Table of contents
Official Content
  • This documentation is valid for:

This article features a list of supported models via /chat Api. The list is periodically updated according to the new models versions added announced in each Release.

Module Provider Model Full Name Chat Support Function Calling support Environment support
saia.models.openai OpenAI
  • openai/gpt-5.5
  • openai/gpt-5.5-pro(5)
  • openai/gpt-5.4-pro (3)
  • openai/gpt-5.4
  • openai/gpt-5.4-mini
  • openai/gpt-5.4-nano
  • openai/gpt-5.3-chat-latest
  • openai/gpt-5.3-codex
  • openai/gpt-5.2-codex
  • openai/gpt-5.2-2025-12-11
  • openai/gpt-5.2-chat-latest
  • openai/gpt-5.2-pro
  • openai/gpt-5.1-codex-max
  • openai/gpt-5.1-codex-mini
  • openai/gpt-5.1-codex
  • openai/gpt-5.1
  • openai/gpt-5-pro
  • openai/gpt-5-codex
  • openai/gpt-5-chat-latest
  • openai/gpt-5
  • openai/gpt-5-mini
  • openai/gpt-5-nano
  • openai/gpt-4o
  • openai/gpt-4o-mini
  • openai/gpt-4o-2024-11-20
  • openai/gpt-4.1
  • openai/gpt-4.1-mini
  • openai/gpt-4.1-nano
  • openai/o1(1)
  • openai/o1-pro(1)
  • openai/o3(1)
  • openai/o3-pro(1)
  • openai/o3-mini(1)
  • openai/o4-mini(1)
  • openai/o4-mini-deep-research(3)
  • openai/o3-deep-research(3)
 ✅ ✅
  • Beta
  • Production
  • openai/gpt-4o-search-preview(2)
  • openai/gpt-4o-mini-search-preview(2)
 ✅  
saia.models.googlevertexai Google VertexAI
  • vertex_ai/gemini-3.1-pro-preview
  • vertex_ai/gemini-3.1-flash-lite-preview
  • vertex_ai/gemini-3-flash-preview
  • vertex_ai/gemini-2.5-pro
  • vertex_ai/gemini-2.5-flash
  • vertex_ai/gemini-2.5-flash-lite
  • vertex_ai/claude-opus-4-7
  • vertex_ai/claude-opus-4-6
  • vertex_ai/claude-sonnet-4-6
  • vertex_ai/claude-haiku-4-5
  • vertex_ai/mistral-small-2503
  • vertex_ai/mistral-medium-3
  • vertex_ai/zai-org-glm-5-maas
  • vertex_ai/openai-gpt-oss-20b-maas
  • vertex_ai/openai-gpt-oss-120b-maas
  • vertex_ai/deepseek-r1-0528-maas
 ✅ ✅
  • Beta
  • Production
  • vertex_ai/codestral-2
 ✅  
saia.models.anthropic Anthropic
  • anthropic/claude-opus-4-7
  • anthropic/claude-opus-4-6
  • anthropic/claude-sonnet-4-6
  • anthropic/claude-haiku-4-5-20251001
 ✅ ✅
  • Beta
  • Production
saia.models.azure Azure OpenAI
  • azure/gpt-5
  • azure/gpt-5-mini
  • azure/gpt-5-nano
  • azure/gpt-4.1
