01-31,0.0011,0.0044,0.00055 +azure,gpt-4o-transcribe,0.0025,0.01,0.0025 +azure,gpt-4o-mini-transcribe,0.00125,0.005,0.00125 +azure,o3-mini,0.0011,0.0044,0.00055 +azure,o1-mini,0.00121,0.00484,0.000605 +azure,o1-mini-2024-09-12,0.0011,0.0044,0.00055 +azure,o1,0.015,0.06,0.0075 +azure,o1-2024-12-17,0.015,0.06,0.0075 +azure,codex-mini,0.0015,0.006,0.000375 +azure,o1-preview,0.015,0.06,0.0075 +azure,o1-preview-2024-09-12,0.015,0.06,0.0075 +azure,gpt-4.5-preview,0.075,0.15,0.0375 +azure,gpt-4o,0.0025,0.01,0.00125 +azure,gpt-4o-2024-08-06,0.0025,0.01,0.00125 +azure,gpt-4o-2024-11-20,0.00275,0.011,0.00125 +azure,gpt-4o-2024-05-13,0.005,0.015,0.005 +azure,gpt-4o-mini,0.000165,0.00066,0.000075 +azure,gpt-4o-mini-2024-07-18,0.000165,0.00066,0.000075 +azure,gpt-4-turbo-2024-04-09,0.01,0.03,0.01 +azure,gpt-4-0125-preview,0.01,0.03,0.01 +azure,gpt-4-1106-preview,0.01,0.03,0.01 +azure,gpt-4-0613,0.03,0.06,0.03 +azure,gpt-4-32k-0613,0.06,0.12,0.06 +azure,gpt-4-32k,0.06,0.12,0.06 +azure,gpt-4,0.03,0.06,0.03 +azure,gpt-4-turbo,0.01,0.03,0.01 +azure,gpt-4-turbo-vision-preview,0.01,0.03,0.01 +azure,gpt-35-turbo-16k-0613,0.003,0.004,0.003 +azure,gpt-35-turbo-1106,0.001,0.002,0.001 +azure,gpt-35-turbo-0613,0.0015,0.002,0.0015 +azure,gpt-35-turbo-0301,0.0002,0.002,0.0002 +azure,gpt-35-turbo-0125,0.0005,0.0015,0.0005 +azure,gpt-3.5-turbo-0125,0.0005,0.0015,0.0005 +azure,gpt-35-turbo-16k,0.003,0.004,0.003 +azure,gpt-35-turbo,0.0005,0.0015,0.0005 +azure,gpt-3.5-turbo,0.0005,0.0015,0.0005 +azure,mistral-large-latest,0.008,0.024,0.008 +azure,mistral-large-2402,0.008,0.024,0.008 +azure,command-r-plus,0.003,0.015,0.003 +azure,grok-3,0.0033,0.0165,0.0033 +azure,grok-3-mini,0.000275,0.00138,0.000275 +azure,deepseek-r1,0.00135,0.0054,0.00135 +azure,deepseek-v3,0.00114,0.00456,0.00114 +azure,deepseek-v3-0324,0.00114,0.00456,0.00114 +azure,jamba-instruct,0.0005,0.0007,0.0005 +azure,jais-30b-chat,3.2,9.71,3.2 +azure,mistral-nemo,0.00015,0.00015,0.00015 +azure,mistral-medium-2505,0.0004,0.002,0.0004 +azure,mistral-large,0.004,0.012,0.004 +azure,mistral-small,0.001,0.003,0.001 +azure,mistral-small-2503,0.001,0.003,0.001 +azure,mistral-large-2407,0.002,0.006,0.002 +azure,ministral-3b,0.00004,0.00004,0.00004 +azure,llama-3.2-11b-vision-instruct,0.00037,0.00037,0.00037 +azure,llama-3.3-70b-instruct,0.00071,0.00071,0.00071 +azure,llama-4-scout-17b-16e-instruct,0.0002,0.00078,0.0002 +azure,llama-4-maverick-17b-128e-instruct-fp8,0.00141,0.00035,0.00141 +azure,llama-3.2-90b-vision-instruct,0.00204,0.00204,0.00204 +azure,meta-llama-3-70b-instruct,0.0011,0.00037,0.0011 +azure,meta-llama-3.1-8b-instruct,0.0003,0.00061,0.0003 +azure,meta-llama-3.1-70b-instruct,0.00268,0.00354,0.00268 +azure,meta-llama-3.1-405b-instruct,0.00533,0.016,0.00533 +azure,phi-4-mini-instruct,0.000075,0.0003,0.000075 +azure,phi-4-multimodal-instruct,0.00008,0.00032,0.00008 +azure,phi-4,0.000125,0.0005,0.000125 +azure,phi-3.5-mini-instruct,0.00013,0.00052,0.00013 +azure,phi-3.5-vision-instruct,0.00013,0.00052,0.00013 +azure,phi-3.5-moe-instruct,0.00016,0.00064,0.00016 +azure,phi-3-mini-4k-instruct,0.00013,0.00052,0.00013 +azure,phi-3-mini-128k-instruct,0.00013,0.00052,0.00013 +azure,phi-3-small-8k-instruct,0.00015,0.0006,0.00015 +azure,phi-3-small-128k-instruct,0.00015,0.0006,0.00015 +azure,phi-3-medium-4k-instruct,0.00017,0.00068,0.00017 +azure,phi-3-medium-128k-instruct,0.00017,0.00068,0.00017 +mistral,mistral-tiny,0.00025,0.00025,0.00025 +mistral,mistral-small,0.0001,0.0003,0.0001 +mistral,mistral-small-latest,0.0001,0.0003,0.0001 +mistral,mistral-medium,0.0027,0.0081,0.0027 +mistral,mistral-medium-latest,0.0004,0.002,0.0004 +mistral,mistral-medium-2505,0.0004,0.002,0.0004 +mistral,mistral-medium-2312,0.0027,0.0081,0.0027 +mistral,mistral-large-latest,0.002,0.006,0.002 +mistral,mistral-large-2411,0.002,0.006,0.002 +mistral,mistral-large-2402,0.004,0.012,0.004 +mistral,mistral-large-2407,0.003,0.009,0.003 +mistral,pixtral-large-latest,0.002,0.006,0.002 +mistral,pixtral-large-2411,0.002,0.006,0.002 +mistral,pixtral-12b-2409,0.00015,0.00015,0.00015 +mistral,open-mistral-7b,0.00025,0.00025,0.00025 +mistral,open-mixtral-8x7b,0.0007,0.0007,0.0007 +mistral,open-mixtral-8x22b,0.002,0.006,0.002 +mistral,codestral-latest,0.001,0.003,0.001 +mistral,codestral-2405,0.001,0.003,0.001 +mistral,open-mistral-nemo,0.0003,0.0003,0.0003 +mistral,open-mistral-nemo-2407,0.0003,0.0003,0.0003 +mistral,open-codestral-mamba,0.00025,0.00025,0.00025 +mistral,codestral-mamba-latest,0.00025,0.00025,0.00025 +mistral,devstral-small-2505,0.0001,0.0003,0.0001 +mistral,devstral-small-2507,0.0001,0.0003,0.0001 +mistral,devstral-medium-2507,0.0004,0.002,0.0004 +mistral,magistral-medium-latest,0.002,0.005,0.002 +mistral,magistral-medium-2506,0.002,0.005,0.002 +mistral,magistral-small-latest,0.0005,0.0015,0.0005 +mistral,magistral-small-2506,0.0005,0.0015,0.0005 +deepseek,deepseek-reasoner,0.00055,0.00219,0.00055 +deepseek,deepseek-chat,0.00027,0.0011,0.00007 +deepseek,deepseek-r1,0.00055,0.00219,0.00055 +deepseek,deepseek-v3,0.00027,0.0011,0.00007 +xai,grok-beta,0.005,0.015,0.005 +xai,grok-2-vision-1212,0.002,0.01,0.002 +xai,grok-2-vision-latest,0.002,0.01,0.002 +xai,grok-2-vision,0.002,0.01,0.002 +xai,grok-3,0.003,0.015,0.003 +xai,grok-3-latest,0.003,0.015,0.003 +xai,grok-3-beta,0.003,0.015,0.003 +xai,grok-3-fast-beta,0.005,0.025,0.005 +xai,grok-3-fast-latest,0.005,0.025,0.005 +xai,grok-3-mini,0.0003,0.0005,0.0003 +xai,grok-3-mini-latest,0.0003,0.0005,0.0003 +xai,grok-3-mini-fast,0.0006,0.004,0.0006 +xai,grok-3-mini-fast-latest,0.0006,0.004,0.0006 +xai,grok-3-mini-beta,0.0003,0.0005,0.0003 +xai,grok-3-mini-fast-beta,0.0006,0.004,0.0006 +xai,grok-vision-beta,0.005,0.015,0.005 +xai,grok-2-1212,0.002,0.01,0.002 +xai,grok-2,0.002,0.01,0.002 +xai,grok-2-latest,0.002,0.01,0.002 +xai,grok-4,0.003,0.015,0.003 +xai,grok-4-0709,0.003,0.015,0.003 +xai,grok-4-latest,0.003,0.015,0.003 +deepseek,deepseek-coder,0.00014,0.00028,0.00014 +groq,deepseek-r1-distill-llama-70b,0.00075,0.00099,0.00075 +groq,llama-3.3-70b-versatile,0.00059,0.00079,0.00059 +groq,llama-3.3-70b-specdec,0.00059,0.00099,0.00059 +groq,llama-guard-3-8b,0.0002,0.0002,0.0002 +groq,llama2-70b-4096,0.0007,0.0008,0.0007 +groq,llama3-8b-8192,0.00005,0.00008,0.00005 +groq,llama-3.2-1b-preview,0.00004,0.00004,0.00004 +groq,llama-3.2-3b-preview,0.00006,0.00006,0.00006 +groq,llama-3.2-11b-text-preview,0.00018,0.00018,0.00018 +groq,llama-3.2-11b-vision-preview,0.00018,0.00018,0.00018 +groq,llama-3.2-90b-text-preview,0.0009,0.0009,0.0009 +groq,llama-3.2-90b-vision-preview,0.0009,0.0009,0.0009 +groq,llama3-70b-8192,0.00059,0.00079,0.00059 +groq,llama-3.1-8b-instant,0.00005,0.00008,0.00005 +groq,llama-3.1-70b-versatile,0.00059,0.00079,0.00059 +groq,llama-3.1-405b-reasoning,0.00059,0.00079,0.00059 +groq,mistral-saba-24b,0.00079,0.00079,0.00079 +groq,mixtral-8x7b-32768,0.00024,0.00024,0.00024 +groq,gemma-7b-it,0.00007,0.00007,0.00007 +groq,gemma2-9b-it,0.0002,0.0002,0.0002 +groq,llama3-groq-70b-8192-tool-use-preview,0.00089,0.00089,0.00089 +groq,llama3-groq-8b-8192-tool-use-preview,0.00019,0.00019,0.00019 +cerebras,llama3.1-8b,0.0001,0.0001,0.0001 +cerebras,llama3.1-70b,0.0006,0.0006,0.0006 +cerebras,llama-3.3-70b,0.00085,0.0012,0.00085 +cerebras,qwen-3-32b,0.0004,0.0008,0.0004 +anthropic,claude-3-haiku-20240307,0.00025,0.00125,0.00003 +anthropic,claude-3-5-haiku-20241022,0.0008,0.004,0.00008 +anthropic,claude-3-5-haiku-latest,0.001,0.005,0.0001 +anthropic,claude-3-opus-latest,0.015,0.075,0.0015 +anthropic,claude-3-opus-20240229,0.015,0.075,0.0015 +anthropic,claude-3-5-sonnet-latest,0.003,0.015,0.0003 +anthropic,claude-3-5-sonnet-20240620,0.003,0.015,0.0003 +anthropic,claude-opus-4-20250514,0.015,0.075,0.0015 +anthropic,claude-opus-4-1,0.015,0.075,0.0015 +anthropic,claude-opus-4-1-20250805,0.015,0.075,0.0015 +anthropic,claude-sonnet-4-20250514,0.003,0.015,0.0003 +anthropic,claude-4-opus-20250514,0.015,0.075,0.0015 +anthropic,claude-4-sonnet-20250514,0.003,0.015,0.0003 +anthropic,claude-3-7-sonnet-latest,0.003,0.015,0.0003 +anthropic,claude-3-7-sonnet-20250219,0.003,0.015,0.0003 +anthropic,claude-3-5-sonnet-20241022,0.003,0.015,0.0003 +vertex,text-bison32k,0.000125,0.000125,0.000125 +vertex,text-bison32k@002,0.000125,0.000125,0.000125 +vertex,text-unicorn,0.01,0.028,0.01 +vertex,text-unicorn@001,0.01,0.028,0.01 +vertex,chat-bison,0.000125,0.000125,0.000125 +vertex,chat-bison@001,0.000125,0.000125,0.000125 +vertex,chat-bison@002,0.000125,0.000125,0.000125 +vertex,chat-bison-32k,0.000125,0.000125,0.000125 +vertex,chat-bison-32k@002,0.000125,0.000125,0.000125 +vertex,code-bison,0.000125,0.000125,0.000125 +vertex,code-bison@001,0.000125,0.000125,0.000125 +vertex,code-bison@002,0.000125,0.000125,0.000125 +vertex,code-bison32k,0.000125,0.000125,0.000125 +vertex,code-bison-32k@002,0.000125,0.000125,0.000125 +vertex,code-gecko@001,0.000125,0.000125,0.000125 +vertex,code-gecko@002,0.000125,0.000125,0.000125 +vertex,code-gecko,0.000125,0.000125,0.000125 +vertex,code-gecko-latest,0.000125,0.000125,0.000125 +vertex,codechat-bison@latest,0.000125,0.000125,0.000125 +vertex,codechat-bison,0.000125,0.000125,0.000125 +vertex,codechat-bison@001,0.000125,0.000125,0.000125 +vertex,codechat-bison@002,0.000125,0.000125,0.000125 +vertex,codechat-bison-32k,0.000125,0.000125,0.000125 +vertex,codechat-bison-32k@002,0.000125,0.000125,0.000125 +vertex,gemini-pro,0.0005,0.0015,0.0005 +vertex,gemini-1.0-pro,0.0005,0.0015,0.0005 +vertex,gemini-1.0-pro-001,0.0005,0.0015,0.0005 +vertex,gemini-1.0-ultra,0.0005,0.0015,0.0005 +vertex,gemini-1.0-ultra-001,0.0005,0.0015,0.0005 +vertex,gemini-1.0-pro-002,0.0005,0.0015,0.0005 +vertex,gemini-1.5-pro,0.00125,0.005,0.00125 +vertex,gemini-1.5-pro-002,0.00125,0.005,0.00125 +vertex,gemini-1.5-pro-001,0.00125,0.005,0.00125 +vertex,gemini-1.5-pro-preview-0514,0.000078125,0.0003125,0.000078125 +vertex,gemini-1.5-pro-preview-0215,0.000078125,0.0003125,0.000078125 +vertex,gemini-1.5-pro-preview-0409,0.000078125,0.0003125,0.000078125 +vertex,gemini-1.5-flash,0.000075,0.0003,0.000075 +vertex,gemini-1.5-flash-exp-0827,0.000004688,0.0000046875,0.000004688 +vertex,gemini-1.5-flash-002,0.000075,0.0003,0.000075 +vertex,gemini-1.5-flash-001,0.000075,0.0003,0.000075 +vertex,gemini-1.5-flash-preview-0514,0.000075,0.0000046875,0.000075 +vertex,gemini-pro-vision,0.0005,0.0015,0.0005 +vertex,gemini-1.0-pro-vision,0.0005,0.0015,0.0005 +vertex,gemini-1.0-pro-vision-001,0.0005,0.0015,0.0005 +vertex,gemini-2.5-pro-exp-03-25,0.00125,0.01,0.0003125 +vertex,gemini-2.0-pro-exp-02-05,0.00125,0.01,0.0003125 +vertex,gemini-2.0-flash-exp,0.00015,0.0006,0.0000375 +vertex,gemini-2.0-flash-001,0.00015,0.0006,0.0000375 +vertex,gemini-2.5-pro,0.00125,0.01,0.0003125 +gemini,models/gemini-2.5-pro,0.00125,0.01,0.0003125 +gemini,models/gemini-2.5-flash,0.0003,0.0025,0.000075 +vertex,gemini-2.5-flash,0.0003,0.0025,0.000075 +gemini,models/gemini-2.0-flash-live-001,0.00035,0.0015,0.000075 +gemini,models/gemini-2.5-flash-preview-tts,0.00015,0.0006,0.0000375 +gemini,models/gemini-2.5-flash-preview-05-20,0.0003,0.0025,0.000075 +gemini,models/gemini-2.5-flash-preview-04-17,0.00015,0.0006,0.0000375 +gemini,models/gemini-2.5-flash-lite-preview-06-17,0.0001,0.0004,0.000025 +gemini,models/gemini-2.5-flash-lite,0.0001,0.0004,0.000025 +vertex,gemini-2.5-flash-preview-05-20,0.0003,0.0025,0.000075 +vertex,gemini-2.5-flash-preview-04-17,0.00015,0.0006,0.0000375 +vertex,gemini-2.5-flash-lite-preview-06-17,0.0001,0.0004,0.000025 +vertex,gemini-2.5-flash-lite,0.0001,0.0004,0.000025 +vertex,gemini-2.0-flash,0.0001,0.0004,0.000025 +vertex,gemini-2.0-flash-lite,0.000075,0.0003,0.00001875 +vertex,gemini-2.0-flash-lite-001,0.000075,0.0003,0.00001875 +vertex,gemini-2.5-pro-preview-06-05,0.00125,0.01,0.0003125 +vertex,gemini-2.5-pro-preview-05-06,0.00125,0.01,0.0003125 +vertex,gemini-2.5-pro-preview-03-25,0.00125,0.01,0.0003125 +vertex,gemini-2.0-flash-preview-image-generation,0.0001,0.0004,0.000025 +vertex,gemini-2.5-pro-preview-tts,0.00125,0.01,0.0003125 +gemini,models/gemini-2.0-flash-preview-image-generation,0.0001,0.0004,0.000025 +gemini,models/gemini-2.0-flash,0.0001,0.0004,0.000025 +gemini,models/gemini-2.0-flash-lite,0.000075,0.0003,0.00001875 +gemini,models/gemini-2.0-flash-001,0.0001,0.0004,0.000025 +gemini,models/gemini-2.5-pro-preview-tts,0.00125,0.01,0.0003125 +gemini,models/gemini-2.5-pro-preview-06-05,0.00125,0.01,0.0003125 +gemini,models/gemini-2.5-pro-preview-05-06,0.00125,0.01,0.0003125 +gemini,models/gemini-2.5-pro-preview-03-25,0.00125,0.01,0.0003125 +gemini,models/gemini-2.0-flash-lite-preview-02-05,0.000075,0.0003,0.00001875 +vertex,gemini-2.0-flash-live-preview-04-09,0.0005,0.002,0.000075 +gemini,models/gemini-1.5-flash-002,0.000075,0.0003,0.00001875 +gemini,models/gemini-1.5-flash-001,0.000075,0.0003,0.00001875 +gemini,models/gemini-1.5-flash,0.000075,0.0003,0.000075 +gemini,models/gemini-1.5-flash-latest,0.000075,0.0003,0.000075 +gemini,models/gemini-pro,0.00035,0.00105,0.00035 +gemini,models/gemini-1.5-pro,0.0035,0.0105,0.0035 +gemini,models/gemini-1.5-pro-002,0.0035,0.0105,0.0035 +gemini,models/gemini-1.5-pro-001,0.0035,0.0105,0.0035 +gemini,models/gemini-1.5-pro-exp-0801,0.0035,0.0105,0.0035 +gemini,models/gemini-1.5-pro-latest,0.0035,0.00105,0.0035 +gemini,models/gemini-pro-vision,0.00035,0.00105,0.00035 +gemini,models/gemini-gemma-2-27b-it,0.00035,0.00105,0.00035 +gemini,models/gemini-gemma-2-9b-it,0.00035,0.00105,0.00035 +cohere,command-a-03-2025,0.0025,0.01,0.0025 +cohere,command-r,0.00015,0.0006,0.00015 +cohere,command-r-08-2024,0.00015,0.0006,0.00015 +cohere,command-r7b-12-2024,0.00015,0.0000375,0.00015 +cohere,command-light,0.0003,0.0006,0.0003 +cohere,command-r-plus,0.0025,0.01,0.0025 +cohere,command-r-plus-08-2024,0.0025,0.01,0.0025 +cohere,command-nightly,0.001,0.002,0.001 +cohere,command,0.001,0.002,0.001 +bedrock,ai21.j2-mid-v1,0.0125,0.0125,0.0125 +bedrock,ai21.j2-ultra-v1,0.0188,0.0188,0.0188 +bedrock,ai21.jamba-instruct-v1:0,0.0005,0.0007,0.0005 +bedrock,ai21.jamba-1-5-large-v1:0,0.002,0.008,0.002 +bedrock,ai21.jamba-1-5-mini-v1:0,0.0002,0.0004,0.0002 +bedrock,amazon.titan-text-lite-v1,0.0003,0.0004,0.0003 +bedrock,amazon.titan-text-express-v1,0.0013,0.0017,0.0013 +bedrock,amazon.titan-text-premier-v1:0,0.0005,0.0015,0.0005 +bedrock,mistral.mistral-7b-instruct-v0:2,0.00015,0.0002,0.00015 +bedrock,mistral.mixtral-8x7b-instruct-v0:1,0.00045,0.0007,0.00045 +bedrock,mistral.mistral-large-2402-v1:0,0.008,0.024,0.008 +bedrock,mistral.mistral-large-2407-v1:0,0.003,0.009,0.003 +bedrock,mistral.mistral-small-2402-v1:0,0.001,0.003,0.001 +bedrock,eu.mistral.pixtral-large-2502-v1:0,0.002,0.006,0.002 +bedrock,us.mistral.pixtral-large-2502-v1:0,0.002,0.006,0.002 +bedrock,amazon.nova-micro-v1:0,0.000035,0.00014,0.000035 +bedrock,us.amazon.nova-micro-v1:0,0.000035,0.00014,0.000035 +bedrock,eu.amazon.nova-micro-v1:0,0.000046,0.000184,0.000046 +bedrock,amazon.nova-lite-v1:0,0.00006,0.00024,0.00006 +bedrock,us.amazon.nova-lite-v1:0,0.00006,0.00024,0.00006 +bedrock,eu.amazon.nova-lite-v1:0,0.000078,0.000312,0.000078 +bedrock,amazon.nova-pro-v1:0,0.0008,0.0032,0.0008 +bedrock,us.amazon.nova-pro-v1:0,0.0008,0.0032,0.0008 +bedrock,eu.amazon.nova-pro-v1:0,0.00105,0.0042,0.00105 +bedrock,apac.amazon.nova-micro-v1:0,0.000037,0.000148,0.000037 +bedrock,apac.amazon.nova-lite-v1:0,0.000063,0.000252,0.000063 +bedrock,apac.amazon.nova-pro-v1:0,0.00084,0.00336,0.00084 +bedrock,us.amazon.nova-premier-v1:0,0.0025,0.0125,0.0025 +bedrock,anthropic.claude-3-sonnet-20240229-v1:0,0.003,0.015,0.003 +bedrock,anthropic.claude-3-5-sonnet-20240620-v1:0,0.003,0.015,0.003 +bedrock,openai.gpt-oss-20b-1:0,0.00007,0.0003,0.00007 +bedrock,openai.gpt-oss-120b-1:0,0.00015,0.0006,0.00015 +bedrock,anthropic.claude-opus-4-1-20250805-v1:0,0.015,0.075,0.0015 +bedrock,anthropic.claude-opus-4-20250514-v1:0,0.015,0.075,0.0015 +bedrock,anthropic.claude-sonnet-4-20250514-v1:0,0.003,0.015,0.0003 +bedrock,anthropic.claude-3-7-sonnet-20250219-v1:0,0.003,0.015,0.0003 +bedrock,anthropic.claude-3-5-sonnet-20241022-v2:0,0.003,0.015,0.0003 +bedrock,anthropic.claude-3-haiku-20240307-v1:0,0.00025,0.00125,0.00025 +bedrock,anthropic.claude-3-5-haiku-20241022-v1:0,0.0008,0.004,0.00008 +bedrock,anthropic.claude-3-opus-20240229-v1:0,0.015,0.075,0.015 +bedrock,us.anthropic.claude-3-sonnet-20240229-v1:0,0.003,0.015,0.003 +bedrock,us.anthropic.claude-3-5-sonnet-20240620-v1:0,0.003,0.015,0.003 +bedrock,us.anthropic.claude-3-5-sonnet-20241022-v2:0,0.003,0.015,0.0003 +bedrock,us.anthropic.claude-3-7-sonnet-20250219-v1:0,0.003,0.015,0.0003 +bedrock,us.anthropic.claude-opus-4-1-20250805-v1:0,0.015,0.075,0.0015 +bedrock,us.anthropic.claude-opus-4-20250514-v1:0,0.015,0.075,0.0015 +bedrock,us.anthropic.claude-sonnet-4-20250514-v1:0,0.003,0.015,0.0003 +bedrock,us.anthropic.claude-3-haiku-20240307-v1:0,0.00025,0.00125,0.00025 +bedrock,us.anthropic.claude-3-5-haiku-20241022-v1:0,0.0008,0.004,0.00008 +bedrock,us.anthropic.claude-3-opus-20240229-v1:0,0.015,0.075,0.015 +bedrock,eu.anthropic.claude-3-sonnet-20240229-v1:0,0.003,0.015,0.003 +bedrock,eu.anthropic.claude-3-5-sonnet-20240620-v1:0,0.003,0.015,0.003 +bedrock,eu.anthropic.claude-3-5-sonnet-20241022-v2:0,0.003,0.015,0.003 +bedrock,eu.anthropic.claude-3-7-sonnet-20250219-v1:0,0.003,0.015,0.003 +bedrock,eu.anthropic.claude-3-haiku-20240307-v1:0,0.00025,0.00125,0.00025 +bedrock,eu.anthropic.claude-opus-4-1-20250805-v1:0,0.015,0.075,0.0015 +bedrock,eu.anthropic.claude-opus-4-20250514-v1:0,0.015,0.075,0.0015 +bedrock,eu.anthropic.claude-sonnet-4-20250514-v1:0,0.003,0.015,0.0003 +bedrock,apac.anthropic.claude-3-haiku-20240307-v1:0,0.00025,0.00125,0.00025 +bedrock,apac.anthropic.claude-3-sonnet-20240229-v1:0,0.003,0.015,0.003 +bedrock,apac.anthropic.claude-3-5-sonnet-20240620-v1:0,0.003,0.015,0.003 +bedrock,apac.anthropic.claude-3-5-sonnet-20241022-v2:0,0.003,0.015,0.0003 +bedrock,apac.anthropic.claude-sonnet-4-20250514-v1:0,0.003,0.015,0.0003 +bedrock,eu.anthropic.claude-3-5-haiku-20241022-v1:0,0.00025,0.00125,0.00025 +bedrock,eu.anthropic.claude-3-opus-20240229-v1:0,0.015,0.075,0.015 +bedrock,anthropic.claude-v1,0.008,0.024,0.008 +bedrock,anthropic.claude-v2,0.008,0.024,0.008 +bedrock,anthropic.claude-v2:1,0.008,0.024,0.008 +bedrock,anthropic.claude-instant-v1,0.0008,0.0024,0.0008 +bedrock,cohere.command-text-v14,0.0015,0.002,0.0015 +bedrock,cohere.command-light-text-v14,0.0003,0.0006,0.0003 +bedrock,cohere.command-r-plus-v1:0,0.003,0.015,0.003 +bedrock,cohere.command-r-v1:0,0.0005,0.0015,0.0005 +bedrock,us.deepseek.r1-v1:0,0.00135,0.0054,0.00135 +bedrock,meta.llama3-3-70b-instruct-v1:0,0.00072,0.00072,0.00072 +bedrock,meta.llama2-13b-chat-v1,0.00075,0.001,0.00075 +bedrock,meta.llama2-70b-chat-v1,0.00195,0.00256,0.00195 +bedrock,meta.llama3-8b-instruct-v1:0,0.0003,0.0006,0.0003 +bedrock,meta.llama3-70b-instruct-v1:0,0.00265,0.0035,0.00265 +bedrock,meta.llama3-1-8b-instruct-v1:0,0.00022,0.00022,0.00022 +bedrock,us.meta.llama3-1-8b-instruct-v1:0,0.00022,0.00022,0.00022 +bedrock,meta.llama3-1-70b-instruct-v1:0,0.00099,0.00099,0.00099 +bedrock,us.meta.llama3-1-70b-instruct-v1:0,0.00099,0.00099,0.00099 +bedrock,meta.llama3-1-405b-instruct-v1:0,0.00532,0.016,0.00532 +bedrock,us.meta.llama3-1-405b-instruct-v1:0,0.00532,0.016,0.00532 +bedrock,meta.llama3-2-1b-instruct-v1:0,0.0001,0.0001,0.0001 +bedrock,us.meta.llama3-2-1b-instruct-v1:0,0.0001,0.0001,0.0001 +bedrock,eu.meta.llama3-2-1b-instruct-v1:0,0.00013,0.00013,0.00013 +bedrock,meta.llama3-2-3b-instruct-v1:0,0.00015,0.00015,0.00015 +bedrock,us.meta.llama3-2-3b-instruct-v1:0,0.00015,0.00015,0.00015 +bedrock,eu.meta.llama3-2-3b-instruct-v1:0,0.00019,0.00019,0.00019 +bedrock,meta.llama3-2-11b-instruct-v1:0,0.00035,0.00035,0.00035 +bedrock,us.meta.llama3-2-11b-instruct-v1:0,0.00035,0.00035,0.00035 +bedrock,meta.llama3-2-90b-instruct-v1:0,0.002,0.002,0.002 +bedrock,us.meta.llama3-2-90b-instruct-v1:0,0.002,0.002,0.002 +bedrock,us.meta.llama3-3-70b-instruct-v1:0,0.00072,0.00072,0.00072 +bedrock,meta.llama4-maverick-17b-instruct-v1:0,0.00024,0.00097,0.00024 +bedrock,us.meta.llama4-maverick-17b-instruct-v1:0,0.00024,0.00097,0.00024 +bedrock,meta.llama4-scout-17b-instruct-v1:0,0.00017,0.00066,0.00017 +bedrock,us.meta.llama4-scout-17b-instruct-v1:0,0.00017,0.00066,0.00017 +together,together-ai-up-to-4b,0.0001,0.0001,0.0001 +together,together-ai-4.1b-8b,0.0002,0.0002,0.0002 +together,together-ai-8.1b-21b,0.0003,0.0003,0.0003 +together,together-ai-21.1b-41b,0.0008,0.0008,0.0008 +together,together-ai-41.1b-80b,0.0009,0.0009,0.0009 +together,together-ai-81.1b-110b,0.0018,0.0018,0.0018 +perplexity,codellama-34b-instruct,0.00035,0.0014,0.00035 +perplexity,codellama-70b-instruct,0.0007,0.0028,0.0007 +perplexity,llama-3.1-70b-instruct,0.001,0.001,0.001 +perplexity,llama-3.1-8b-instruct,0.0002,0.0002,0.0002 +perplexity,llama-3.1-sonar-huge-128k-online,0.005,0.005,0.005 +perplexity,llama-3.1-sonar-large-128k-online,0.001,0.001,0.001 +perplexity,llama-3.1-sonar-large-128k-chat,0.001,0.001,0.001 +perplexity,llama-3.1-sonar-small-128k-chat,0.0002,0.0002,0.0002 +perplexity,llama-3.1-sonar-small-128k-online,0.0002,0.0002,0.0002 +perplexity,pplx-7b-chat,0.00007,0.00028,0.00007 +perplexity,pplx-70b-chat,0.0007,0.0028,0.0007 +perplexity,llama-2-70b-chat,0.0007,0.0028,0.0007 +perplexity,mistral-7b-instruct,0.00007,0.00028,0.00007 +perplexity,mixtral-8x7b-instruct,0.00007,0.00028,0.00007 +perplexity,sonar-small-chat,0.00007,0.00028,0.00007 +perplexity,sonar-medium-chat,0.0006,0.0018,0.0006 +perplexity,sonar,0.001,0.001,0.001 +perplexity,sonar-pro,0.003,0.015,0.003 +perplexity,sonar-reasoning,0.001,0.005,0.001 +perplexity,sonar-reasoning-pro,0.002,0.008,0.002 +perplexity,sonar-deep-research,0.002,0.008,0.002 +fireworks,fireworks-ai-up-to-4b,0.0002,0.0002,0.0002 +fireworks,fireworks-ai-4.1b-to-16b,0.0002,0.0002,0.0002 +fireworks,fireworks-ai-above-16b,0.0009,0.0009,0.0009 +fireworks,fireworks-ai-moe-up-to-56b,0.0005,0.0005,0.0005 +fireworks,fireworks-ai-56b-to-176b,0.0012,0.0012,0.0012