Choose the right model for every agent.
Compare execution, research, image, and video models by capability, context, provider, and USD cost before routing work through agents, SDKs, project tasks, or Imagine workflows.
Start now
Compare frontier and efficient models for coding, operations, browser work, and product tasks.
Choose deeper research paths when agents need stronger coverage, synthesis, and source review.
Create and edit visuals from the same workspace agents use for files, plans, and deliverables.
Generate and edit short videos with USD-credit pricing based on model, duration, and resolution.
Review USD costs, defaults, context windows, and BYOM options before routing work.
USD credits are ACP’s billing unit for model usage, video seconds, and runtime. Model prices include the managed LLM margin, and the cost columns below show weighted average consumption and relative cost using the same baseline across the docs and platform.
Relative cost multipliers are calculated against a stable billing baseline. This is a pricing reference, not the default execution model.
Managed system agents now use Spark for fast execution, Forge for implementation-heavy work, and Foundry for high-rigor synthesis and reasoning.
DeepSeek V4 Flash
MiniMax M3
Claude Opus 4.8USD cost uses this representative token mix so model costs stay comparable at a glance.
Model comparison
| Model | Intelligence | Speed | Context | USD Cost | Cost Baseline |
|---|---|---|---|---|---|
 Claude Opus 4.8 Anthropic’s latest flagship for complex reasoning, long-horizon coding, and high-autonomy agent work. | Medium | 1M | $9.41 / 1M | 5.0x | |
Claude Opus 4.7 Anthropic’s latest flagship for the most complex reasoning and agentic coding work. | Medium | 1M | $9.41 / 1M | 5.0x | |
Claude Opus 4.6 Previous-generation flagship Claude model for complex reasoning and coding. | Medium | 1M | $9.41 / 1M | 5.0x | |
Claude Sonnet 4.5 Best balance of intelligence and speed. Excellent for coding and daily tasks. | Fast | 200k | $5.64 / 1M | 3.0x | |
Claude Haiku 4.5 Fast and cost-effective for quick tasks and high-volume operations. | Very Fast | 200k | $1.88 / 1M | 1x (baseline) | |
 GPT-5.5 Pro OpenAI highest-accuracy model for the hardest professional and agentic work. | Medium | 1M | $66.00 / 1M | 35.1x | |
GPT-5.5 OpenAI frontier model for coding, professional work, and long-context agents. | Fast | 1M | $10.51 / 1M | 5.6x | |
GPT-5.4 OpenAI flagship model for advanced coding, planning, and computer use. | Fast | 1M | $5.25 / 1M | 2.8x | |
GPT-5.4 mini OpenAI mini model tuned for fast coding, subagents, and computer-use tasks. | Fast | 400k | $1.58 / 1M | 0.84x | |
GPT-5.4 nano Lightweight OpenAI model for simple instructions, routing, and high-volume tasks. | Very Fast | 400k | $0.43 / 1M | 0.23x | |
 Gemini 3.1 Pro Higher-reasoning Gemini model for complex planning and analysis. | Fast | 1M | $5.64 / 1M | 3.0x | |
Gemini 3 Flash Fast default model for everyday agent execution. | Very Fast | 1M | $1.88 / 1M | 1x (baseline) | |
Gemini 3.1 Flash Fast Gemini tier that currently routes through the same runtime as Gemini 3 Flash. | Very Fast | 1M | $1.88 / 1M | 1x (baseline) | |
 DeepSeek V4 ProDefault DeepSeek flagship model running through Clawcode for agentic coding and long-context reasoning. | Fast | 1M | $0.53 / 1M | 0.28x | |
DeepSeek V4 Flash Fast DeepSeek V4 model running through Clawcode for efficient agent execution. | Very Fast | 1M | $0.17 / 1M | 0.09x | |
MiniMax M3 MiniMax long-context model served via Cloudflare Workers AI for efficient agentic coding, tool use, and digital work. | Fast | 1M | $1.00 / 1M | 0.53x | |
 Kimi K2.6 Moonshot flagship served via Cloudflare Workers AI for long-horizon coding and agentic execution. | Fast | 262k | $1.63 / 1M | 0.87x |
Research models
| Model | Intelligence | Speed | Context | Pricing | Best for |
|---|---|---|---|---|---|
Gemini 3.1 FlashDefault Faster deep research path tuned for speed and lower cost. | Very Fast | 1M | $1.88 / 1M | Quick researchSummaries | |
Gemini 3.1 Pro Higher-depth deep research path tuned for stronger coverage. | Fast | 1M | $5.64 / 1M | Deep researchComplex reasoning |
Image generation models
| Model | Quality | Speed | Mode | Pricing | Best for |
|---|---|---|---|---|---|
GPT Image 2Default Highest-fidelity OpenAI image model with quality-based USD-credit billing. | Highest | Medium | Generation and editing | $0.01-$0.12/img | Final assetsText rendering |
Gemini 3.1 Flash Image Preview Fast multimodal image generation and editing preview with a flat USD-credit estimate. | High | Very Fast | Generation and editing | $0.07/img | Fast iterationLower-cost drafts |
Video generation models
| Model | Provider | Max Duration | Resolutions | Input Modalities | Pricing |
|---|---|---|---|---|---|
 Grok Imagine Video Creative video generation for motion concepts, clips, and stylized visuals. | xAI | 15s | 480p, 720p | Text, Image, Video | $0.055 / s |
 Seedance 2.0 FastDefault Fast reference-aware video generation for quick iteration. | ByteDance | 12s | 480p, 720p | Text, Image, Video | $0.088 / s |
Seedance 2.0 Higher-quality video generation with 1080p output support. | ByteDance | 12s | 480p, 720p, 1080p | Text, Image, Video | |
| Default / 720p | ByteDance | 12s | 480p, 720p | Text, Image, Video | $0.242 / s |
| 1080p | ByteDance | 12s | 1080p | Text, Image, Video | $0.605 / s |
Bring your own models
Team and Enterprise workspaces can connect external model providers and route agent execution through their own model inventory. That includes OpenAI-compatible endpoints, custom inference backends, and workspace-level model catalogs exposed through ACP’s external model connection flow.