Back to Registry

Databricks API Catalog

Comprehensive overview of all databricks models available through the LLM Kit

Overview

Provider
databricks
Total Models
68
Last Updated
2026-10-01

databricks-bge-large-en

Model ID databricks-bge-large-en
Family
databricks-bge-large-en

Specifications

Context Window: 512 tokens

Modalities

Input
text
Output
embedding

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.09999999999999999
Output
$0.0

databricks-claude-3-7-sonnet

Model ID databricks-claude-3-7-sonnet
Family
databricks-claude-3-7-sonnet

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill

Pricing (per million tokens)

Text Tokens - Standard
Input
$3.0
Output
$15.0

databricks-claude-haiku-4-5

Model ID databricks-claude-haiku-4-5
Family
databricks-claude-haiku-4-5

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 64,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill System messages Prompt caching Cache control

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.0
Output
$5.0
Text Tokens - Cached
Input
$1.25
Output
$0.09999999999999999

databricks-claude-opus-4

Model ID databricks-claude-opus-4
Family
databricks-claude-opus-4

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 32,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill System messages Prompt caching Cache control

Pricing (per million tokens)

Text Tokens - Standard
Input
$15.0
Output
$75.0
Text Tokens - Cached
Input
$18.75
Output
$1.5

databricks-claude-opus-4-1

Model ID databricks-claude-opus-4-1
Family
databricks-claude-opus-4-1

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 32,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill

Pricing (per million tokens)

Text Tokens - Standard
Input
$15.0
Output
$75.0

databricks-claude-opus-4-5

Model ID databricks-claude-opus-4-5
Family
databricks-claude-opus-4-5

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 32,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill Prompt caching System messages Cache control

Pricing (per million tokens)

Text Tokens - Standard
Input
$5.0
Output
$25.0
Text Tokens - Cached
Input
$6.25
Output
$0.5

databricks-claude-opus-4-6

Model ID databricks-claude-opus-4-6
Family
databricks-claude-opus-4-6

Specifications

Context Window: 1,000,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image, pdf
Output
text

Capabilities

Function calling Tool choice Prompt caching Structured output Cache control Assistant prefill

Pricing (per million tokens)

Text Tokens - Standard
Input
$5.0
Output
$25.0
Text Tokens - Cached
Input
$6.25
Output
$0.5

databricks-claude-opus-4-7

Model ID databricks-claude-opus-4-7
Family
databricks-claude-opus-4-7

Specifications

Context Window: 1,000,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image, pdf
Output
text

Capabilities

Function calling Parallel function calling Cache control System messages Tool choice Prompt caching Assistant prefill Structured output Code execution

Pricing (per million tokens)

Text Tokens - Standard
Input
$5.0
Output
$25.0
Text Tokens - Cached
Input
$6.25
Output
$0.5

databricks-claude-sonnet-4

Model ID databricks-claude-sonnet-4
Family
databricks-claude-sonnet-4

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 64,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill

Pricing (per million tokens)

Text Tokens - Standard
Input
$3.0
Output
$15.0

databricks-claude-sonnet-4-1

Model ID databricks-claude-sonnet-4-1
Family
databricks-claude-sonnet-4-1

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 64,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill

Pricing (per million tokens)

Text Tokens - Standard
Input
$3.0
Output
$15.0

databricks-claude-sonnet-4-5

Model ID databricks-claude-sonnet-4-5
Family
databricks-claude-sonnet-4-5

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 64,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill Prompt caching Cache control System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$3.0
Output
$15.0

databricks-claude-sonnet-4-6

Model ID databricks-claude-sonnet-4-6
Family
databricks-claude-sonnet-4-6

Specifications

Context Window: 1,000,000 tokens
Max Output Tokens: 64,000 tokens

Modalities

Input
text, image, pdf
Output
text

Capabilities

Function calling Parallel function calling Tool choice Prompt caching Cache control Structured output Assistant prefill System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$3.0
Output
$15.0
Text Tokens - Cached
Input
$3.75
Output
$0.3

