Documentation Index

Fetch the complete documentation index at: https://kb.expedient.com/llms.txt

Use this file to discover all available pages before exploring further.

AI CTRL Ratecard

  • Updated on Jun 30, 2026
  • Published on May 19, 2026
Prev Next

★ Standard Model

Universal Credits powered by GPT-5 mini
100
Credits
=
117.65 M
Tokens
Based on standard usage patterns with a 9:1 input-to-output ratio. Credits work across all models — token allocations vary by model capability.
OpenAIAnthropicGooglePerplexity⬆ More tokens than GPT-5 mini
O

OpenAI

GPT-5.5, GPT-5, GPT-4.1, GPT-4o, o-series, GPT Image, and DALL-E
ModelInput Tokens / 100 CROutput Tokens / 100 CR
GPT-5 miniStandard
General chat, analysis, and light coding		200M25M
DALL-E 3
Creative illustrations, concepts, and marketing-style imagery		10M1.56M
GPT Image 1.5
Strong image quality, variations, and multimodal workflows at scale		10M1.56M
GPT Image 2
Latest image generation with rich detail, edits, and complex scenes		10M1.67M
GPT-4.1
Strong coding and long-context instruction following		25M6.25M
GPT-4o
Vision and general multimodal assistants		20M5M
GPT-4o mini
Budget multimodal chat, vision, and simple extraction		333.33M83.33M
GPT-5
Reasoning, coding, and general-purpose assistants		40M5M
GPT-5 nano
Summaries, tagging, and high-volume triage		1B125M
GPT-5 Pro
Deep analysis and planning with extended thinking		3.33M416.67K
GPT-5.1
Everyday coding and agent-style tasks		40M5M
GPT-5.1 Codex
Economical coding, implementation, and code review		40M5M
GPT-5.2
Coding, tool use, and multimodal workflows		28.57M3.57M
GPT-5.2 Codex
IDE-style edits, debugging, and repo-aware changes		28.57M3.57M
GPT-5.2 Pro
Very demanding reasoning, long-form analysis, complex decisions		2.38M297.62K
GPT-5.3 Codex
Agentic coding, refactors, and multi-file software work		28.57M3.57M
GPT-5.4
Coding, agents, math, and broad analysis		20M3.33M
GPT-5.4 Mini
Quick iterations, lighter coding, and tool-heavy workflows		66.67M11.11M
GPT-5.4 Nano
Snippets, small fixes, classification, and routing		250M40M
GPT-5.4 Pro
Hardest problems, maximum precision, long-running work		1.67M277.78K
GPT-5.5
Flagship for coding, agents, computer-use, and professional work		10M1.67M
o3
STEM, logic, and careful step-by-step analysis		25M6.25M
o3 Deep Research
Long reports, due diligence, and literature-style synthesis		5M1.25M
o4-mini
Cost-efficient math, logic, and structured reasoning		45.45M11.36M
o4-mini Deep Research
Faster, more affordable deep research model		25M6.25M
A

Anthropic

Claude Opus 4.8 through Haiku model families
ModelInput Tokens / 100 CROutput Tokens / 100 CR
Claude Haiku 3
Maximum economy and minimum latency at high scale		200M40M
Claude Haiku 4.5
High-volume assistants and chat with strong answer quality		50M10M
Claude Opus 4
Broad flagship-quality coding, analysis, and writing		3.33M666.67K
Claude Opus 4.1
Premium coding, instruction following, and high-stakes work		3.33M666.67K
Claude Opus 4.5
Elite reasoning, research depth, and strategic analysis		10M2M
Claude Opus 4.6
Hardest agents, complex coding, and very long documents		10M2M
Claude Opus 4.7
Stronger coding, vision, and complex multi-step tasks with improved consistency		10M2M
Claude Opus 4.8
Most capable Opus for complex reasoning, long-horizon agentic coding, and high-autonomy work		10M2M
Claude Sonnet 4
Implementation, documentation, and general software tasks		16.67M3.33M
Claude Sonnet 4.5
Product engineering, coding, and long-context sessions (up to 1M with opt-in context)		16.67M3.33M
Claude Sonnet 4.6
Coding, agent planning, and drafting with strong long-context reasoning		16.67M3.33M
G

Google Gemini

Gemini Pro, Flash, and Flash-Lite models
ModelInput Tokens / 100 CROutput Tokens / 100 CR
Gemini 2.0 Flash
Balanced multimodal assistant		500M125M
Gemini 2.0 Flash-Lite
Simple input–output and minimum spend per request		666.67M166.67M
Gemini 2.5 Flash
Chat, summarization, and extraction at large scale		166.67M20M
Gemini 2.5 Flash-Lite
Routing, translation, and extremely high request volume		500M125M
Gemini 2.5 Pro
Complex code, deep analysis, and very long context		40M5M
Gemini 3 Flash
Fast multimodal work, thinking-style tasks, large context		100M16.67M
Gemini 3 Pro
Complex analysis, coding, and multimodal assistants (preview)		25M4.17M
Gemini 3.1 Flash-Lite
High-throughput tasks where cost and speed both matter		200M33.33M
Gemini 3.1 Pro
Agents, coding, and multimodal reasoning (preview)		25M4.17M
P

Perplexity

Sonar search-grounded models
ModelInput Tokens / 100 CROutput Tokens / 100 CR
Sonar
Web-grounded answers		50M50M
Sonar Deep Research
Long reports, due diligence, and literature-style synthesis		25M6.25M
Sonar Pro
Multi-step research questions, broad sources, nuanced synthesis		16.67M3.33M
Sonar Reasoning
Structured analysis grounded in live search results		50M10M
Sonar Reasoning Pro
Deep multi-step reasoning over retrieved web evidence		25M6.25M

Understanding This Rate Card

  • Higher-capability models consume more credits per token
  • Efficient models stretch your credits further
  • All values based on 100 Credits
  • GPT-5 mini is the baseline standard model
  • Green values indicate more tokens than GPT-5 mini
  • Rates are subject to change by providers
  • Actual usage varies based on conversation patterns
© 2026 Expedient. All rights reserved.  |  AI CTRL Platform Documentation
Page last updated: 6/30/2026, 6:00:26 AM ET