ModelPorta
Create account

THE MODEL DIRECTORY

A model for your next idea.

Explore the catalog across providers. Compare the cost. Find your fit.

Integration guide ↗
397 catalog entries22 providersPay as you go no subscription
Preview pricing · API activation pending

Prices use published service-group rates. Availability and the final service group will be confirmed before activation. Text prices are per 1 million tokens; other units are shown separately.

Compare ModelPorta with published provider prices. Savings use our final sale rates: (official − our price) ÷ official. Input and output are compared separately. Sources and comparison conditions appear on each card; “not verified” means no reliable matching benchmark. Taxes, tools, batch discounts and cache storage are excluded.

155 of 397 listings have a verified official token-price reference. These are provider prices, not previous ModelPorta prices. Different regions, routing and service terms may apply.

397 matching modelsPrices checked Sep 9, 2026
CClaudePreview

claude-opus-5

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$5.00$0.6176887.6%
Output$25.00$3.088487.6%
Cached input$0.50$0.06176887.6%

Claude API · standard base input and output rates.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
OOpenAIPreview

gpt-5.6-sol

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$4.00$0.2573993.5%
Output$20.00$1.5443492.2%
Cached input$0.40$0.02573993.5%

OpenAI Standard · short-context text rates. Regional and fast-mode charges excluded.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
GGooglePreview

gemini-3.1-pro-preview

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$2.00$0.74118862.9%
Output$12.00$4.44712862.9%
Cached input$0.20$0.07411962.9%

Gemini paid Standard · text tokens; base context tier; cache storage excluded. Prompts up to 200K tokens.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
GGooglePreview

gemini-3-flash-preview

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$0.50$0.05147189.7%
Output$3.00$0.30882689.7%
Cached input$0.05$0.00514889.7%

Gemini paid Standard · text tokens; base context tier; cache storage excluded.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
OOpenAI PlusPreview

gpt-image-2-c

Image
USD · reference settings
UsageOfficialOur priceSaving
Generation$0.012354

Official: not verified · saving unavailable.
No verified official price for these exact generation settings.

Settings can change the final cost. This service is not enabled.

CClaudePreview

claude-fable-5-1

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$10.00$2.4705875.2%
Output$50.00$12.352975.2%
Cached input$0.25$0.06176675.2%

Claude API · standard base input and output rates.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
GGooglePreview

gemini-3.8-flash

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$0.75$0.27794762.9%
Output$3.75$1.38972962.9%
Cached input$0.075$0.02779562.9%

Gemini paid Standard · text tokens; base context tier; cache storage excluded. Current promotional rates through 2026-12-31.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
GGooglePreview

gemini-3.1-flash-image-preview

Image
USD · reference settings
UsageOfficialOur priceSaving
Generation$0.017037

Official: not verified · saving unavailable.
No verified official price for these exact generation settings.

Settings can change the final cost. This service is not enabled.

CClaudePreview

claude-opus-4-8

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$5.00$0.6176887.6%
Output$25.00$3.088487.6%
Cached input$0.50$0.06176887.6%

Claude API · standard base input and output rates.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
OOpenAIPreview

gpt-5.5

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$5.00$0.2573994.8%
Output$30.00$1.5443494.8%
Cached input$0.50$0.02573994.8%

OpenAI Standard · short-context text rates. Regional and fast-mode charges excluded.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
GGooglePreview

gemini-3-pro-image-preview

Image
USD · reference settings
UsageOfficialOur priceSaving
Generation$0.033971

Official: not verified · saving unavailable.
No verified official price for these exact generation settings.

Settings can change the final cost. This service is not enabled.

GGooglePreview

gemini-3.7-flash

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$0.75$0.07720889.7%
Output$3.75$0.38603489.7%
Cached input$0.075$0.00772189.7%

Gemini paid Standard · text tokens; base context tier; cache storage excluded. Current promotional rates through 2026-12-31.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
GGooglePreview

gemini-3.1-flash-lite

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$0.25$0.02573789.7%
Output$1.50$0.15441389.7%
Cached input$0.025$0.00257489.7%

Gemini paid Standard · text tokens; base context tier; cache storage excluded.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
OOpenAIPreview

gpt-6-astra

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$10.00$0.5147894.8%
Output$50.00$2.573994.8%
Cached input$1.00$0.05147894.8%

OpenAI Standard · short-context text rates. Regional and fast-mode charges excluded.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
OOpenAIPreview

gpt-image-2

Image
USD reference rates · billing unit not verified
UsageOfficialOur priceSaving
Input reference$0.41181
Output reference$2.47086

Official: not verified · saving unavailable.
An exact official price comparison has not been verified for this model.

Final ModelPorta rates are shown above.
CClaudePreview

claude-fable-5

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$10.00$2.4705875.2%
Output$50.00$12.352975.2%
Cached input$1.00$0.24705875.2%

Claude API · standard base input and output rates.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
CClaudePreview

claude-sonnet-5

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$2.00$0.24707287.6%
Output$10.00$1.2353687.6%
Cached input$0.20$0.02470887.6%

Claude API · standard base input and output rates.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
OOpenAIPreview

gpt-5.6-terra

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$2.00$0.10295694.8%
Output$12.00$0.61773694.8%
Cached input$0.20$0.01029694.8%

OpenAI Standard · short-context text rates. Regional and fast-mode charges excluded.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
OOpenAIPreview

gpt-5.6-luna

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$0.20$0.02882685.5%
Output$1.20$0.17295685.5%
Cached input$0.02$0.00288385.5%

OpenAI Standard · short-context text rates. Regional and fast-mode charges excluded.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
CClaudePreview

claude-opus-4-6

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$5.00$0.6176887.6%
Output$25.00$3.088487.6%
Cached input$0.50$0.06176887.6%

Claude API · standard base input and output rates.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
GGooglePreview

gemini-3.5-flash

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$1.50$0.55589162.9%
Output$9.00$3.33534662.9%
Cached input$0.15$0.0555962.9%

Gemini paid Standard · text tokens; base context tier; cache storage excluded.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
CClaudePreview

claude-sonnet-4-6

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$3.00$0.37060887.6%
Output$15.00$1.8530487.6%
Cached input$0.30$0.03706187.6%

Claude API · standard base input and output rates.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
GGooglePreview

gemini-2.5-pro

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$1.25$0.46324462.9%
Output$10.00$3.7059462.9%
Cached input$0.125$0.04632562.9%

Gemini paid Standard · text tokens; base context tier; cache storage excluded. Prompts up to 200K tokens.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
CChatGLMPreview

glm-5.3-flash

Chat
USD per 1M tokens · base context tier
UsageOfficialOur priceSaving
Input$0.15$0.052565%
Output$0.50$0.17565%
Cached input$0.03$0.010565%

Z.AI · standard text API rates; cache storage excluded.

Official price source ↗Checked 2026-09-09
Final ModelPorta rates are shown above.
Page 1 of 17
Found your next model?

Create a free account and prepare your application keys. Live access opens after activation.

Create free account