databricks-claude-sonnet-5

Model ID databricks-claude-sonnet-5
Family
databricks-claude-sonnet-5

Specifications

Context Window: 1,000,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice System messages Prompt caching Cache control Structured output Assistant prefill Mid conversation system messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$2.0
Output
$10.0
Text Tokens - Cached
Input
$2.5
Output
$0.19999999999999998

databricks-gemini-2-5-flash

Model ID databricks-gemini-2-5-flash
Family
databricks-gemini-2-5-flash

Specifications

Context Window: 1,048,576 tokens
Max Output Tokens: 65,536 tokens

Modalities

Input
text, image, video, audio
Output
text

Capabilities

Function calling Tool choice Structured output System messages Prompt caching

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.3
Output
$2.5

databricks-gemini-2-5-pro

Model ID databricks-gemini-2-5-pro
Family
databricks-gemini-2-5-pro

Specifications

Context Window: 1,048,576 tokens
Max Output Tokens: 65,536 tokens

Modalities

Input
text, image, audio, video
Output
text

Capabilities

Function calling Tool choice Structured output System messages Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.25
Output
$10.0

databricks-gemma-3-12b

Model ID databricks-gemma-3-12b
Family
databricks-gemma-3-12b

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.15
Output
$0.5
Text Tokens - Cached
Input
$0.15001
Output
$0.15001

databricks-gpt-5

Model ID databricks-gpt-5
Family
databricks-gpt-5

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Parallel function calling System messages Tool choice Structured output Prompt caching Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.25
Output
$10.0
Text Tokens - Cached
Input
$1.25
Output
$0.125

databricks-gpt-5-1

Model ID databricks-gpt-5-1
Family
databricks-gpt-5-1

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

System messages Function calling Parallel function calling Structured output Json output Tool choice Prompt caching

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.25
Output
$10.0
Text Tokens - Cached
Input
$1.24999
Output
$0.125

databricks-gpt-5-2

Model ID databricks-gpt-5-2
Family
databricks-gpt-5-2

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling System messages Tool choice Prompt caching Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.75
Output
$14.0
Text Tokens - Cached
Input
$1.75
Output
$0.175

databricks-gpt-5-3-codex

Model ID databricks-gpt-5-3-codex
Family
databricks-gpt-5-3-codex

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling System messages Tool choice Prompt caching Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.75
Output
$14.0
Text Tokens - Cached
Input
$1.75
Output
$0.175

databricks-gpt-5-4

Model ID databricks-gpt-5-4
Family
databricks-gpt-5-4

Specifications

Context Window: 1,050,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice System messages Structured output Prompt caching Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$2.5
Output
$15.0
Text Tokens - Cached
Input
$2.5
Output
$0.25

databricks-gpt-5-4-mini

Model ID databricks-gpt-5-4-mini
Family
databricks-gpt-5-4-mini

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Structured output Prompt caching Tool choice System messages Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.75
Output
$4.5
Text Tokens - Cached
Input
$0.75
Output
$0.075

databricks-gpt-5-4-nano

Model ID databricks-gpt-5-4-nano
Family
databricks-gpt-5-4-nano

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Structured output Tool choice System messages Prompt caching Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.19999999999999998
Output
$1.25
Text Tokens - Cached
Input
$0.19999999999999998
Output
$0.02

databricks-gpt-5-5

Model ID databricks-gpt-5-5
Family
databricks-gpt-5-5

Specifications

Context Window: 1,050,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice System messages Prompt caching Structured output Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$5.0
Output
$30.0
Text Tokens - Cached
Input
$5.0
Output
$0.5

databricks-gpt-5-5-pro

Model ID databricks-gpt-5-5-pro
Family
databricks-gpt-5-5-pro

Specifications

Context Window: 1,050,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$30.0
Output
$180.0
Text Tokens - Cached
Input
$30.0
Output
$30.0

databricks-gpt-5-6-luna

Model ID databricks-gpt-5-6-luna
Family
databricks-gpt-5-6-luna

Specifications

Context Window: 1,050,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Structured output Prompt caching System messages Tool choice Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.0000200000000001
Output
$5.99998
Text Tokens - Cached
Input
$1.24999
Output
$0.10003000000000001

