Find your next model

Compare verified models, copy exact IDs, and go from discovery to a working request without leaving ModelPort.

Live catalog

Verified models

105

Providers

16

Latest health audit

9/24/2026, 12:01:59 AM

OP

OpenAI

Verified
text

GPT 6 Astra

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$1.60per 1M tokens

One rate for input and output

1.1M contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

cx/gpt-6-astra
Use model
AN

Anthropic

Verified
text

Claude Opus 5

Chat and agent model from Anthropic. Works anywhere the OpenAI API works.

$1.20per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings score92.0% less

Sourced exact-model input + output benchmark

cc/claude-opus-5
Use model
AN

Anthropic

Verified
text

Claude Opus 4.6

Chat and agent model from Anthropic. Works anywhere the OpenAI API works.

$0.80per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings score94.7% less

Sourced exact-model input + output benchmark

cc/claude-opus-4-6
Use model
AN

Anthropic

Verified
text

Claude Opus 4.7

Chat and agent model from Anthropic. Works anywhere the OpenAI API works.

$0.80per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings score94.7% less

Sourced exact-model input + output benchmark

cc/claude-opus-4-7
Use model
AN

Anthropic

Verified
text

Claude Opus 4.8

Chat and agent model from Anthropic. Works anywhere the OpenAI API works.

$0.80per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings score94.7% less

Sourced exact-model input + output benchmark

cc/claude-opus-4-8
Use model
OP

OpenAI

Verified
text

GPT 5.6 Sol

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$0.80per 1M tokens

One rate for input and output

1.1M contextReasoningToolsVisionSearch
Savings score95.4% less

Sourced exact-model input + output benchmark

cx/gpt-5.6-sol
Use model
OP

OpenAI

Verified
text

GPT 5.6 Sol Review

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$0.80per 1M tokens

One rate for input and output

1.1M contextReasoningToolsVisionSearch
Savings scoreN/A

no direct-vendor review SKU

cx/gpt-5.6-sol-review
Use model
QW

Qwen

Verified
text

Qwen3.6 35B A3B

Chat and agent model from Qwen. Works anywhere the OpenAI API works.

$0.64per 1M tokens

Input $0.64 · output $4.60

1M contextReasoningToolsVision
Savings scoreN/A

exact direct list price not published

am/qwen3.6-35b-a3b
Use model
AN

Anthropic

Verified
text

Claude Sonnet 5

Chat and agent model from Anthropic. Works anywhere the OpenAI API works.

$0.60per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings score90.0% less

Sourced exact-model input + output benchmark

cc/claude-sonnet-5
Use model
OP

OpenAI

Verified
text

GPT 5.5

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$0.60per 1M tokens

One rate for input and output

400K contextReasoningToolsVisionSearch
Savings score96.6% less

Sourced exact-model input + output benchmark

cx/gpt-5.5
Use model
OP

OpenAI

Verified
text

GPT 5.5 Review

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$0.60per 1M tokens

One rate for input and output

400K contextReasoningToolsVisionSearch
Savings scoreN/A

no direct-vendor review SKU

cx/gpt-5.5-review
Use model
OP

OpenAI

Verified
text

GPT 5.6 Terra

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$0.60per 1M tokens

One rate for input and output

1.1M contextReasoningToolsVisionSearch
Savings score91.4% less

Sourced exact-model input + output benchmark

cx/gpt-5.6-terra
Use model
OP

OpenAI

Verified
text

GPT 5.6 Terra Review

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$0.60per 1M tokens

One rate for input and output

1.1M contextReasoningToolsVisionSearch
Savings scoreN/A

no direct-vendor review SKU

cx/gpt-5.6-terra-review
Use model
MO

Moonshot

Verified
text

K3

Chat and agent model from Moonshot. Works anywhere the OpenAI API works.

$0.60per 1M tokens

One rate for input and output

262K contextReasoningToolsVision
Savings scoreN/A

no exact public direct-vendor price

kmc/k3
Use model
AN

Anthropic

Verified
text

Claude Sonnet 4.6

Chat and agent model from Anthropic. Works anywhere the OpenAI API works.

