Claude Opus 5.5 vs Gemini 3.1 Pro (Preview)

Claude Opus 5.5: $4.00 input and $20 output per million tokens. Gemini 3.1 Pro (Preview): $2.00 input and $12 output per million tokens. The cheaper choice depends on your input-to-output ratio; a model can have a lower input rate but a higher output rate.

For an example workload of 20 million input tokens and 5 million output tokens per month: Claude Opus 5.5: $180. Gemini 3.1 Pro (Preview): $100. These are token-only estimates using the displayed rates, without caching discounts, additional tool charges or taxes. Actual bills depend on usage and endpoint pricing.

Claude Opus 5.5: 1M tokens of context; maximum output 128K tokens. Gemini 3.1 Pro (Preview): 1M tokens of context; maximum output 66K tokens. Context capacity and maximum output are separate limits. A larger context window allows more material in a request but does not guarantee more accurate answers.

Claude Opus 5.5: Artificial Analysis SciCode 66.9%. Gemini 3.1 Pro (Preview): Artificial Analysis SciCode 58.7%. Compare coding results within the same evaluation, then test representative tasks from your own codebase. A missing score is not a zero, and a single benchmark does not establish the best model for every programming task.

These evaluations measure different tasks and use different scales. Arena Elo and DesignArena ratings must remain separate, as must Artificial Analysis Intelligence Index and MMLU-Pro. Compare models within the same evaluation rather than combining scores. Missing results are marked Not listed, not treated as measured zeroes.

Claude Opus 5.5: Artificial Analysis output speed 91 tokens/s; time to first token 0.76 seconds. Gemini 3.1 Pro (Preview): Artificial Analysis output speed 120 tokens/s; time to first token 25.66 seconds. Output speed measures generation throughput, while time to first token measures the initial wait. Real-world latency also depends on the API provider, request size and load; missing measurements cannot establish a speed winner.

Claude Opus 5.5: listed input formats: text, image, file; output formats: text. Gemini 3.1 Pro (Preview): listed input formats: audio, file, image, text, video; output formats: text. Input and output support are different capabilities: accepting an image does not mean a model generates images. Confirm formats and file limits for the endpoint you plan to use.

Claude Opus 5.5: listed features: Function calling, Structured outputs, JSON mode, Reasoning, Prompt caching. Gemini 3.1 Pro (Preview): listed features: Function calling, Structured outputs, JSON mode, Reasoning, Deterministic seed, Prompt caching. Only recorded capabilities are shown; an unlisted feature is not proof that it is unsupported. Availability can vary by API provider, so confirm tool calling and JSON schema support for your chosen endpoint.

Claude Opus 5.5: cached input price $0.20 per million tokens. Gemini 3.1 Pro (Preview): cached input price $0.20 per million tokens. Caching may reduce charges for eligible repeated input when supported by the endpoint. A listed cached rate does not guarantee every request qualifies; cache duration, minimum token counts and any write charges depend on the provider.

Claude Opus 5.5: catalog status active; API identifier claude-opus-5.5; listed API hosts Amazon Bedrock, Azure, Google, Claude Platform on AWS, Anthropic. Gemini 3.1 Pro (Preview): catalog status active; API identifier gemini-3.1-pro-preview; listed API hosts Google, Google AI Studio. Catalog status is not a live availability check. Before integrating, verify the provider's documentation, endpoint access, rate limits, regional availability and data-handling terms.