WWhichAITry via Vercel AI Gateway
Updated Feb 2026 · 20 models tracked

Pick the right AI model
in 60 seconds.

Independent, opinionated rankings of every major LLM. Compare price, context, and real-world fit for coding, writing, agents, and research — without wading through a dozen vendor sites.

Head-to-head

Most-compared this month

See all 190
Our picks

Top models for coding

Full ranking →
Cheapest that still ship

Top models for bulk workloads

Full ranking →
Hard problems only

Top models for reasoning

Full ranking →
Everything

All tracked models

Anthropic

Claude Opus 4.7

Anthropic's flagship. Deep reasoning, long-horizon agents.

context
1M
in/M
$15.00
out/M
$75.00
Anthropic

Claude Sonnet 4.6

Sonnet strikes back. The price-performance sweet spot.

context
1M
in/M
$3.00
out/M
$15.00
Anthropic

Claude Haiku 4.5

Fast, cheap, surprisingly smart.

context
200K
in/M
$1.00
out/M
$5.00
OpenAI

GPT-5

OpenAI's flagship. Omni-modal, omni-purpose.

context
400K
in/M
$10.00
out/M
$40.00
OpenAI

GPT-5 Mini

GPT-5 shrunk for scale.

context
200K
in/M
$0.40
out/M
$1.60
OpenAI

GPT-4.1

Long-context workhorse still on the menu.

context
1M
in/M
$2.00
out/M
$8.00
OpenAI

o4

Reasoning model. Thinks before it speaks.

context
200K
in/M
$15.00
out/M
$60.00
Google

Gemini 3 Pro

Google's flagship. Massive context, native multimodality.

context
2M
in/M
$3.50
out/M
$14.00
Google

Gemini 3 Flash

Cheap, fast, 2M-token context.

context
2M
in/M
$0.30
out/M
$1.20
xAI

Grok 4

Real-time-aware, unfiltered, strong reasoner.

context
256K
in/M
$5.00
out/M
$15.00
Meta

Llama 4 405B

open

Open-weights heavyweight. Self-host or run anywhere.

context
256K
in/M
$2.70
out/M
$2.70
Meta

Llama 4 70B

open

Mid-size open model. Excellent price-performance when self-hosted.

context
128K
in/M
$0.60
out/M
$0.60
DeepSeek

DeepSeek V3

open

Open-weights reasoning at bargain pricing.

context
128K
in/M
$0.27
out/M
$1.10
Mistral

Mistral Large 3

European flagship with strong multilingual chops.

context
256K
in/M
$2.00
out/M
$6.00
Mistral

Mistral Small 3

open

Small, open-weights, surprisingly sharp.

context
128K
in/M
$0.20
out/M
$0.60
Alibaba

Qwen 3 Max

Alibaba's flagship. Top-tier multilingual and coding.

context
256K
in/M
$1.20
out/M
$4.00
Alibaba

Qwen 3 Coder

open

Open-weights coding specialist.

context
128K
in/M
$0.50
out/M
$1.50
Cohere

Command R+

open

RAG-tuned enterprise workhorse.

context
128K
in/M
$2.50
out/M
$10.00
OpenAI

GPT-OSS 20B

open

OpenAI's open-weights return.

context
128K
in/M
$0.15
out/M
$0.60
Google

Gemini Nano 2

On-device first. Free inference, private by default.

context
32K
in/M
Free
out/M
Free
By use case

Pick a guide