$0.48per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings score94.7% less

Sourced exact-model input + output benchmark

cc/claude-sonnet-4-6
Use model
AN

Anthropic

Verified
text

Claude Sonnet 4.6

Chat and agent model from Anthropic. Works anywhere the OpenAI API works.

$0.48per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings scoreN/A

gateway-specific agent variant

ag/claude-sonnet-4-6
Use model
XA

xAI

Verified
text

Grok 4.20 Multi Agent (0309)

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.40per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings scoreN/A

gateway-specific agent variant

xai/grok-4.20-multi-agent-0309
Use model
XA

xAI

Verified
text

Grok 4.5

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.40per 1M tokens

One rate for input and output

500K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

gcli/grok-4.5
Use model
XA

xAI

Verified
text

Grok 4.5

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.40per 1M tokens

One rate for input and output

500K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-4.5
Use model
XA

xAI

Verified
text

Grok 4.6

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.40per 1M tokens

One rate for input and output

500K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

gcli/grok-4.6
Use model
XA

xAI

Verified
text

Grok 4.6

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.40per 1M tokens

One rate for input and output

500K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-4.6
Use model
XA

xAI

Verified
text

Grok 4.7

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.40per 1M tokens

One rate for input and output

500K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-4.7
Use model
XA

xAI

Verified
text

Grok 4.7

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.40per 1M tokens

One rate for input and output

500K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

gcli/grok-4.7
Use model
XA

xAI

Verified
text

Grok 4.7 Build Fast

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.40per 1M tokens

One rate for input and output

500K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

gcli/grok-4.7-build-fast
Use model
GL

Google

Verified
text

Gemini 3.1 Pro Low

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.34per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-3.1-pro-low
Use model
GL

Google

Verified
text

Gemini Pro Agent

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.34per 1M tokens

One rate for input and output

1M contextToolsVisionSearch
Savings scoreN/A

gateway-specific agent variant

ag/gemini-pro-agent
Use model
AN

Anthropic

Verified
text

Claude Haiku 4.5 (20251001)

Chat and agent model from Anthropic. Works anywhere the OpenAI API works.

$0.32per 1M tokens

One rate for input and output

200K contextReasoningToolsVisionSearch
Savings score89.3% less

Sourced exact-model input + output benchmark

cc/claude-haiku-4-5-20251001
Use model
ZH

Zhipu

Verified
text

GLM 5.1

Chat and agent model from Zhipu. Works anywhere the OpenAI API works.

$0.30per 1M tokens

One rate for input and output

200K contextReasoningTools
Savings scoreN/A

exact direct list price not published

glm/glm-5.1
Use model
ZH

Zhipu

Verified
text

GLM 5.2

Chat and agent model from Zhipu. Works anywhere the OpenAI API works.

$0.30per 1M tokens

One rate for input and output

200K contextReasoningTools
Savings scoreN/A

exact direct list price not published

glm/glm-5.2
Use model
ZH

Zhipu

Verified
text

GLM 5.3

Chat and agent model from Zhipu. Works anywhere the OpenAI API works.

$0.30per 1M tokens

One rate for input and output

200K contextReasoningTools
Savings scoreN/A

exact direct list price not published

glm/glm-5.3
Use model
OP

OpenAI

Verified
text

GPT 5.6 Luna

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$0.30per 1M tokens

One rate for input and output

1.1M contextReasoningToolsVisionSearch
Savings score57.1% less

Sourced exact-model input + output benchmark

cx/gpt-5.6-luna
Use model
OP

OpenAI

Verified
text

GPT 5.6 Luna Review

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$0.30per 1M tokens

One rate for input and output

1.1M contextReasoningToolsVisionSearch
Savings scoreN/A

no direct-vendor review SKU

cx/gpt-5.6-luna-review
Use model
MO

Moonshot

Verified
text

Kimi For Coding

Chat and agent model from Moonshot. Works anywhere the OpenAI API works.