databricks-gpt-5-6-sol

Model ID databricks-gpt-5-6-sol
Family
databricks-gpt-5-6-sol

Specifications

Context Window: 1,050,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Structured output Prompt caching System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$4.0
Output
$20.0
Text Tokens - Cached
Input
$5.0
Output
$0.39999999999999997

databricks-gpt-5-6-terra

Model ID databricks-gpt-5-6-terra
Family
databricks-gpt-5-6-terra

Specifications

Context Window: 1,050,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling System messages Tool choice Prompt caching Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$2.0
Output
$12.0
Text Tokens - Cached
Input
$2.5
Output
$0.19999999999999998

databricks-gpt-5-mini

Model ID databricks-gpt-5-mini
Family
databricks-gpt-5-mini

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Structured output Json output Prompt caching System messages Cache control

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.25
Output
$2.0
Text Tokens - Cached
Input
$0.25
Output
$0.024999999999999998

databricks-gpt-5-nano

Model ID databricks-gpt-5-nano
Family
databricks-gpt-5-nano

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

System messages Function calling Tool choice Structured output Prompt caching

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.049999999999999996
Output
$0.39999999999999997
Text Tokens - Cached
Input
$0.049999999999999996
Output
$0.005

databricks-gpt-oss-120b

Model ID databricks-gpt-oss-120b
Family
databricks-gpt-oss-120b

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 25,000 tokens

Modalities

Input
text
Output
text

Capabilities

Function calling System messages Tool choice Structured output Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.15
Output
$0.6

databricks-gpt-oss-20b

Model ID databricks-gpt-oss-20b
Family
databricks-gpt-oss-20b

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 25,000 tokens

Modalities

Input
text
Output
text

Capabilities

Function calling Structured output Json output System messages Tool choice

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.07
Output
$0.3

databricks-gte-large-en

Model ID databricks-gte-large-en
Family
databricks-gte-large-en

Specifications

Context Window: 8,192 tokens

Modalities

Input
text
Output
embedding

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.13
Output
$0.0

databricks-llama-2-70b-chat

Model ID databricks-llama-2-70b-chat
Family
databricks-llama-2-70b-chat

Specifications

Context Window: 4,096 tokens
Max Output Tokens: 4,096 tokens

Modalities

Input
text
Output
text

Capabilities

Tool choice

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.5
Output
$1.5

databricks-llama-4-maverick

Model ID databricks-llama-4-maverick
Family
databricks-llama-4-maverick

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.5
Output
$1.5

databricks-meta-llama-3-1-405b-instruct

Model ID databricks-meta-llama-3-1-405b-instruct
Family
databricks-meta-llama-3-1-405b-instruct

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text
Output
text

Capabilities

Tool choice

Pricing (per million tokens)

Text Tokens - Standard
Input
$5.0
Output
$15.0

databricks-meta-llama-3-1-8b-instruct

Model ID databricks-meta-llama-3-1-8b-instruct
Family
databricks-meta-llama-3-1-8b-instruct

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text
Output
text

Capabilities

Function calling Tool choice System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.15
Output
$0.44999999999999996

databricks-meta-llama-3-3-70b-instruct

Model ID databricks-meta-llama-3-3-70b-instruct
Family
databricks-meta-llama-3-3-70b-instruct

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text
Output
text

Capabilities

Tool choice Function calling Structured output Json output System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.5
Output
$1.5

databricks-meta-llama-3-70b-instruct

Model ID databricks-meta-llama-3-70b-instruct
Family
databricks-meta-llama-3-70b-instruct

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text
Output
text

Capabilities

Tool choice

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.0
Output
$3.0

databricks-mixtral-8x7b-instruct

Model ID databricks-mixtral-8x7b-instruct
Family
databricks-mixtral-8x7b-instruct

Specifications

Context Window: 4,096 tokens
Max Output Tokens: 4,096 tokens

Modalities

Input
text
Output
text

Capabilities

Tool choice

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.5
Output
$1.0

databricks-mpt-30b-instruct

Model ID databricks-mpt-30b-instruct
Family
databricks-mpt-30b-instruct

Specifications

Context Window: 8,192 tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text
Output
text

