Model catalog

All models available through RouterLab.

Explore available models, compare API formats, context windows and pricing. Use model identifiers directly in your integrations.

available models

Active public catalog

catalog categories

Categories derived from the catalog

API formats

Routes published in the catalog

embedding models

Also visible in this catalog

Quick access

Common starting points

Dedicated embeddings view

45 of 45 models

Sort by

DeepSeek V4 FlashHigh availability

deepseek-v4-flash

DeepSeekOpen sourceOpenAI-compatibleClaude MessagesToolsReasoningStreaming

Model origin

DeepSeek

Context

Format

OpenAI-compatible

Max output

384K

Input / 1M

$0.09

Output / 1M

$0.18

Cache read / 1M

$0.018

Cache write / 1M

$0.09

View model

DeepSeek V4 Flash 0731High availability

deepseek-v4-flash-0731

DeepSeekOpen sourceOpenAI-compatibleClaude MessagesToolsReasoningStreaming

Model origin

DeepSeek

Context

Format

OpenAI-compatible

Max output

384K

Input / 1M

$0.09

Output / 1M

$0.18

Cache read / 1M

$0.018

Cache write / 1M

$0.09

View model

DeepSeek V4 ProHigh availability

deepseek-v4-pro

DeepSeekOpen sourceOpenAI-compatibleClaude MessagesToolsReasoningStreaming

Model origin

DeepSeek

Context

Format

OpenAI-compatible

Max output

384K

Input / 1M

$1.25

Output / 1M

$2.55

Cache read / 1M

$0.10

Cache write / 1M

$0.10

View model

DeepSeek V4 Pro 0813High availability

deepseek-v4-pro-0813

DeepSeekOpen sourceOpenAI-compatibleToolsReasoningStreaming

Model origin

DeepSeek

Context

Format

OpenAI-compatible

Max output

384K

Input / 1M

$1.25

Output / 1M

$2.55

Cache read / 1M

$0.10

Cache write / 1M

$0.10

View model

DeepSeek V4.1 FlashHigh availability

deepseek-v4.1-flash

DeepSeekOpen sourceOpenAI-compatibleVisionToolsReasoning

Model origin

DeepSeek

Context

Format

OpenAI-compatible

Max output

384K

Input / 1M

$0.25

Output / 1M

$1.15

Cache read / 1M

$0.006

Cache write / 1M

$0.03

View model

GLM 5.2High availability

glm-5.2

GLMOpen sourceOpenAI-compatibleClaude MessagesToolsReasoningStreaming

Model origin

GLM

Context

1.0M

Format

OpenAI-compatible

Max output

131.1K

Input / 1M

$0.95

Output / 1M

$3.00

Cache read / 1M

$0.18

Cache write / 1M

$0.95

View model

GLM 5.3High availability

glm-5.3

GLMOpen sourceOpenAI-compatibleToolsReasoningStreaming

Model origin

GLM

Context

1.3M

Format

OpenAI-compatible

Max output

262.1K

Input / 1M

$1.40

Output / 1M

$4.40

Cache read / 1M

$0.26

Cache write / 1M

$1.40

View model

GLM 5.3 FlashHigh availability

glm-5.3-flash

GLMOpen sourceOpenAI-compatibleVisionToolsReasoning

Model origin

GLM

Context

1.0M

Format

OpenAI-compatible

Max output

131.1K

Input / 1M

$0.15

Output / 1M

$0.50

Cache read / 1M

$0.03

Cache write / 1M

$0.15

View model

Hy4 PreviewHigh availability

hy4-preview

OpenAIOpen sourceOpenAI-compatibleToolsReasoningStreaming

Model origin

OpenAI

Context

960K

Format

OpenAI-compatible

Max output

64K

Input / 1M

$0.834

Output / 1M

$2.501

Cache read / 1M

$0.042

