anonrouter
Sign up

Model comparison

Claude Fable 5 vs GPT-5.5 vs Gemini 3.1 Pro Preview

Compare verified catalog metadata across pricing, context, privacy, capabilities, and routing. Unknown values remain unknown—no synthetic benchmark claims.

Open in chat

Overview

Creator

Anthropic

Creator

OpenAI

Creator

Google

Provider

Venice

Provider

Venice

Provider

Venice

Model ID

anthropic/claude-fable-5

Model ID

openai/gpt-5.5

Model ID

google/gemini-3.1-pro-preview

Modalities

Modalities

Modalities

Context window

1M tokens

Context window

1M tokens

Context window

1M tokens

Privacy

Higher boundary is stricter

Anonymous

Venice Anonymous routing

Privacy

Higher boundary is stricter

Anonymous

Venice Anonymous routing

Privacy

Higher boundary is stricter

Anonymous

Venice Anonymous routing

Availability

Available

Availability

Available

Availability

Available

Released

Jun 10, 2026

Released

Apr 23, 2026

Released

Feb 19, 2026

Catalog updated

Oct 22, 2026

Catalog updated

Oct 22, 2026

Catalog updated

Oct 22, 2026

Summary

Claude Fable 5 is Anthropic's Mythos-class model released for general use, built for demanding reasoning and long-horizon agentic work. It takes text and image input and produces text output, with a…

Summary

GPT-5.5 is OpenAI's GPT-5 series model for coding and complex professional work. It takes text and image input and produces text output, with a context window of about 1.05M tokens, up to 128K output…

Summary

Gemini 3.1 Pro Preview is the preview release of Google's Gemini 3.1 Pro, a reasoning model for software engineering and agentic workflows that need precise tool use. It refines the Gemini 3 Pro…

Pricing

Input

Lower is better when units match

$10.00 / M

Input

Lower is better when units match

$5.00 / M

Input

Lower is better when units match

$2.50 / M

Output

Lower is better when units match

$50.00 / M

Output

Lower is better when units match

$30.00 / M

Output

Lower is better when units match

$15.00 / M

Cache read

$1.00 / M

Cache read

$0.50 / M

Cache read

$0.50 / M

Cache write

$12.50 / M

Cache write

—

Cache write

$0.50 / M

Pricing note

USD per 1M tokens from the Venice models API.

Pricing note

USD per 1M tokens from the Venice models API. Prompts over 272,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.

Pricing note

USD per 1M tokens from the Venice models API. Prompts over 200,000 input tokens have a higher long-context rate for the whole request. It is not applied yet; these requests are billed at the standard rate.

Capabilities

Reasoning

Yes

Reasoning

Yes

Reasoning

Yes

Code optimized

Yes

Code optimized

No

Code optimized

No

Streaming

Yes

Streaming

Yes

Streaming

Yes

Tool calling

Yes

Tool calling

Yes

Tool calling

Yes

JSON/schema

Yes

JSON/schema

Yes

JSON/schema

Yes

Vision

Yes

Vision

Yes

Vision

Yes

Web search

Yes

Web search

Yes

Web search

Yes

Prompt caching

Yes

Prompt caching

Yes

Prompt caching

Yes

Routing

Anonrouter hosted

Yes

Anonrouter hosted

Yes

Anonrouter hosted

Yes

Provider direct

Yes

Provider direct

Yes

Provider direct

Yes

Region boundary

No region-specific metadata published.

Region boundary

No region-specific metadata published.

Region boundary

No region-specific metadata published.

“Best” highlights only comparable known values. Route-specific image, video, and audio units are never ranked against per-token pricing.