[[providers]]
key = "anthropic"
display_name = "Anthropic"
kind = "remote"
auth_mode = "bearer"
credential_env_var = "ANTHROPIC_API_KEY"
base_url_env_var = "ANTHROPIC_BASE_URL"
default_base_url = "https://api.anthropic.com"
[[providers.presets]]
id = "sonnet_46"
display_name = "Anthropic Sonnet 4.6"
group = "sonnet"
model_id = "claude-sonnet-4-6"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 16384
cost_per_million_input = 3.0
cost_per_million_output = 15.0
cost_per_million_cache_read = 0.30
cost_per_million_cache_write = 3.75
[[providers.presets]]
id = "opus_46"
display_name = "Anthropic Opus 4.6"
group = "opus"
model_id = "claude-opus-4-6"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 32768
cost_per_million_input = 15.0
cost_per_million_output = 75.0
cost_per_million_cache_read = 1.50
cost_per_million_cache_write = 18.75
[[providers.presets]]
id = "haiku_45"
display_name = "Anthropic Haiku 4.5"
group = "haiku"
model_id = "claude-haiku-4-5-20251001"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 8192
cost_per_million_input = 0.80
cost_per_million_output = 4.0
cost_per_million_cache_read = 0.08
cost_per_million_cache_write = 1.0
[[providers]]
key = "openai"
display_name = "OpenAI"
kind = "remote"
auth_mode = "bearer"
credential_env_var = "OPENAI_API_KEY"
base_url_env_var = "OPENAI_BASE_URL"
default_base_url = "https://api.openai.com"
[[providers.presets]]
id = "gpt_5"
display_name = "OpenAI GPT-5"
group = "gpt5"
model_id = "gpt-5"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 1000000
max_output_tokens = 32768
cost_per_million_input = 10.0
cost_per_million_output = 30.0
cost_per_million_cache_read = 2.50
cost_per_million_cache_write = 10.0
[[providers.presets]]
id = "gpt_5_2025_08_07"
display_name = "OpenAI GPT-5 (2025-08-07)"
group = "gpt5"
model_id = "gpt-5-2025-08-07"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 1000000
max_output_tokens = 32768
cost_per_million_input = 10.0
cost_per_million_output = 30.0
cost_per_million_cache_read = 2.50
cost_per_million_cache_write = 10.0
[[providers.presets]]
id = "gpt_5_mini"
display_name = "OpenAI GPT-5 Mini"
group = "gpt5"
model_id = "gpt-5-mini"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 1000000
max_output_tokens = 32768
cost_per_million_input = 1.50
cost_per_million_output = 6.0
cost_per_million_cache_read = 0.375
cost_per_million_cache_write = 1.50
[[providers.presets]]
id = "gpt_5_mini_2025_08_07"
display_name = "OpenAI GPT-5 Mini (2025-08-07)"
group = "gpt5"
model_id = "gpt-5-mini-2025-08-07"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 1000000
max_output_tokens = 32768
cost_per_million_input = 1.50
cost_per_million_output = 6.0
cost_per_million_cache_read = 0.375
cost_per_million_cache_write = 1.50
[[providers.presets]]
id = "gpt_5_nano"
display_name = "OpenAI GPT-5 Nano"
group = "gpt5"
model_id = "gpt-5-nano"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 1000000
max_output_tokens = 32768
cost_per_million_input = 0.50
cost_per_million_output = 2.0
cost_per_million_cache_read = 0.125
cost_per_million_cache_write = 0.50
[[providers.presets]]
id = "gpt_5_nano_2025_08_07"
display_name = "OpenAI GPT-5 Nano (2025-08-07)"
group = "gpt5"
model_id = "gpt-5-nano-2025-08-07"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 1000000
max_output_tokens = 32768
cost_per_million_input = 0.50
cost_per_million_output = 2.0
cost_per_million_cache_read = 0.125
cost_per_million_cache_write = 0.50
[[providers.presets]]
id = "gpt_5_4"
display_name = "OpenAI GPT-5.4"
group = "gpt54"
model_id = "gpt-5.4"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 1050000
max_output_tokens = 128000
cost_per_million_input = 2.50
cost_per_million_output = 15.0
cost_per_million_cache_read = 0.25
cost_per_million_cache_write = 2.50
[[providers.presets]]
id = "gpt_5_4_mini"
display_name = "OpenAI GPT-5.4 Mini"
group = "gpt54"
model_id = "gpt-5.4-mini"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 400000
max_output_tokens = 32768
cost_per_million_input = 0.75
cost_per_million_output = 4.50
cost_per_million_cache_read = 0.075
cost_per_million_cache_write = 0.75
[[providers.presets]]
id = "gpt_5_4_nano"
display_name = "OpenAI GPT-5.4 Nano"
group = "gpt54"
model_id = "gpt-5.4-nano"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 400000