Cache write / 1M

Same as input

View model

Kimi K2.7 CodeHigh availability

kimi-k2.7-code

KimiOpen sourceOpenAI-compatibleClaude MessagesVisionToolsReasoning

Model origin

Kimi

Context

262.1K

Format

OpenAI-compatible

Max output

32.8K

Input / 1M

$0.70

Output / 1M

$3.45

Cache read / 1M

$0.15

Cache write / 1M

$0.70

View model

Kimi K3High availability

kimi-k3

KimiOpen sourceOpenAI-compatibleVisionToolsReasoning

Model origin

Kimi

Context

1.0M

Format

OpenAI-compatible

Max output

131.1K

Input / 1M

$3.00

Output / 1M

$15.00

Cache read / 1M

$0.30

Cache write / 1M

$3.00

View model

MiniMax M2.7High availability

minimax-m2.7

MiniMaxOpen sourceOpenAI-compatibleClaude MessagesToolsReasoningStreaming

Model origin

MiniMax

Context

204.8K

Format

OpenAI-compatible

Max output

204.8K

Input / 1M

$0.29

Output / 1M

$1.19

Cache read / 1M

$0.29

Cache write / 1M

$0.29

View model

MiniMax M3High availability

minimax-m3

MiniMaxOpen sourceOpenAI-compatibleClaude MessagesToolsReasoningStreaming

Model origin

MiniMax

Context

204.8K

Format

OpenAI-compatible

Max output

204.8K

Input / 1M

$0.28

Output / 1M

$1.15

Cache read / 1M

$0.06

Cache write / 1M

$0.28

View model

Qwen3.8 MaxHigh availability

qwen3.8-max

QwenOpen sourceOpenAI-compatibleVisionToolsReasoning

Model origin

Qwen

Context

991.8K

Format

OpenAI-compatible

Max output

131.1K

Input / 1M

$2.00

Output / 1M

$6.00

Cache read / 1M

$0.25

Cache write / 1M

$2.50

View model

AWS Claude Haiku 4 5

aws-claude-haiku-4-5

AWS ClaudeClaudeClaude MessagesVisionToolsReasoning

Model origin

AWS Claude

Context

200K

Format

Claude Messages

Max output

64K

Input / 1M

$0.60

Output / 1M

$3.00

Cache read / 1M

$0.06

Cache write / 1M

$0.75

View model

AWS Claude Opus 5

aws-claude-opus-5

AWS ClaudeClaudeClaude MessagesVisionToolsReasoning

Model origin

AWS Claude

Context

200K

Format

Claude Messages

Max output

64K

Input / 1M

$3.00

Output / 1M

$15.00

Cache read / 1M

$0.30

Cache write / 1M

$3.75

View model

AWS Claude Sonnet 5

aws-claude-sonnet-5

AWS ClaudeClaudeClaude MessagesVisionToolsReasoning

Model origin

AWS Claude

Context

200K

Format

Claude Messages

Max output

64K

Input / 1M

$1.20

Output / 1M

$6.00

Cache read / 1M

$0.12

Cache write / 1M

$1.50

View model

BAAI/Bge M3

BAAI/bge-m3

Open sourceEmbeddingsEmbeddings

Model origin

Open source

Context

8.2K

Format

Embeddings

Max output

—

Input / 1M

$0.01

Output / 1M

$0.00

Cache read / 1M

Not applicable

Cache write / 1M

Not applicable

View model

Claude Fable 5

claude-fable-5

ClaudeClaudeClaude MessagesVisionToolsReasoning

Model origin

Claude

Context

Format

Claude Messages

Max output

128K

Input / 1M

$10.00

Output / 1M

$50.00

Cache read / 1M

$1.00

Cache write / 1M

$12.50

View model

Claude Haiku 4 5

claude-haiku-4-5

ClaudeClaudeClaude MessagesVisionToolsReasoning

Model origin

Claude

Context

200K

Format

Claude Messages

Max output

64K

Input / 1M

$1.00

Output / 1M

$5.00

Cache read / 1M

$0.10

Cache write / 1M

