GPT 5.5 (Beta)
GPT 5.5 (Beta)
- Context window
- 1.1M tokens
- Max output
- 128K tokens
- Released
- Apr 2026
- Knowledge cutoff
- Dec 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Anthropic Claude Opus 4.7 on Amazon (Beta)
Anthropic Claude Opus 4.7 on Amazon (Beta)
- Context window
- 1M tokens
- Max output
- 128K tokens
- Released
- Apr 2026
- Knowledge cutoff
- Jan 2026
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
GPT 5.4 Mini (Beta)
GPT 5.4 Mini (Beta)
- Context window
- 400K tokens
- Max output
- 128K tokens
- Released
- Mar 2026
- Knowledge cutoff
- Aug 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Imageinput, but the Salesforce text endpoint used here doesn't support it.
NVIDIA Nemotron 3 Super 120B (Beta)
NVIDIA Nemotron 3 Super 120B (Beta)
- Context window
- 262K tokens
- Max output
- 262K tokens
- Released
- Mar 2026
- Knowledge cutoff
- Apr 2024
Provider list price(reference, not Salesforce cost)
Input / output
GPT 5.4
GPT 5.4
- Context window
- 1.1M tokens
- Max output
- 128K tokens
- Released
- Mar 2026
- Knowledge cutoff
- Aug 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Google Gemini 3.1 Flash Lite (Beta)
Google Gemini 3.1 Flash Lite (Beta)
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Released
- Mar 2026
- Knowledge cutoff
- Jan 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, Video, Audio, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Google Gemini 3.1 Pro (Beta)
Google Gemini 3.1 Pro (Beta)
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Released
- Feb 2026
- Knowledge cutoff
- Jan 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, Video, Audio, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Anthropic Claude Sonnet 4.6 on Amazon
Anthropic Claude Sonnet 4.6 on Amazon
- Context window
- 1M tokens
- Max output
- 64K tokens
- Released
- Feb 2026
- Knowledge cutoff
- Aug 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Anthropic Claude Opus 4.6 on Amazon
Anthropic Claude Opus 4.6 on Amazon
- Context window
- 1M tokens
- Max output
- 128K tokens
- Released
- Feb 2026
- Knowledge cutoff
- May 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Google Gemini 3 Flash
Google Gemini 3 Flash
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Released
- Dec 2025
- Knowledge cutoff
- Jan 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, Video, Audio, PDFinput, but the Salesforce text endpoint used here doesn't support it.
GPT 5.2
GPT 5.2
- Context window
- 400K tokens
- Max output
- 128K tokens
- Released
- Dec 2025
- Knowledge cutoff
- Aug 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Imageinput, but the Salesforce text endpoint used here doesn't support it.
Anthropic Claude Opus 4.5 on Amazon
Anthropic Claude Opus 4.5 on Amazon
- Context window
- 200K tokens
- Max output
- 64K tokens
- Released
- Nov 2025
- Knowledge cutoff
- Mar 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
GPT 5.1
GPT 5.1
- Context window
- 400K tokens
- Max output
- 128K tokens
- Released
- Nov 2025
- Knowledge cutoff
- Sep 2024
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Imageinput, but the Salesforce text endpoint used here doesn't support it.
Anthropic Claude Haiku 4.5 on Amazon
Anthropic Claude Haiku 4.5 on Amazon
- Context window
- 200K tokens
- Max output
- 64K tokens
- Released
- Oct 2025
- Knowledge cutoff
- Feb 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Anthropic Claude Sonnet 4.5 on Amazon
Anthropic Claude Sonnet 4.5 on Amazon
- Context window
- 200K tokens
- Max output
- 64K tokens
- Released
- Sep 2025
- Knowledge cutoff
- Jul 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
GPT 5 Mini
GPT 5 Mini
- Context window
- 400K tokens
- Max output
- 128K tokens
- Released
- Aug 2025
- Knowledge cutoff
- May 2024
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Imageinput, but the Salesforce text endpoint used here doesn't support it.
GPT 5
GPT 5
- Context window
- 400K tokens
- Max output
- 128K tokens
- Released
- Aug 2025
- Knowledge cutoff
- Sep 2024
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Imageinput, but the Salesforce text endpoint used here doesn't support it.
Google Gemini 2.5 Flash Lite
Google Gemini 2.5 Flash Lite
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Released
- Jun 2025
- Knowledge cutoff
- Jan 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, Audio, Video, PDFinput, but the Salesforce text endpoint used here doesn't support it.
OpenAI O4 Mini
OpenAI O4 Mini
- Context window
- 200K tokens
- Max output
- 100K tokens
- Released
- Apr 2025
- Knowledge cutoff
- May 2024
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Imageinput, but the Salesforce text endpoint used here doesn't support it.
OpenAI O3
OpenAI O3
- Context window
- 200K tokens
- Max output
- 100K tokens
- Released
- Apr 2025
- Knowledge cutoff
- May 2024
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
GPT 4.1 Mini
GPT 4.1 Mini
- Context window
- 1.0M tokens
- Max output
- 33K tokens
- Released
- Apr 2025
- Knowledge cutoff
- Apr 2024
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
GPT 4.1
GPT 4.1
- Context window
- 1.0M tokens
- Max output
- 33K tokens
- Released
- Apr 2025
- Knowledge cutoff
- Apr 2024
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Google Gemini 2.5 Flash
Google Gemini 2.5 Flash
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Released
- Mar 2025
- Knowledge cutoff
- Jan 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, Audio, Video, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Google Gemini 2.5 Pro
Google Gemini 2.5 Pro
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Released
- Mar 2025
- Knowledge cutoff
- Jan 2025
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, Audio, Video, PDFinput, but the Salesforce text endpoint used here doesn't support it.
Amazon Nova Lite
Amazon Nova Lite
- Context window
- 300K tokens
- Max output
- 8K tokens
- Released
- Dec 2024
- Knowledge cutoff
- Oct 2024
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, Videoinput, but the Salesforce text endpoint used here doesn't support it.
Amazon Nova Pro
Amazon Nova Pro
- Context window
- 300K tokens
- Max output
- 8K tokens
- Released
- Dec 2024
- Knowledge cutoff
- Oct 2024
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, Videoinput, but the Salesforce text endpoint used here doesn't support it.
NVIDIA Nemotron 3 Nano 30B (Beta)
NVIDIA Nemotron 3 Nano 30B (Beta)
- Context window
- 131K tokens
- Max output
- 131K tokens
- Released
- Dec 2024
- Knowledge cutoff
- Sep 2024
Provider list price(reference, not Salesforce cost)
Input / output
GPT 4 Omni Mini
GPT 4 Omni Mini
- Context window
- 128K tokens
- Max output
- 16K tokens
- Released
- Jul 2024
- Knowledge cutoff
- Sep 2023
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
GPT 4 Omni
GPT 4 Omni
- Context window
- 128K tokens
- Max output
- 16K tokens
- Released
- May 2024
- Knowledge cutoff
- Sep 2023
Provider list price(reference, not Salesforce cost)
Input / output
Underlying model also accepts Image, PDFinput, but the Salesforce text endpoint used here doesn't support it.