  • azure/gpt-4.1-mini
  • azure/gpt-4.1-nano
  • azure/gpt-4o
  • azure/gpt-4o-mini
  • azure/o1(1)
  • azure/o3(1)
  • azure/o3-mini(1)
  • azure/o4-mini(1)
 ✅ ✅
  • Beta
  • Production
  • azure/o1-mini(1)
 ✅  
saia.models.azure.foundry Microsoft Foundry
  • azure_ai_foundry/claude-opus-4-7
  • azure_ai_foundry/claude-opus-4-6
  • azure_ai_foundry/claude-sonnet-4-6
  • azure_ai_foundry/gpt-5.5
  • azure_ai_foundry/gpt-5.4
  • azure_ai_foundry/gpt-5.4-mini
  • azure_ai_foundry/gpt-5.4-nano
  • azure_ai_foundry/gpt-5.2
  • azure_ai_foundry/gpt-5.1-codex
  • azure_ai_foundry/gpt-5.1-codex-mini
  • azure_ai_foundry/gpt-4.1
  • azure_ai_foundry/gpt-4.1-mini
  • azure_ai_foundry/model-router
  • azure_ai_foundry/grok-4-1-fast-non-reasoning
  • azure_ai_foundry/grok-4-20-non-reasoning
  • azure_ai_foundry/DeepSeek-V3-0324
 ✅ ✅
  • Beta
  • Production
  • azure_ai_foundry/gpt-oss-120b
  • azure_ai_foundry/Phi-4
  • azure_ai_foundry/Phi-4-mini-instruct
  • azure_ai_foundry/Phi-4-multimodal-instruct
 ✅  
saia.models.awsbedrock AWS Bedrock
  • awsbedrock/us.anthropic.claude-opus-4-7
  • awsbedrock/eu.anthropic.claude-opus-4-7
  • awsbedrock/global.anthropic.claude-opus-4-7
  • awsbedrock/us.anthropic.claude-opus-4-6-v1
  • awsbedrock/us.anthropic.claude-sonnet-4-6
  • awsbedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0
  • awsbedrock/openai.gpt-oss-120b-1:0
  • awsbedrock/openai.gpt-oss-20b-1:0
  • awsbedrock/meta.llama3-8b
  • awsbedrock/meta.llama3-70b
  • awsbedrock/meta.llama3-1-70b
  • awsbedrock/meta.llama3-1-405b
  • awsbedrock/amazon.nova-premier-v1:0
  • awsbedrock/amazon.nova-2-lite-v1:0
  • awsbedrock/amazon.nova-pro-v1:0
  • awsbedrock/amazon.nova-lite-v1:0
  • awsbedrock/amazon.nova-micro-v1:0
  • awsbedrock/meta.llama3-2-1b
  • awsbedrock/meta.llama3-2-3b
  • awsbedrock/meta.llama3-2-11b
  • awsbedrock/meta.llama3-2-90b
 ✅ ✅
  • Beta
  • Production
  • awsbedrock/us.deepseek.r1-v1:0
 ✅  
saia.models.xai xAI
  • xai/grok-4.3
  • xai/grok-4.20-0309-reasoning
  • xai/grok-4.20-0309-non-reasoning
  • xai/grok-4.20-multi-agent-0309 (3)
 ✅ ✅
  • Beta
  • Production
saia.models.cohere Cohere
  • cohere/command-r-08-2024
  • cohere/command-r-plus-08-2024
  • cohere/command-r7b-12-2024
  • cohere/command-a-03-2025
 ✅ ✅
  • Beta
  • Production