$0.30per 1M tokens

One rate for input and output

262K contextReasoningToolsVision
Savings scoreN/A

no exact public direct-vendor price

kmc/kimi-for-coding
Use model
XA

xAI

Verified
text

Grok 4.20 Non Reasoning (0309)

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.20per 1M tokens

One rate for input and output

1M contextToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-4.20-0309-non-reasoning
Use model
XA

xAI

Verified
text

Grok 4.20 Reasoning (0309)

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.20per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-4.20-0309-reasoning
Use model
XA

xAI

Verified
text

Grok 4.3

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.20per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-4.3
Use model
AN

ANTHROPIC

Verified
text

Claude Fable 5 GPT 5.6 Luna

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-fable-5-gpt-5-6-luna
Use model
AN

ANTHROPIC

Verified
text

Claude Fable 5 GPT 5.6 Sol

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-fable-5-gpt-5-6-sol
Use model
AN

ANTHROPIC

Verified
text

Claude Fable 5 GPT 5.6 Terra

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-fable-5-gpt-5-6-terra
Use model
AN

ANTHROPIC

Verified
text

Claude Haiku 4.5 GPT 5.6 Luna

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-haiku-4-5-gpt-5-6-luna
Use model
AN

ANTHROPIC

Verified
text

Claude Haiku 4.5 GPT 5.6 Sol

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-haiku-4-5-gpt-5-6-sol
Use model
AN

ANTHROPIC

Verified
text

Claude Haiku 4.5 GPT 5.6 Terra

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-haiku-4-5-gpt-5-6-terra
Use model
AN

ANTHROPIC

Verified
text

Claude Opus 4.5 GPT 5.6 Luna

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-opus-4-5-gpt-5-6-luna
Use model
AN

ANTHROPIC

Verified
text

Claude Opus 4.5 GPT 5.6 Sol

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-opus-4-5-gpt-5-6-sol
Use model
AN

ANTHROPIC

Verified
text

Claude Opus 4.5 GPT 5.6 Terra

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-opus-4-5-gpt-5-6-terra
Use model
AN

ANTHROPIC

Verified
text

Claude Sonnet 4.5 GPT 5.6 Luna

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-sonnet-4-5-gpt-5-6-luna
Use model
AN

ANTHROPIC

Verified
text

Claude Sonnet 4.5 GPT 5.6 Sol

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-sonnet-4-5-gpt-5-6-sol
Use model
AN

ANTHROPIC

Verified
text

Claude Sonnet 4.5 GPT 5.6 Terra

Chat and agent model from ANTHROPIC. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

Savings scoreN/A

no exact public direct-vendor price

anthropic/claude-sonnet-4-5-gpt-5-6-terra
Use model
XA

xAI

Verified
text

Grok 3

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

131K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-3
Use model
XA

xAI

Verified
text

Grok 4

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

256K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-4
Use model
XA

xAI

Verified
text

Grok 4 Fast Reasoning

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

256K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-4-fast-reasoning
Use model
XA

xAI

Verified
text

Grok Code Fast 1

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.14per 1M tokens

One rate for input and output

256K contextReasoningTools
Savings scoreN/A

no exact public direct-vendor price

xai/grok-code-fast-1
Use model
GL

Google

Verified
text

Gemini 2.5 Flash

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-2.5-flash
Use model
GL

Google

Verified
text

Gemini 2.5 Flash

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

official price source not yet verified

gc/gemini-2.5-flash
Use model
GL

Google

Verified
text

Gemini 2.5 Flash Lite

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-2.5-flash-lite
Use model
GL

Google

Verified
text

Gemini 2.5 Flash Lite

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

official price source not yet verified

gc/gemini-2.5-flash-lite
Use model
GL

Google

Verified
text

Gemini 3 Flash

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-3-flash
Use model
GL

Google

Verified
text

Gemini 3.1 Flash Lite Preview

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

official price source not yet verified

gc/gemini-3.1-flash-lite-preview
Use model
GL

Google

Verified
text

Gemini 3.1 Flash Lite Preview

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-3.1-flash-lite-preview
Use model
GL