max_output_tokens = 32768
cost_per_million_input = 0.20
cost_per_million_output = 1.25
cost_per_million_cache_read = 0.02
cost_per_million_cache_write = 0.20
[[providers]]
key = "local"
display_name = "Local"
kind = "local"
[[providers.presets]]
id = "smollm3_3b"
display_name = "Local SmolLM3-3B"
group = "legacy"
model_id = "SmolLM3-3B-Q4_K_M"
capabilities = ["text", "streaming"]
include_by_default = false
repo_id = "unsloth/SmolLM3-3B-GGUF"
filename = "SmolLM3-3B-Q4_K_M.gguf"
context_window_tokens = 8192
max_output_tokens = 2048
[[providers.presets]]
id = "gemma4_e2b"
display_name = "Gemma 4 E2B (Ollama)"
group = "default"
model_id = "gemma4:e2b"
capabilities = ["text", "tools", "streaming", "thinking"]
include_by_default = true
context_window_tokens = 128000
max_output_tokens = 8192
[[providers.presets]]
id = "gemma4_e4b"
display_name = "Gemma 4 E4B (Ollama)"
group = "default"
model_id = "gemma4:e4b"
capabilities = ["text", "tools", "streaming", "thinking"]
context_window_tokens = 128000
max_output_tokens = 8192
[[providers.presets]]
id = "gemma4_26b"
display_name = "Gemma 4 26B MoE (Ollama)"
group = "large"
model_id = "gemma4:26b"
capabilities = ["text", "tools", "streaming", "thinking"]
context_window_tokens = 256000
max_output_tokens = 8192
[[providers]]
key = "google"
display_name = "Google"
kind = "remote"
auth_mode = "api_key_header"
credential_env_var = "GEMINI_API_KEY"
base_url_env_var = "GEMINI_BASE_URL"
default_base_url = "https://generativelanguage.googleapis.com"
[[providers.presets]]
id = "gemini_3_1_pro"
display_name = "Google Gemini 3.1 Pro"
group = "gemini_3_1"
model_id = "gemini-3.1-pro-preview"
api_version = "v1beta"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "preview"
context_window_tokens = 1000000
max_output_tokens = 65536
cost_per_million_input = 2.50
cost_per_million_output = 15.0
[[providers.presets]]
id = "gemini_3_1_deep_think"
display_name = "Google Gemini 3.1 Deep Think"
group = "gemini_3_1"
model_id = "gemini-3.1-deep-think-preview"
api_version = "v1beta"
capabilities = ["text", "tools", "thinking", "images_in", "streaming"]
status = "preview"
context_window_tokens = 1000000
max_output_tokens = 65536
cost_per_million_input = 2.50
cost_per_million_output = 15.0
[[providers.presets]]
id = "gemini_3_flash"
display_name = "Google Gemini 3 Flash"
group = "gemini_3"
model_id = "gemini-3-flash-preview"
api_version = "v1beta"
capabilities = ["text", "tools", "thinking", "images_in", "streaming", "structured_output"]
status = "preview"
context_window_tokens = 1000000
max_output_tokens = 65536
cost_per_million_input = 0.15
cost_per_million_output = 0.60
[[providers.presets]]
id = "gemini_3_1_flash_lite"
display_name = "Google Gemini 3.1 Flash-Lite"
group = "gemini_3_1"
model_id = "gemini-3.1-flash-lite-preview"
api_version = "v1beta"
capabilities = ["text", "tools", "thinking", "images_in", "streaming"]
status = "preview"
context_window_tokens = 1000000
max_output_tokens = 65536
cost_per_million_input = 0.075
cost_per_million_output = 0.30
[[providers]]
key = "azure"
display_name = "Azure"
kind = "remote"
auth_mode = "api_key_header"
credential_env_var = "AZURE_API_KEY"
base_url_env_var = "AZURE_BASE_URL"
requires_base_url = true
[[providers.presets]]
id = "gpt_4o"
display_name = "Azure GPT-4o"
group = "openai"
model_id = "gpt-4o"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 16384
[[providers.presets]]
id = "gpt_4o_mini"
display_name = "Azure GPT-4o Mini"
group = "openai"
model_id = "gpt-4o-mini"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 16384
[[providers.presets]]
id = "phi_4"
display_name = "Azure Phi-4"
group = "foundry"
model_id = "Phi-4"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 16384
max_output_tokens = 4096
[[providers]]
key = "xai"
display_name = "xAI"
kind = "remote"
auth_mode = "bearer"
credential_env_var = "XAI_API_KEY"
base_url_env_var = "XAI_BASE_URL"
default_base_url = "https://api.x.ai"
[[providers.presets]]
id = "grok_4_20_reasoning"
display_name = "xAI Grok 4.20 Reasoning"
group = "grok"
model_id = "grok-4.20-0309-reasoning"
api_version = "v1"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 2000000
max_output_tokens = 16384
cost_per_million_input = 2.0
cost_per_million_output = 6.0
[[providers.presets]]
id = "grok_4_20_non_reasoning"