saia.models.globantdgx

 Globant DGX
  • globant_dgx/GLM-4.6
 ✅ ✅
  • Beta
  • Globant Clients and Corp

saia.models.fireworks-ai

 Fireworks AI
  • fireworks-ai/glm-5p1
  • fireworks-ai/kimi-k2p6
  • fireworks-ai/kimi-k2p5
 ✅ ✅
  • Beta

saia.models.openrouter

OpenRouter
  • openrouter/moonshotai-kimi-k2.6
  • openrouter/z-ai-glm-5.1
  • openrouter/minimax/minimax-m2.1
  • openrouter/moonshotai-kimi-k2.5
  • openrouter/openai-gpt-5-codex
  • openrouter/moonshotai-kimi-k2-thinking
  • openrouter/openai-gpt-oss-120b
  • openrouter/openai-gpt-oss-20b
  • openrouter/z-ai-glm-4.5
  • openrouter/z-ai-glm-4.5-air
  • openrouter/qwen3-coder
  • openrouter/qwen3-vl-235b-a22b-thinking
  • openrouter/qwen3-vl-235b-a22b-thinking
  • openrouter/qwen3-vl-30b-a3b-instruct
  • openrouter/qwen3-vl-30b-a3b-thinking
  • openrouter/qwen3-vl-8b-instruct
  • openrouter/qwen3-32b
  • openrouter/qwen3-235b-a22b
  • openrouter/deepseek-chat-v3-0324
  • openrouter/deepseek-v3.2
  • openrouter/deepseek-v3.2-exp
  • openrouter/deepseek-v3.2-speciale
  • openrouter/deepseek-v3.1-terminus
  • openrouter/qwen3-vl-235b-a22b-instruct
  • openrouter/qwen3-vl-235b-a22b-thinking
  • openrouter/qwen3-vl-30b-a3b-instruct
  • openrouter/qwen3-vl-30b-a3b-thinking
  • openrouter/qwen3-vl-8b-instruct
  • openrouter/qwen3.5-397b-a17b
  • openrouter/qwen3.5-plus-02-15
  • openrouter/qwen3.5-flash-02-23
  • openrouter/qwen3.5-122b-a10b
  • openrouter/qwen3.5-27b
  • openrouter/qwen3.5-35b-a3b
  • openrouter/auto

✅

✅
  • Beta
  • openrouter/qwen3-8b:free
  • openrouter/qwen3-14b:free
  • openrouter/qwen3-30b-a3b:free
  • openrouter/qwen3-32b:free
  • openrouter/qwen3-235b-a22b:free 
 ✅  
saia.models.mistral Mistral AI
  • mistral/magistral-medium-latest
  • mistral/mistral-medium-latest
  • mistral/codestral-latest
  • mistral/mistral-saba-latest
  • mistral/mistral-large-latest
  • mistral/pixtral-large-latest
  • mistral/ministral-3b-latest
  • mistral/ministral-8b-latest
  • mistral/devstral-small-latest
  • mistral/mistral-small-latest
  • mistral/pixtral-12b-2409
  • mistral/open-mistral-nemo
 ✅ ✅
  • Beta
  • mistral/magistral-small-latest
 ✅  
saia.models.deepseek DeepSeek
  • deepseek/deepseek-chat
  • deepseek/deepseek-reasoner
 ✅ ✅
  • Beta
saia.models.groq Groq
  • groq/openai-gpt-oss-120b
  • groq/openai-gpt-oss-20b
  • groq/llama-3.3-70b-versatile
  • groq/llama-3.1-8b-instant
  • groq/meta-llama-4-scout-17b-16e-instruct
  • groq/meta-llama-4-maverick-17b-128e-instruct
  • groq/qwen3-32b
  • groq/mistral-saba-24b
 ✅ ✅
  • Beta
saia.models.nvidia NVidia
  • nvidia/nvidia.nemotron-mini-4b-instruct
  • nvidia/meta.llama-3.1-8b-instruct
  • nvidia/meta.llama-3.1-70b-instruct
  • nvidia/meta.llama-3.1-405b-instruct
  • nvidia/meta.llama-3.2-3b-instruct
  • nvidia/meta-llama-4-scout-17b-16e-instruct
  • nvidia/llama-3.3-nemotron-super-49b-v1
  • nvidia/llama-3.1-nemotron-70b-instruct
 ✅ ✅
  • Beta
  • nvidia/meta.llama-3.2-1b-instruct
  • nvidia/llama-3.1-nemotron-ultra-253b-v1
  • nvidia/meta-llama-4-maverick-17b-128e-instruct
  • nvidia/deepseek-ai-deepseek-r1
 ✅  
saia.models.inception Inception Labs
  • inception/mercury(4)
  • inception/mercury-coder(4)
  • inception/mercury-2(4)
 ✅ ✅
  • Beta
(1) - To use these models the temperature must be set to 1, check Reasoning models.
(2)- These models do not support the Temperature parameter in the request body.
(3) - This model is only available via Responses API.
(4) - difussion LLM (dLLM).  
(5) - This model is only available via Chat API and Responses API.

See Also

—
Last update: Today by usr238810
Last update: 2026 | © Globant S.A. All rights reserved.