Google

Verified
text

Gemini 3.6 Flash High

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-3.6-flash-high
Use model
GL

Google

Verified
text

Gemini 3.6 Flash Low

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-3.6-flash-low
Use model
GL

Google

Verified
text

Gemini 3.6 Flash Medium

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-3.6-flash-medium
Use model
GL

Google

Verified
text

Gemini 3.7 Flash High

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-3.7-flash-high
Use model
GL

Google

Verified
text

Gemini 3.7 Flash Low

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-3.7-flash-low
Use model
GL

Google

Verified
text

Gemini 3.7 Flash Medium

Chat and agent model from Google. Works anywhere the OpenAI API works.

$0.12per 1M tokens

One rate for input and output

1M contextReasoningToolsVisionSearchAudio in
Savings scoreN/A

gateway-specific agent variant

ag/gemini-3.7-flash-medium
Use model
ZH

Zhipu

Verified
text

GLM 5

Chat and agent model from Zhipu. Works anywhere the OpenAI API works.

$0.10per 1M tokens

One rate for input and output

200K contextReasoningTools
Savings scoreN/A

exact direct list price not published

glm/glm-5
Use model
ZH

Zhipu

Verified
text

GLM 5.3 Flash

Chat and agent model from Zhipu. Works anywhere the OpenAI API works.

$0.10per 1M tokens

One rate for input and output

1M contextReasoningToolsVision
Savings scoreN/A

exact direct list price not published

glm/glm-5.3-flash
Use model
OP

OpenAI

Verified
text

GPT OSS 120B Medium

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

$0.10per 1M tokens

One rate for input and output

128K contextReasoningTools
Savings scoreN/A

gateway-specific agent variant

ag/gpt-oss-120b-medium
Use model
XA

xAI

Verified
text

Grok Build 0.1

Chat and agent model from xAI. Works anywhere the OpenAI API works.

$0.10per 1M tokens

One rate for input and output

256K contextReasoningToolsVisionSearch
Savings scoreN/A

no exact public direct-vendor price

xai/grok-build-0.1
Use model
ZH

Zhipu

Verified
text

GLM 4.6v

Chat and agent model from Zhipu. Works anywhere the OpenAI API works.

$0.06per 1M tokens

One rate for input and output

128K contextReasoningToolsVision
Savings scoreN/A

exact direct list price not published

glm/glm-4.6v
Use model
ZH

Zhipu

Verified
text

GLM 4.7

Chat and agent model from Zhipu. Works anywhere the OpenAI API works.

$0.06per 1M tokens

One rate for input and output

200K contextReasoningTools
Savings scoreN/A

exact direct list price not published

glm/glm-4.7
Use model
QW

Qwen

Verified
text

Qwen3.7 Max

Chat and agent model from Qwen. Works anywhere the OpenAI API works.

$0.05per 1M tokens

One rate for input and output

1M contextReasoningTools
Savings scoreN/A

no exact public direct-vendor price

qwen/qwen3.7-max
Use model
QW

Qwen

Verified
text

Qwen3.7 Plus

Chat and agent model from Qwen. Works anywhere the OpenAI API works.

$0.05per 1M tokens

One rate for input and output

1M contextReasoningToolsVision
Savings scoreN/A

no exact public direct-vendor price

qwen/qwen3.7-plus
Use model
QW

Qwen

Verified
text

Qwen3.8 Max

Chat and agent model from Qwen. Works anywhere the OpenAI API works.

$0.05per 1M tokens

One rate for input and output

1M contextReasoningTools
Savings scoreN/A

no exact public direct-vendor price

qwen/qwen3.8-max
Use model
DS

DeepSeek

Verified
text

DeepSeek V4 Pro

Chat and agent model from DeepSeek. Works anywhere the OpenAI API works.

$0.03per 1M tokens

One rate for input and output

1M contextReasoningTools
Savings scoreN/A

no exact public direct-vendor price

ds/deepseek-v4-pro
Use model
DS

DeepSeek

Verified
text

DeepSeek V4 Flash

Chat and agent model from DeepSeek. Works anywhere the OpenAI API works.