display_name = "xAI Grok 4.20 Non-Reasoning"
group = "grok"
model_id = "grok-4.20-0309-non-reasoning"
api_version = "v1"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 2000000
max_output_tokens = 16384
cost_per_million_input = 2.0
cost_per_million_output = 6.0
[[providers.presets]]
id = "grok_4_1_fast_reasoning"
display_name = "xAI Grok 4.1 Fast Reasoning"
group = "grok"
model_id = "grok-4-1-fast-reasoning"
api_version = "v1"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 2000000
max_output_tokens = 16384
cost_per_million_input = 0.2
cost_per_million_output = 0.5
[[providers.presets]]
id = "grok_4_1_fast_non_reasoning"
display_name = "xAI Grok 4.1 Fast Non-Reasoning"
group = "grok"
model_id = "grok-4-1-fast-non-reasoning"
api_version = "v1"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 2000000
max_output_tokens = 16384
cost_per_million_input = 0.2
cost_per_million_output = 0.5
[[providers.presets]]
id = "grok_4_20_multi_agent"
display_name = "xAI Grok 4.20 Multi-Agent"
group = "grok"
model_id = "grok-4.20-multi-agent-0309"
api_version = "v1"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 2000000
max_output_tokens = 16384
cost_per_million_input = 2.0
cost_per_million_output = 6.0
[[providers]]
key = "mistral"
display_name = "Mistral"
kind = "remote"
auth_mode = "bearer"
credential_env_var = "MISTRAL_API_KEY"
base_url_env_var = "MISTRAL_BASE_URL"
default_base_url = "https://api.mistral.ai"
[[providers.presets]]
id = "mistral_large"
display_name = "Mistral Large"
group = "mistral"
model_id = "mistral-large-latest"
api_version = "v1"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 8192
cost_per_million_input = 2.0
cost_per_million_output = 6.0
[[providers.presets]]
id = "mistral_medium"
display_name = "Mistral Medium"
group = "mistral"
model_id = "mistral-medium-latest"
api_version = "v1"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 8192
cost_per_million_input = 0.40
cost_per_million_output = 2.0
[[providers.presets]]
id = "mistral_small"
display_name = "Mistral Small"
group = "mistral"
model_id = "mistral-small-latest"
api_version = "v1"
capabilities = ["text", "tools", "images_in", "streaming", "structured_output"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 8192
cost_per_million_input = 0.10
cost_per_million_output = 0.30
[[providers.presets]]
id = "ministral_3b"
display_name = "Ministral 3B"
group = "ministral"
model_id = "ministral-3b-2512"
api_version = "v1"
capabilities = ["text", "images_in", "streaming"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 8192
[[providers.presets]]
id = "ministral_8b"
display_name = "Ministral 8B"
group = "ministral"
model_id = "ministral-8b-2512"
api_version = "v1"
capabilities = ["text", "images_in", "streaming"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 8192
[[providers.presets]]
id = "ministral_14b"
display_name = "Ministral 14B"
group = "ministral"
model_id = "ministral-14b-2512"
api_version = "v1"
capabilities = ["text", "images_in", "streaming"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 8192
[[providers.presets]]
id = "magistral_medium"
display_name = "Magistral Medium"
group = "magistral"
model_id = "magistral-medium-2509"
api_version = "v1"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 40000
max_output_tokens = 8192
[[providers.presets]]
id = "magistral_small"
display_name = "Magistral Small"
group = "magistral"
model_id = "magistral-small-2509"
api_version = "v1"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 40000
max_output_tokens = 8192
[[providers.presets]]
id = "codestral"
display_name = "Codestral"
group = "codestral"
model_id = "codestral-latest"
api_version = "v1"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 8192
cost_per_million_input = 0.30
cost_per_million_output = 0.90
[[providers.presets]]
id = "devstral"
display_name = "Devstral"
group = "codestral"
model_id = "devstral-2512"
api_version = "v1"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 8192
[[providers.presets]]
id = "pixtral_large"
display_name = "Pixtral Large"
group = "pixtral"
model_id = "pixtral-large-2411"
api_version = "v1"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 8192
[[providers.presets]]
id = "pixtral_12b"
display_name = "Pixtral 12B"
group = "pixtral"
model_id = "pixtral-12b-2409"
api_version = "v1"
