117 models
Ranked by Design Arena: website
Tools JSON 1051.0

Long-lived GPT workhorse for coding, instruction following, and production apps

openai/gpt-4.1 2025-04-14 1.04758M context $2/M input $8/M output
28 providers
Reasoning 1048.0

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

openai/o3 2025-04-16 200K context $2/M input $8/M output
20 providers
1048.0

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

openai/o3:batch 200K context $1/M input $4/M output
1040.0

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

mistralai/ministral-3b-2512 131.072K context $0.1/M input $0.1/M output
1010.0

Affordable GPT-4.1 lane for fast coding help and structured extraction

openai/gpt-4.1-mini 2025-04-14 1.04758M context $0.4/M input $1.6/M output
25 providers
1010.0

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

openai/gpt-4.1-mini:batch 1.04758M context $0.2/M input $0.8/M output
Reasoning Tools JSON 998.0

Fast o-series model for compact reasoning, coding, and tool use

openai/o4-mini 2025-04-16 200K context $1.1/M input $4.4/M output
20 providers
998.0

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

openai/o4-mini:batch 200K context $0.55/M input $2.2/M output
985.0

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

openai/gpt-4.1-nano 2025-04-14 1.04758M context $0.1/M input $0.4/M output
20 providers
985.0

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

openai/gpt-4.1-nano:batch 1.04758M context $0.05/M input $0.2/M output
908.0

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

mistralai/mistral-small-3.2-24b-instruct 128K context $0.075/M input $0.2/M output
883.0

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

meta-llama/llama-4-maverick 128K context $0.2/M input $0.696/M output
847.0

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

amazon/nova-premier-v1 1M context $2.5/M input $12.5/M output
Tools 843.0

Omni-era GPT for multimodal chat, practical coding, and general assistants

openai/gpt-4o 2024-05-13 128K context $2.5/M input $10/M output
23 providers
843.0

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

openai/gpt-4o:batch 128K context $1.25/M input $5/M output
808.0

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...

amazon/nova-pro-v1 300K context $0.8/M input $3.2/M output
762.0

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

meta-llama/llama-4-scout 327.68K context $0.1/M input $0.3/M output