$0.01per 1M tokens

One rate for input and output

1M contextReasoningTools
Savings scoreN/A

no exact public direct-vendor price

ds/deepseek-v4-flash
Use model
XA

xAI

Verified
image

Grok Imagine Image Quality

Generates images from a text prompt. Billed per image, not per token.

$0.87per image
Savings scoreN/A

image uses a different billing unit

xai/grok-imagine-image-quality
GL

Google

Verified
image

Nano Banana Pro

Generates images from a text prompt. Billed per image, not per token.

$0.60per image
Savings scoreN/A

image uses a different billing unit

flow/nano-banana-pro
OP

OpenAI

Verified
image

GPT Image 2

Generates images from a text prompt. Billed per image, not per token.

$0.50per image
Savings scoreN/A

image uses a different billing unit

cx/gpt-image-2
OP

OpenAI

Verified
image

GPT Image 1.5

Generates images from a text prompt. Billed per image, not per token.

$0.38per image
Savings scoreN/A

image uses a different billing unit

cx/gpt-image-1.5
XA

xAI

Verified
image

Grok Imagine Image

Generates images from a text prompt. Billed per image, not per token.

$0.35per image
Savings scoreN/A

image uses a different billing unit

xai/grok-imagine-image
GL

Google

Verified
image

Nano Banana

Generates images from a text prompt. Billed per image, not per token.

$0.30per image
Savings scoreN/A

image uses a different billing unit

flow/nano-banana
GL

Google

Verified
image

Gemini 3.1 Flash Image

Generates images from a text prompt. Billed per image, not per token.

$0.20per image
Savings scoreN/A

image uses a different billing unit

ag/gemini-3.1-flash-image
DG

Deepgram

Verified
stt

Nova

Transcribes speech to text. Billed per minute of audio.

$0.20per minute
Savings scoreN/A

stt uses a different billing unit

dg/nova
DG

Deepgram

Verified
stt

Nova 2

Transcribes speech to text. Billed per minute of audio.

$0.20per minute
Savings scoreN/A

stt uses a different billing unit

dg/nova-2
DG

Deepgram

Verified
stt

Nova 3

Transcribes speech to text. Billed per minute of audio.

$0.20per minute
Savings scoreN/A

stt uses a different billing unit

dg/nova-3
DG

Deepgram

Verified
stt

Whisper Large

Transcribes speech to text. Billed per minute of audio.

$0.20per minute
Savings scoreN/A

stt uses a different billing unit

dg/whisper-large
NV

NVIDIA

Verified
embedding

Llama Nemotron Embed VL 1B V2

Turns text into vectors for search, ranking, and retrieval. Not a chat model.

$0.02per 1M tokens
Savings scoreN/A

embedding uses a different billing unit

am/nvidia/llama-nemotron-embed-vl-1b-v2:free
DS

DeepSeek

temporarily_unavailable
text

DeepSeek V4 Flash

Chat and agent model from DeepSeek. Works anywhere the OpenAI API works.

Free

One rate for input and output

1M contextReasoningTools
Savings scoreN/A

exact direct list price not published

am/deepseek-v4-flash
Use model
GL

Google

Verified
text

DiffusionGemma 26B A4B IT

Chat and agent model from Google. Works anywhere the OpenAI API works.

Free

One rate for input and output

131K contextReasoningVision
Savings scoreN/A

exact direct list price not published

am/diffusiongemma-26b-a4b-it
Use model
BF

Black Forest Labs

Verified
image

Flux.2 Klein 4B

Generates images from a text prompt. Billed per image, not per token.

Free
Savings scoreN/A

image uses a different billing unit

am/flux.2-klein-4b
OS

Open models

Verified
text

Free

Chat and agent model from Open models. Works anywhere the OpenAI API works.

Free

One rate for input and output

Savings scoreN/A

exact direct list price not published

am/free
Use model
OP

OpenAI

Verified
text

GPT OSS 20B

Chat and agent model from OpenAI. Works anywhere the OpenAI API works.