$1.25

View model

Claude Opus 5

claude-opus-5

ClaudeClaudeClaude MessagesVisionToolsReasoning

Model origin

Claude

Context

Format

Claude Messages

Max output

128K

Input / 1M

$5.00

Output / 1M

$25.00

Cache read / 1M

$0.50

Cache write / 1M

$6.25

View model

Claude Sonnet 5

claude-sonnet-5

ClaudeClaudeClaude MessagesVisionToolsReasoning

Model origin

Claude

Context

Format

Claude Messages

Max output

128K

Input / 1M

$2.00

Output / 1M

$10.00

Cache read / 1M

$0.20

Cache write / 1M

$2.50

View model

Gemini 3.1 Pro Preview

gemini-3.1-pro-preview

GoogleGoogleOpenAI-compatibleVisionToolsReasoning

Model origin

Google

Context

1.0M

Format

OpenAI-compatible

Max output

65.5K

Input / 1M

$4.00

Output / 1M

$18.00

Cache read / 1M

$0.40

Cache write / 1M

$0.40

View model

Gemini 3.5 Flash

gemini-3.5-flash

GoogleGoogleOpenAI-compatibleVisionToolsReasoning

Model origin

Google

Context

1.0M

Format

OpenAI-compatible

Max output

65.5K

Input / 1M

$1.50

Output / 1M

$9.00

Cache read / 1M

$0.15

Cache write / 1M

$0.15

View model

Gemini 3.6 Flash

gemini-3.6-flash

GoogleGoogleOpenAI-compatibleVisionToolsReasoning

Model origin

Google

Context

1.0M

Format

OpenAI-compatible

Max output

65.5K

Input / 1M

$0.75

Output / 1M

$3.75

Cache read / 1M

$0.075

Cache write / 1M

$0.075

View model

Gemini 3.7 Flash

gemini-3.7-flash

GoogleGoogleOpenAI-compatibleVisionToolsReasoning

Model origin

Google

Context

1.0M

Format

OpenAI-compatible

Max output

65.5K

Input / 1M

$0.75

Output / 1M

$3.75

Cache read / 1M

$0.075

Cache write / 1M

$0.075

View model

Gemini 3.8 Flash

gemini-3.8-flash

GoogleGoogleOpenAI-compatibleVisionToolsReasoning

Model origin

Google

Context

1.0M

Format

OpenAI-compatible

Max output

65.5K

Input / 1M

$0.75

Output / 1M

$3.75

Cache read / 1M

$0.075

Cache write / 1M

$0.075

View model

GPT 5.6 Luna

gpt-5.6-luna

OpenAIOpenAIOpenAI-compatibleClaude MessagesVisionToolsReasoning

Model origin

OpenAI

Context

922K

Format

OpenAI-compatible

Max output

128K

Input / 1M

$0.20

Output / 1M

$1.20

Cache read / 1M

$0.02

Cache write / 1M

$0.25

View model

GPT 5.6 Sol

gpt-5.6-sol

OpenAIOpenAIOpenAI-compatibleClaude MessagesVisionToolsReasoning

Model origin

OpenAI

Context

922K

Format

OpenAI-compatible

Max output

128K

Input / 1M

$5.00

Output / 1M

$30.00

Cache read / 1M

$0.50

Cache write / 1M

$6.25

View model

GPT 5.6 Terra

gpt-5.6-terra

OpenAIOpenAIOpenAI-compatibleClaude MessagesVisionToolsReasoning

Model origin

OpenAI

Context

922K

Format

OpenAI-compatible

Max output

128K

Input / 1M

$2.00

Output / 1M

$12.00

Cache read / 1M

$0.20

Cache write / 1M

$2.50

View model

GPT 6 Astra

gpt-6-astra

OpenAIOpenAIOpenAI-compatibleVisionToolsReasoning

Model origin

OpenAI

Context

922K

Format

OpenAI-compatible

Max output

128K

Input / 1M

$10.00

Output / 1M

$50.00

Cache read / 1M

$1.00

Cache write / 1M

$12.50

View model

Grok 4.6

grok-4.6

xAI (SpaceX)xAIOpenAI-compatibleVisionToolsReasoning

Model origin

xAI (SpaceX)