capabilities = ["text", "images_in", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 8192
[[providers]]
key = "bedrock"
display_name = "AWS Bedrock"
kind = "remote"
auth_mode = "aws_sigv4"
region_env_var = "AWS_REGION"
[[providers.presets]]
id = "anthropic_claude_opus_46"
display_name = "Bedrock Claude Opus 4.6"
group = "anthropic"
model_id = "us.anthropic.claude-opus-4-6-20250916-v1:0"
capabilities = ["text", "tools", "thinking", "images_in", "streaming"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 32000
[[providers.presets]]
id = "anthropic_claude_sonnet_46"
display_name = "Bedrock Claude Sonnet 4.6"
group = "anthropic"
model_id = "us.anthropic.claude-sonnet-4-6-20250514-v1:0"
capabilities = ["text", "tools", "thinking", "images_in", "streaming"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 16384
[[providers.presets]]
id = "anthropic_claude_sonnet_45"
display_name = "Bedrock Claude Sonnet 4.5"
group = "anthropic"
model_id = "us.anthropic.claude-sonnet-4-5-20250929-v1:0"
capabilities = ["text", "tools", "thinking", "images_in", "streaming"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 8192
[[providers.presets]]
id = "anthropic_claude_haiku_45"
display_name = "Bedrock Claude Haiku 4.5"
group = "anthropic"
model_id = "us.anthropic.claude-haiku-4-5-20251001-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 8192
[[providers.presets]]
id = "anthropic_claude_37_sonnet"
display_name = "Bedrock Claude 3.7 Sonnet"
group = "anthropic"
model_id = "us.anthropic.claude-3-7-sonnet-20250219-v1:0"
capabilities = ["text", "tools", "thinking", "images_in", "streaming"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 8192
[[providers.presets]]
id = "anthropic_claude_35_sonnet_v2"
display_name = "Bedrock Claude 3.5 Sonnet v2"
group = "anthropic"
model_id = "us.anthropic.claude-3-5-sonnet-20241022-v2:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 8192
[[providers.presets]]
id = "anthropic_claude_35_haiku"
display_name = "Bedrock Claude 3.5 Haiku"
group = "anthropic"
model_id = "us.anthropic.claude-3-5-haiku-20241022-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 8192
[[providers.presets]]
id = "anthropic_claude_3_opus"
display_name = "Bedrock Claude 3 Opus"
group = "anthropic"
model_id = "us.anthropic.claude-3-opus-20240229-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 4096
[[providers.presets]]
id = "anthropic_claude_3_haiku"
display_name = "Bedrock Claude 3 Haiku"
group = "anthropic"
model_id = "us.anthropic.claude-3-haiku-20240307-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 200000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_4_scout"
display_name = "Bedrock Llama 4 Scout"
group = "meta"
model_id = "us.meta.llama4-scout-17b-instruct-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_4_maverick"
display_name = "Bedrock Llama 4 Maverick"
group = "meta"
model_id = "us.meta.llama4-maverick-17b-instruct-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_33_70b"
display_name = "Bedrock Llama 3.3 70B"
group = "meta"
model_id = "us.meta.llama3-3-70b-instruct-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_32_90b"
display_name = "Bedrock Llama 3.2 90B"
group = "meta"
model_id = "us.meta.llama3-2-90b-instruct-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_32_11b"
display_name = "Bedrock Llama 3.2 11B"
group = "meta"
model_id = "us.meta.llama3-2-11b-instruct-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_32_3b"
display_name = "Bedrock Llama 3.2 3B"
group = "meta"
model_id = "us.meta.llama3-2-3b-instruct-v1:0"
capabilities = ["text", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_32_1b"
display_name = "Bedrock Llama 3.2 1B"
group = "meta"
model_id = "us.meta.llama3-2-1b-instruct-v1:0"
capabilities = ["text", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_31_405b"
display_name = "Bedrock Llama 3.1 405B"
group = "meta"
model_id = "us.meta.llama3-1-405b-instruct-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_31_70b"
display_name = "Bedrock Llama 3.1 70B"
group = "meta"
model_id = "us.meta.llama3-1-70b-instruct-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "meta_llama_31_8b"
display_name = "Bedrock Llama 3.1 8B"
group = "meta"
model_id = "us.meta.llama3-1-8b-instruct-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "amazon_nova_2_pro"
