Choose from the models that matter.

Mistral coding agent model for repository tasks and software engineering workflows

Context

128,000

Providers

2

Input / 1M

$0.4

Output / 1M

$2

Mistral coding agent model for repository tasks and software engineering workflows

Context

128,000

Providers

2

Input / 1M

$0.1

Output / 1M

$0.3

Multi-agent model for routing expert agents across complex analytical tasks

Context

1,000,000

Providers

1

Input / 1M

Unknown

Output / 1M

Unknown

Quality-first multi-agent model for hard research, analysis, and competitions

Context

1,000,000

Providers

6

Input / 1M

$5

Output / 1M

$30

Earlier Gemini Flash workhorse for responsive multimodal apps and tool use

Context

1,048,576

Providers

3

Input / 1M

$0.1

Output / 1M

$0.4

Low-latency Gemini model for high-volume multimodal and agent workloads

Context

2,000,000

Providers

4

Input / 1M

$0.052

Output / 1M

$0.21

Fast Gemini workhorse for multimodal apps where latency and price matter

Context

1,065,535

Providers

28

Input / 1M

$0.09

Output / 1M

$0.71

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Context

1,048,756

Providers

18

Input / 1M

$0.07

Output / 1M

$0.28

Speech generation model for controllable voice, narration, and audio delivery

Context

32,768

Providers

1

Input / 1M

$0.5

Output / 1M

$10

Google's proven reasoning model for coding, math, and multimodal analysis

Context

1,065,535

Providers

29

Input / 1M

$0.87

Output / 1M

$7

Speech generation model for controllable voice, narration, and audio delivery

Context

32,768

Providers

1

Input / 1M

$1

Output / 1M

$20

Low-latency Gemini model for high-volume multimodal and agent workloads

Context

1,048,576

Providers

15

Input / 1M

$0.25

Output / 1M

$1.5