Capabilities

Tool choice

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.0
Output
$1.0

databricks-mpt-7b-instruct

Model ID databricks-mpt-7b-instruct
Family
databricks-mpt-7b-instruct

Specifications

Context Window: 8,192 tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text
Output
text

Capabilities

Tool choice

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.5
Output
$0.0

system.ai.claude-haiku-4-5

Model ID system.ai.claude-haiku-4-5
Family
system.ai.claude-haiku-4-5

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 64,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill System messages Prompt caching Cache control

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.0
Output
$5.0
Text Tokens - Cached
Input
$1.25
Output
$0.09999999999999999

system.ai.claude-opus-4-1

Model ID system.ai.claude-opus-4-1
Family
system.ai.claude-opus-4-1

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 32,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill

Pricing (per million tokens)

Text Tokens - Standard
Input
$15.0
Output
$75.0

system.ai.claude-opus-4-5

Model ID system.ai.claude-opus-4-5
Family
system.ai.claude-opus-4-5

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 32,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill Prompt caching System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$5.0
Output
$25.0
Text Tokens - Cached
Input
$6.25
Output
$0.5

system.ai.claude-opus-4-6

Model ID system.ai.claude-opus-4-6
Family
system.ai.claude-opus-4-6

Specifications

Context Window: 1,000,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image, pdf
Output
text

Capabilities

Function calling Tool choice Prompt caching Structured output Cache control Assistant prefill

Pricing (per million tokens)

Text Tokens - Standard
Input
$5.0
Output
$25.0
Text Tokens - Cached
Input
$6.25
Output
$0.5

system.ai.claude-opus-4-7

Model ID system.ai.claude-opus-4-7
Family
system.ai.claude-opus-4-7

Specifications

Context Window: 1,000,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image, pdf
Output
text

Capabilities

Function calling Parallel function calling Cache control System messages Tool choice Prompt caching Assistant prefill Structured output Code execution

Pricing (per million tokens)

Text Tokens - Standard
Input
$5.0
Output
$25.0
Text Tokens - Cached
Input
$6.25
Output
$0.5

system.ai.claude-sonnet-4

Model ID system.ai.claude-sonnet-4
Family
system.ai.claude-sonnet-4

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 64,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill

Pricing (per million tokens)

Text Tokens - Standard
Input
$3.0
Output
$15.0

system.ai.claude-sonnet-4-5

Model ID system.ai.claude-sonnet-4-5
Family
system.ai.claude-sonnet-4-5

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 64,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Assistant prefill Prompt caching Cache control System messages Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$3.0
Output
$15.0
Text Tokens - Cached
Input
$3.7499700000000002
Output
$0.30002

system.ai.claude-sonnet-4-6

Model ID system.ai.claude-sonnet-4-6
Family
system.ai.claude-sonnet-4-6

Specifications

Context Window: 1,000,000 tokens
Max Output Tokens: 64,000 tokens

Modalities

Input
text, image, pdf
Output
text

Capabilities

Function calling Parallel function calling Tool choice Prompt caching Cache control Structured output Assistant prefill System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$3.0
Output
$15.0
Text Tokens - Cached
Input
$3.75
Output
$0.3

system.ai.gemini-2-5-flash

Model ID system.ai.gemini-2-5-flash
Family
system.ai.gemini-2-5-flash

Specifications

Context Window: 1,048,576 tokens
Max Output Tokens: 65,536 tokens

Modalities

Input
text, image, video, audio
Output
text

Capabilities

Function calling Tool choice Structured output System messages Prompt caching

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.3
Output
$2.5

system.ai.gemini-2-5-pro

Model ID system.ai.gemini-2-5-pro
Family
system.ai.gemini-2-5-pro

Specifications

Context Window: 1,048,576 tokens
Max Output Tokens: 65,536 tokens

Modalities

Input
text, image, audio, video
Output
text

Capabilities

Function calling Tool choice Structured output System messages Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.25
Output
$10.0

system.ai.gemma-3-12b

Model ID system.ai.gemma-3-12b
Family
system.ai.gemma-3-12b

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.15
Output
$0.5

system.ai.gpt-5

Model ID system.ai.gpt-5
Family
system.ai.gpt-5

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Parallel function calling System messages Tool choice Structured output Prompt caching Json output Cache control