display_name = "Bedrock Nova 2 Pro"
group = "amazon"
model_id = "amazon.nova-2-pro-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 300000
max_output_tokens = 5120
[[providers.presets]]
id = "amazon_nova_2_lite"
display_name = "Bedrock Nova 2 Lite"
group = "amazon"
model_id = "amazon.nova-2-lite-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 300000
max_output_tokens = 5120
[[providers.presets]]
id = "amazon_nova_pro"
display_name = "Bedrock Nova Pro"
group = "amazon"
model_id = "amazon.nova-pro-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 300000
max_output_tokens = 5120
[[providers.presets]]
id = "amazon_nova_lite"
display_name = "Bedrock Nova Lite"
group = "amazon"
model_id = "amazon.nova-lite-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 300000
max_output_tokens = 5120
[[providers.presets]]
id = "amazon_nova_micro"
display_name = "Bedrock Nova Micro"
group = "amazon"
model_id = "amazon.nova-micro-v1:0"
capabilities = ["text", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 5120
[[providers.presets]]
id = "amazon_nova_premier"
display_name = "Bedrock Nova Premier"
group = "amazon"
model_id = "amazon.nova-premier-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 1000000
max_output_tokens = 5120
[[providers.presets]]
id = "mistral_large_3"
display_name = "Bedrock Mistral Large 3"
group = "mistral"
model_id = "mistral.mistral-large-2512-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 8192
[[providers.presets]]
id = "mistral_large_2407"
display_name = "Bedrock Mistral Large 2407"
group = "mistral"
model_id = "mistral.mistral-large-2407-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 8192
[[providers.presets]]
id = "mistral_pixtral_large"
display_name = "Bedrock Pixtral Large"
group = "mistral"
model_id = "mistral.pixtral-large-2502-v1:0"
capabilities = ["text", "tools", "images_in", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 8192
[[providers.presets]]
id = "mistral_small"
display_name = "Bedrock Mistral Small"
group = "mistral"
model_id = "mistral.mistral-small-2402-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 32000
max_output_tokens = 8192
[[providers.presets]]
id = "mistral_mixtral_8x7b"
display_name = "Bedrock Mixtral 8x7B"
group = "mistral"
model_id = "mistral.mixtral-8x7b-instruct-v0:1"
capabilities = ["text", "streaming"]
status = "ga"
context_window_tokens = 32000
max_output_tokens = 4096
[[providers.presets]]
id = "mistral_7b"
display_name = "Bedrock Mistral 7B"
group = "mistral"
model_id = "mistral.mistral-7b-instruct-v0:2"
capabilities = ["text", "streaming"]
status = "ga"
context_window_tokens = 32000
max_output_tokens = 4096
[[providers.presets]]
id = "deepseek_r1"
display_name = "Bedrock DeepSeek R1"
group = "deepseek"
model_id = "us.deepseek.deepseek-r1-v1:0"
capabilities = ["text", "thinking", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 8192
[[providers.presets]]
id = "ai21_jamba_1_5_large"
display_name = "Bedrock Jamba 1.5 Large"
group = "ai21"
model_id = "ai21.jamba-1-5-large-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 4096
[[providers.presets]]
id = "ai21_jamba_1_5_mini"
display_name = "Bedrock Jamba 1.5 Mini"
group = "ai21"
model_id = "ai21.jamba-1-5-mini-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 4096
[[providers.presets]]
id = "ai21_jamba_instruct"
display_name = "Bedrock Jamba Instruct"
group = "ai21"
model_id = "ai21.jamba-instruct-v1:0"
capabilities = ["text", "streaming"]
status = "ga"
context_window_tokens = 256000
max_output_tokens = 4096
[[providers.presets]]
id = "cohere_command_r_plus"
display_name = "Bedrock Command R+"
group = "cohere"
model_id = "cohere.command-r-plus-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "cohere_command_r"
display_name = "Bedrock Command R"
group = "cohere"
model_id = "cohere.command-r-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 4096
[[providers.presets]]
id = "writer_palmyra_x5"
display_name = "Bedrock Palmyra X5"
group = "writer"
model_id = "writer.palmyra-x5-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 8192
[[providers.presets]]
id = "writer_palmyra_x4"
display_name = "Bedrock Palmyra X4"
group = "writer"
model_id = "writer.palmyra-x4-v1:0"
capabilities = ["text", "tools", "streaming"]
status = "ga"
context_window_tokens = 128000
max_output_tokens = 8192