Context

500K

Format

OpenAI-compatible

Max output

—

Input / 1M

$2.00

Output / 1M

$6.00

Cache read / 1M

$0.50

Cache write / 1M

Same as input

View model

Qwen/Qwen3 Embedding 0.6B

Qwen/Qwen3-Embedding-0.6B

QwenEmbeddingsEmbeddings

Model origin

Qwen

Context

32.8K

Format

Embeddings

Max output

—

Input / 1M

$0.012

Output / 1M

$0.00

Cache read / 1M

Not applicable

Cache write / 1M

Not applicable

View model

Qwen/Qwen3 Embedding 4B

Qwen/Qwen3-Embedding-4B

QwenEmbeddingsEmbeddings

Model origin

Qwen

Context

32.8K

Format

Embeddings

Max output

—

Input / 1M

$0.02

Output / 1M

$0.00

Cache read / 1M

Not applicable

Cache write / 1M

Not applicable

View model

Qwen3 VL Embedding 2B

Qwen3-VL-Embedding-2B

QwenEmbeddingsEmbeddingsVision

Model origin

Qwen

Context

32.8K

Format

Embeddings

Max output

—

Input / 1M

$0.09

Output / 1M

$0.00

Cache read / 1M

Not applicable

Cache write / 1M

Not applicable

View model

Text Embedding 3 Large

text-embedding-3-large

OpenAIEmbeddingsEmbeddings

Model origin

OpenAI

Context

8.2K

Format

Embeddings

Max output

—

Input / 1M

$0.13

Output / 1M

$0.00

Cache read / 1M

Not applicable

Cache write / 1M

Not applicable

View model

Z Image Turbo

z-image-turbo

OpenAIOpen sourceOpenAI-compatible

Model origin

OpenAI

Context

—

Format

OpenAI-compatible

Max output

—

Input / 1M

$0.00

Output / 1M

$0.00

Cache read / 1M

Same as input

Cache write / 1M

Same as input

View model

Zembed 1

zembed-1

Open sourceEmbeddingsEmbeddings

Model origin

Open source

Context

32.8K

Format

Embeddings

Max output

—

Input / 1M

$0.05

Output / 1M

$0.00

Cache read / 1M

Not applicable

Cache write / 1M

Not applicable

View model

DeepSeek V4 Flash 0731Trial variants

deepseek-v4-flash-0731-trial

DeepSeekTrialOpenAI-compatibleToolsReasoningStreaming

Model origin

DeepSeek

Context

Format

OpenAI-compatible

Max output

384K

Input / 1M

$0.01

Output / 1M

$0.01

Cache read / 1M

$0.001

Cache write / 1M

$0.001

View model

DeepSeek V4 Pro 0813Trial variants

deepseek-v4-pro-0813-trial

DeepSeekTrialOpenAI-compatibleToolsReasoningStreaming

Model origin

DeepSeek

Context

Format

OpenAI-compatible

Max output

384K

Input / 1M

$0.01

Output / 1M

$0.01

Cache read / 1M

$0.001

Cache write / 1M

$0.001

View model

Gemini 3.7 FlashTrial variants

gemini-3.7-flash-trial

GoogleTrialOpenAI-compatibleVisionToolsReasoning

Model origin

Google

Context

1.0M

Format

OpenAI-compatible

Max output

65.5K

Input / 1M

$0.01

Output / 1M

$0.01

Cache read / 1M

$0.001

Cache write / 1M

$0.001

View model

GLM 5.3 FlashTrial variants

glm-5.3-flash-trial

GLMTrialOpenAI-compatibleVisionToolsReasoning

Model origin

GLM

Context

1.0M

Format

OpenAI-compatible

Max output

131.1K

Input / 1M

$0.01

Output / 1M

$0.01

Cache read / 1M

$0.001

Cache write / 1M

$0.001

View model

Grok 4.6Trial variants

grok-4.6-trial

xAI (SpaceX)TrialOpenAI-compatibleVisionToolsReasoning

Model origin

xAI (SpaceX)

Context

500K

Format

OpenAI-compatible

Max output

—

Input / 1M

$0.01

Output / 1M

$0.01

Cache read / 1M

$0.001

Cache write / 1M

$0.001

View model

MiniMax M3Trial variants

MiniMax-M3-trial

MiniMaxTrialOpenAI-compatibleToolsReasoningStreaming

Model origin

MiniMax

Context

204.8K

Format

OpenAI-compatible

Max output

204.8K

Input / 1M

$0.01

Output / 1M

$0.01

Cache read / 1M

$0.001

Cache write / 1M

$0.001

View model

Qwen3.8 MaxTrial variants

qwen3.8-max-trial

QwenTrialOpenAI-compatibleVisionToolsReasoning

Model origin

Qwen

Context

991.8K

Format

OpenAI-compatible

Max output

131.1K

Input / 1M

$0.01

Output / 1M

$0.01

Cache read / 1M

$0.001

Cache write / 1M

$0.001

View model

Need a dedicated embeddings view?

Compare dimensions, context and cost on the specialized page.

Open embeddings view

Next step

Need to understand how a route works?

See how to integrate a model into your application in minutes.

How it works Open API docs