From 2c29e9c360f35e95f3f81ce77f404e875b6095bb Mon Sep 17 00:00:00 2001
From: "berriai-litellm-provider-info-sync[bot]"
 <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
Date: Thu, 8 Oct 2026 19:28:25 -0700
Subject: [PATCH] fix(bedrock): add gpt-6.1-sol ultrafast tier prices from the
 Bedrock model card (#45482)

Price-Sync: litellm-providers

Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
---
 ...odel_prices_and_context_window_backup.json | 24 +++++++++++++++++++
 model_prices_and_context_window.json          | 24 +++++++++++++++++++
 2 files changed, 48 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 7930a823e07..093a16aaf8a 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -80595,10 +80595,16 @@
     "global.openai.gpt-6.1-sol": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.5e-05,
         "cache_read_input_token_cost": 1e-07,
         "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06,
+        "cache_read_input_token_cost_ultrafast": 6e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05,
+        "input_cost_per_token_ultrafast": 1.2e-05,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1050000,
         "max_output_tokens": 131072,
@@ -80606,6 +80612,8 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05,
+        "output_cost_per_token_ultrafast": 6e-05,
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -80633,10 +80641,16 @@
     "bedrock_mantle/openai.gpt-6.1-sol": {
         "cache_creation_input_token_cost": 2.75e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.65e-05,
         "cache_read_input_token_cost": 1.1e-07,
         "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06,
+        "cache_read_input_token_cost_ultrafast": 6.6e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05,
+        "input_cost_per_token_ultrafast": 1.32e-05,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 1050000,
         "max_output_tokens": 131072,
@@ -80644,6 +80658,8 @@
         "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05,
+        "output_cost_per_token_ultrafast": 6.6e-05,
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -80672,10 +80688,16 @@
     "us.openai.gpt-6.1-sol": {
         "cache_creation_input_token_cost": 2.75e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.65e-05,
         "cache_read_input_token_cost": 1.1e-07,
         "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06,
+        "cache_read_input_token_cost_ultrafast": 6.6e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05,
+        "input_cost_per_token_ultrafast": 1.32e-05,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1050000,
         "max_output_tokens": 131072,
@@ -80683,6 +80705,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05,
+        "output_cost_per_token_ultrafast": 6.6e-05,
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
         "supported_endpoints": [
             "/v1/chat/completions",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 7930a823e07..093a16aaf8a 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -80595,10 +80595,16 @@
     "global.openai.gpt-6.1-sol": {
         "cache_creation_input_token_cost": 2.5e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.5e-05,
         "cache_read_input_token_cost": 1e-07,
         "cache_read_input_token_cost_above_272k_tokens": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.2e-06,
+        "cache_read_input_token_cost_ultrafast": 6e-07,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_above_272k_tokens": 4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.4e-05,
+        "input_cost_per_token_ultrafast": 1.2e-05,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1050000,
         "max_output_tokens": 131072,
@@ -80606,6 +80612,8 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_272k_tokens": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9e-05,
+        "output_cost_per_token_ultrafast": 6e-05,
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -80633,10 +80641,16 @@
     "bedrock_mantle/openai.gpt-6.1-sol": {
         "cache_creation_input_token_cost": 2.75e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.65e-05,
         "cache_read_input_token_cost": 1.1e-07,
         "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06,
+        "cache_read_input_token_cost_ultrafast": 6.6e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05,
+        "input_cost_per_token_ultrafast": 1.32e-05,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 1050000,
         "max_output_tokens": 131072,
@@ -80644,6 +80658,8 @@
         "mode": "responses",
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05,
+        "output_cost_per_token_ultrafast": 6.6e-05,
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -80672,10 +80688,16 @@
     "us.openai.gpt-6.1-sol": {
         "cache_creation_input_token_cost": 2.75e-06,
         "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 3.3e-05,
+        "cache_creation_input_token_cost_ultrafast": 1.65e-05,
         "cache_read_input_token_cost": 1.1e-07,
         "cache_read_input_token_cost_above_272k_tokens": 2.2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_ultrafast": 1.32e-06,
+        "cache_read_input_token_cost_ultrafast": 6.6e-07,
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
+        "input_cost_per_token_above_272k_tokens_ultrafast": 2.64e-05,
+        "input_cost_per_token_ultrafast": 1.32e-05,
         "litellm_provider": "bedrock_converse",
         "max_input_tokens": 1050000,
         "max_output_tokens": 131072,
@@ -80683,6 +80705,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.1e-05,
         "output_cost_per_token_above_272k_tokens": 1.65e-05,
+        "output_cost_per_token_above_272k_tokens_ultrafast": 9.9e-05,
+        "output_cost_per_token_ultrafast": 6.6e-05,
         "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-1-sol.html",
         "supported_endpoints": [
             "/v1/chat/completions",