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.25
Output
$10.0
Text Tokens - Cached
Input
$1.24999
Output
$0.125

system.ai.gpt-5-1

Model ID system.ai.gpt-5-1
Family
system.ai.gpt-5-1

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

System messages Function calling Structured output Json output Tool choice Prompt caching

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.25
Output
$10.0
Text Tokens - Cached
Input
$1.25
Output
$0.125

system.ai.gpt-5-2

Model ID system.ai.gpt-5-2
Family
system.ai.gpt-5-2

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling System messages Tool choice Prompt caching Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.75
Output
$14.0
Text Tokens - Cached
Input
$1.75
Output
$0.175

system.ai.gpt-5-3-codex

Model ID system.ai.gpt-5-3-codex
Family
system.ai.gpt-5-3-codex

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling System messages Tool choice Prompt caching Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.75
Output
$14.0
Text Tokens - Cached
Input
$1.75
Output
$0.175

system.ai.gpt-5-4

Model ID system.ai.gpt-5-4
Family
system.ai.gpt-5-4

Specifications

Context Window: 1,050,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice System messages Structured output Prompt caching Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$2.5
Output
$15.0
Text Tokens - Cached
Input
$2.5
Output
$0.25

system.ai.gpt-5-4-mini

Model ID system.ai.gpt-5-4-mini
Family
system.ai.gpt-5-4-mini

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Structured output Prompt caching Tool choice System messages Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.75
Output
$4.5
Text Tokens - Cached
Input
$0.75
Output
$0.075

system.ai.gpt-5-4-nano

Model ID system.ai.gpt-5-4-nano
Family
system.ai.gpt-5-4-nano

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Structured output Tool choice System messages Prompt caching

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.19999999999999998
Output
$1.25
Text Tokens - Cached
Input
$0.19999999999999998
Output
$0.02

system.ai.gpt-5-5-pro

Model ID system.ai.gpt-5-5-pro
Family
system.ai.gpt-5-5-pro

Specifications

Context Window: 1,050,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Structured output System messages Tool choice Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$30.0
Output
$180.0

system.ai.gpt-5-mini

Model ID system.ai.gpt-5-mini
Family
system.ai.gpt-5-mini

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Structured output Json output Prompt caching System messages Cache control

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.25
Output
$2.0
Text Tokens - Cached
Input
$0.24997
Output
$0.024999999999999998

system.ai.gpt-5-nano

Model ID system.ai.gpt-5-nano
Family
system.ai.gpt-5-nano

Specifications

Context Window: 400,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

System messages Function calling Tool choice Structured output Prompt caching

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.049999999999999996
Output
$0.39999999999999997
Text Tokens - Cached
Input
$0.049999999999999996
Output
$0.005

system.ai.gpt-oss-120b

Model ID system.ai.gpt-oss-120b
Family
system.ai.gpt-oss-120b

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 25,000 tokens

Modalities

Input
text
Output
text

Capabilities

Function calling System messages Tool choice Structured output Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.15
Output
$0.6

system.ai.gpt-oss-20b

Model ID system.ai.gpt-oss-20b
Family
system.ai.gpt-oss-20b

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 25,000 tokens

Modalities

Input
text
Output
text

Capabilities

Function calling Structured output Json output System messages Tool choice

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.07
Output
$0.3

system.ai.gte-large-en

Model ID system.ai.gte-large-en
Family
system.ai.gte-large-en

Specifications

Context Window: 8,192 tokens

Modalities

Input
text
Output
embedding

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.13
Output
$0.0

system.ai.llama-4-maverick

Model ID system.ai.llama-4-maverick
Family
system.ai.llama-4-maverick

Specifications

Context Window: tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text, image
Output
text

Capabilities

Function calling Tool choice Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.5
Output
$1.5

system.ai.meta-llama-3-3-70b-instruct

Model ID system.ai.meta-llama-3-3-70b-instruct
Family
system.ai.meta-llama-3-3-70b-instruct

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text
Output
text

Capabilities

Tool choice Function calling Structured output Json output System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.5
Output
$1.5