Free

One rate for input and output

131K contextReasoningTools
Savings scoreN/A

exact direct list price not published

am/gpt-oss-20b
Use model
PO

Poolside

Verified
text

Laguna XS 2.1

Chat and agent model from Poolside. Works anywhere the OpenAI API works.

Free

One rate for input and output

131K contextTools
Savings scoreN/A

exact direct list price not published

am/laguna-xs-2.1
Use model
ME

Meta

Verified
text

Llama 3.2 11B Vision Instruct

Chat and agent model from Meta. Works anywhere the OpenAI API works.

Free

One rate for input and output

131K contextToolsVision
Savings scoreN/A

exact direct list price not published

am/llama-3.2-11b-vision-instruct
Use model
NV

NVIDIA

Verified
embedding

Llama Nemotron Embed VL 1B V2

Turns text into vectors for search, ranking, and retrieval. Not a chat model.

Free
Savings scoreN/A

embedding uses a different billing unit

am/llama-nemotron-embed-vl-1b-v2
MA

Mistral AI

Verified
text

Mistral Nemotron

Chat and agent model from Mistral AI. Works anywhere the OpenAI API works.

Free

One rate for input and output

131K contextReasoningTools
Savings scoreN/A

exact direct list price not published

am/mistral-nemotron
Use model
NV

NVIDIA

Verified
embedding

Nemotron 3 Embed 1B

Turns text into vectors for search, ranking, and retrieval. Not a chat model.

Free
Savings scoreN/A

embedding uses a different billing unit

am/nemotron-3-embed-1b
NV

NVIDIA

Verified
text

Nemotron 3 Nano Omni 30B A3B Reasoning

Chat and agent model from NVIDIA. Works anywhere the OpenAI API works.

Free

One rate for input and output

262K contextReasoningToolsVisionAudio in
Savings scoreN/A

exact direct list price not published

am/nemotron-3-nano-omni-30b-a3b-reasoning
Use model
NV

NVIDIA

Verified
stt

Nemotron 3 Nano Omni 30B A3B Reasoning STT

Transcribes speech to text. Billed per minute of audio.

Free
Savings scoreN/A

stt uses a different billing unit

am/nemotron-3-nano-omni-30b-a3b-reasoning-stt
NV

NVIDIA

Verified
text

Nemotron 3 Super 120B A12B

Chat and agent model from NVIDIA. Works anywhere the OpenAI API works.

Free

One rate for input and output

262K contextReasoningTools
Savings scoreN/A

exact direct list price not published

am/nemotron-3-super-120b-a12b
Use model
NV

NVIDIA

Verified
text

Nemotron 3 Ultra 550B A55B

Chat and agent model from NVIDIA. Works anywhere the OpenAI API works.

Free

One rate for input and output

262K contextReasoningTools
Savings scoreN/A

exact direct list price not published

am/nemotron-3-ultra-550b-a55b
Use model
NV

NVIDIA

Verified
text

Nemotron 3.5 Content Safety

Chat and agent model from NVIDIA. Works anywhere the OpenAI API works.

Free

One rate for input and output

33K context
Savings scoreN/A

exact direct list price not published

am/nemotron-3.5-content-safety
Use model
NV

NVIDIA

Verified
text

Nemotron 3.5 Lightning 30B A3B

Chat and agent model from NVIDIA. Works anywhere the OpenAI API works.

Free

One rate for input and output

262K contextReasoningTools
Savings scoreN/A

exact direct list price not published

am/nemotron-3.5-lightning-30b-a3b
Use model
NV

NVIDIA

Verified
text

Riva Translate 4B Instruct V2

Chat and agent model from NVIDIA. Works anywhere the OpenAI API works.

Free

One rate for input and output

8K context
Savings scoreN/A

exact direct list price not published

am/riva-translate-4b-instruct-v2
Use model

Showing 105 of 105 verified models. Every paid model has a savings status; a percentage appears only for an exact, unit-matched comparison backed by an official source.