Choose from the models that matter.

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

262,144

Providers

19

Input / 1M

$0.2

Output / 1M

$0.6

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Context

262,144

Providers

15

Input / 1M

$0.112

Output / 1M

$0.48

Qwen vision-language model for visual reasoning, documents, and agent tasks

Context

1,000,000

Providers

14

Input / 1M

$0

Output / 1M

$0

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Context

262,144

Providers

9

Input / 1M

$1.04

Output / 1M

$6.24

Earlier Qwen multimodal workhorse for million-token agent and document tasks

Context

1,000,000

Providers

20

Input / 1M

$0

Output / 1M

$0

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

Context

1,000,000

Providers

22

Input / 1M

$0

Output / 1M

$0

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

Context

1,000,000

Providers

17

Input / 1M

$0

Output / 1M

$0

Qwen reasoning model for deliberate problem solving, math, and coding

Context

131,072

Providers

2

Input / 1M

$0.23

Output / 1M

$0.574

Flagship Indian-language reasoning model for enterprise multilingual applications

Context

131,072

Providers

3

Input / 1M

$0.04

Output / 1M

$0.16

Efficient Indian-language reasoning model for chat, coding, and multilingual work

Context

128,000

Providers

3

Input / 1M

$0.02

Output / 1M

$0.1

Fast web-grounded Sonar for current answers, citations, and lightweight retrieval

Context

130,000

Providers

9

Input / 1M

$0.25

Output / 1M

$1

Deeper Sonar search model with broader retrieval and stronger synthesis

Context

200,000

Providers

9

Input / 1M

$2.992

Output / 1M

$14.994