Agent Models
Models suited for AI agents with function calling, automation, and tool-use capabilities.
Models suited for AI agents with function calling, automation, and tool-use capabilities.
Models
43
in category
Providers
9
represented
Avg. API Cost
$16.33
combined in+out / 1M
Top Model
Gemini 3.6 Flash
Coding
Agent Models Rankings
Sorted by coding
| # | Model | Provider | Context | Input / 1M |
|---|---|---|---|---|
| 1 | Claude 4 Opus | Anthropic | 200K | $15.00 |
| 2 | Claude Opus 4.1 | Anthropic | 200K | $15.00 |
| 3 | Claude 4 Sonnet | Anthropic | 200K | $3.00 |
| 4 | Claude Sonnet 4.5 | Anthropic | 200K | $3.00 |
| 5 | GPT-5 | OpenAI | 400K | $5.00 |
| 6 | OpenAI o3 | OpenAI | 200K | $10.00 |
| 7 | Claude 3.7 Sonnet | Anthropic | 200K | $3.00 |
| 8 | GPT-4.1 | OpenAI | 1M | $2.00 |
| 9 | DeepSeek R1 | DeepSeek | 64K | $0.55 |
| 10 | Codestral | Mistral | 256K | $0.30 |
Related Models
Gemini 3.6 Flash
Google's speed-optimized Gemini 3.6 Flash with frontier-level intelligence at lower cost than prior Flash tiers.
Why: Google · Coding leader
Kimi K3
Moonshot flagship open-frontier model with ~2.8T parameters, native vision, and a 1M-token context window.
Why: Moonshot AI · Coding leader
Claude Sonnet 4.5
Anthropic's balanced Sonnet 4.5 for production coding and agent workflows.
Why: Anthropic · Coding leader
GPT-5
OpenAI flagship GPT-5 generation for general and agentic workloads.
Why: OpenAI · Coding leader
GPT-5 Mini
Cost-efficient GPT-5 family model for high-volume production.
Why: OpenAI · Coding leader
DeepSeek V4
Next-gen DeepSeek general model emphasizing coding and cost efficiency.
Why: DeepSeek · Coding leader
Claude Opus 4.1
Anthropic's latest Opus-class model for deep reasoning, coding, and long-form analysis.
Why: Anthropic · Coding leader
Gemini 3 Pro
Google Gemini 3 Pro frontier tier for complex multimodal reasoning and long-context workloads.
Why: Google · Coding leader
Related Providers
OpenAI
Why: 11 models in catalog
Confidence99%Anthropic
Why: 9 models in catalog
Confidence90%Google
Why: 7 models in catalog
Confidence80%Meta
Why: 4 models in catalog
Confidence70%xAI
Why: 4 models in catalog
Confidence60%Mistral
Why: 5 models in catalog
Confidence50%Cohere
Why: 3 models in catalog
Confidence40%DeepSeek
Why: 5 models in catalog
Confidence30%Moonshot AI
Why: 2 models in catalog
Confidence20%
Relevant Comparisons
Gemini 3.6 Flash vs Kimi K3
Why: Top models in this category
Gemini 3.6 Flash vs Claude Sonnet 4.5
Why: Top models in this category
Gemini 3.6 Flash vs GPT-5
Why: Top models in this category
Kimi K3 vs Claude Sonnet 4.5
Why: Top models in this category
Kimi K3 vs GPT-5
Why: Top models in this category
Claude Sonnet 4.5 vs GPT-5
Why: Top models in this category
Calculators
Timeline Events
Gemini 3.6 Flash — Model Release
Why: Model Release
Gemini 3.6 Flash — API Release
Why: API Release
Gemini 3.6 Flash — Pricing Update
Why: Pricing Update
Gemini 3.6 Flash — Context Window Increase
Why: Context Window Increase
Gemini 3.6 Flash — Vision Support
Why: Vision Support
Gemini 3.6 Flash — Audio Support
Why: Audio Support
Frequently Asked Questions
- What is the agent models?
- Based on SGO's dataset, GPT-4o by OpenAI ranks highly for coding with a coding score of 90. Rankings are computed from structured benchmark and pricing data.
- How are agent models ranked?
- Rankings are derived from the centralized SGO model dataset — benchmark scores, API pricing, context windows, and capability flags. No recommendations are hardcoded.
- How many models match this category?
- 43 models in the SGO catalog currently match this category.
Explore More
43 models · Data derived from the SGO intelligence catalog