Compare model

google / Chat

Gemini 2.5 Pro

google/gemini-2.5-pro

Strong multimodal reasoning

Catalog status

Enabled

Research checked

2026-10-06

Price / performance

What it costs to get this result

GPQA Diamond · Source-reported results, not a composite ranking. Prices use the average of TokenBazaar input and output rates per million tokens; actual spend depends on usage. Test configurations differ.

Gemini 2.5 Pro85.3% · 12 sourced models

Blended price / 1M tokens · log scale

● Current model● Other modelsDashed line: price/score frontier among plotted models
Compare sourced models on this benchmark

Benchmark results

6 reported results

Results are source-attributed, not TokenBazaar measurements. Different tests and thinking variants are not interchangeable.

6 of 6 results

GPQA Diamond

Reasoning · Third-party report

Test conditions and source

Official Google-reported score at launch (Gemini 2.5 Pro Experimental, Mar 2025); single-attempt/pass@1 methodology per Gemini technical report conventions. Published source text: GPQA Diamond | Reasoning | 85.3% | accuracy | Official | Mar 25, 2025

Tested model: google/gemini-2.5-pro

evals.report – Gemini 2.5 Pro benchmark scores (sourced from Google's official Mar 25, 2025 launch materials) · Checked 2026-10-06

85.3%

Humanity's Last Exam

Reasoning · Third-party report

Test conditions and source

Official Google-reported score, no tools, Mar 2025 launch. Published source text: Humanity's Last Exam | Reasoning | 21.64% | accuracy | Official | Mar 25, 2025

Tested model: google/gemini-2.5-pro

evals.report – Gemini 2.5 Pro benchmark scores · Checked 2026-10-06

21.64%

SWE-bench Verified

Coding · Third-party report

Test conditions and source

Official Google-reported single-attempt agentic coding score, Mar 2025 launch. Published source text: SWE-bench Verified | Coding | 57.6% | % resolved | Official | Mar 25, 2025

Tested model: google/gemini-2.5-pro

evals.report – Gemini 2.5 Pro benchmark scores · Checked 2026-10-06

57.6%

AIME 2025 (OTIS Mock)

Math · Third-party report

Test conditions and source

Official Google-reported score, no tools, Mar 2025 launch. Published source text: AIME (OTIS Mock) | Reasoning | 84.2% | accuracy | Official | Mar 25, 2025

Tested model: google/gemini-2.5-pro

evals.report – Gemini 2.5 Pro benchmark scores · Checked 2026-10-06

84.2%

LMArena Elo

General · Third-party report

Test conditions and source

Human-preference blind evaluation, LMArena leaderboard, Mar 2025. Published source text: LMArena | Chat preference | 1457 | source-defined rating | Official | Mar 25, 2025

Tested model: google/gemini-2.5-pro

evals.report – Gemini 2.5 Pro benchmark scores · Checked 2026-10-06

1457elo

Artificial Analysis Intelligence Index

General · Third-party report

Test conditions and source

Artificial Analysis Intelligence Index v4.3.2 (current composite methodology as re-scored on AA's exact-model page, default reasoning effort), not the original v1 score at launch. Published source text: Gemini 2.5 Pro scores 16 on the Artificial Analysis Intelligence Index

Tested model: google/gemini-2.5-pro

Artificial Analysis – Gemini 2.5 Pro model page · Checked 2026-10-06

16index

Model specifications

Input token limit

1.05M

Published provider limit

Maximum output

65.54K

Published provider limit

Knowledge cutoff

January 2025

Upstream model

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Text
Image
Audio
Video

Output

Text
Exact model ID
google/gemini-2.5-pro
Model type
Chat
Input token limit
1,048,576 tokens
Maximum output
65,536 tokens
Knowledge cutoff
January 2025

Input token limits describe provider input capacity. Published provider limits are not independently tested TokenBazaar request limits.

Versions and thinking levels

One enabled version is currently listed for this model.

Gemini 2.5 ProSelected₹60.00 in / ₹480.00 out per 1M tokens

Features and tool support

TokenBazaar’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Reasoning configuration

No independent reasoning-mode guarantee is recorded for this exact model.

See enabled versions and provider sources for supported controls.

Coding and agent workflows

Text/code generation and customer-managed tool loops.

Coding benchmark results do not establish a hosted terminal, sandbox, autonomous browser or guaranteed task success.

Streaming answers

Available

Incremental text through TokenBazaar’s chat endpoint; Claude also has native Messages access.

Customer-defined function tools

Limited

Only customer-defined function tools are forwarded. Model/protocol compatibility applies; your application authorizes and executes every tool.

Forced or named tool selection

Limited

The chat route accepts auto, none and required. A named-tool choice is not forwarded; exact model compatibility is not independently tested.

Images and PDFs

Limited

The chat bridge accepts image/PDF content. Provider input modalities are listed separately; file size, content and model limits still apply.

Hosted web search / browsing

Not exposed

No provider-hosted web search or web-fetch tool is exposed. Customer-owned search can be implemented as an authorized function tool.

Hosted code execution / computer use

Not exposed

No built-in execution environment or computer-control tool is provided. Code generation is not code execution.

Hosted file search / persistent assistants

Not exposed

No hosted file-search index, Assistants endpoint or persistent provider agent is exposed.

Batch / fine-tuning / cached-price discounts

Not exposed

No public batch or fine-tuning endpoint, or separate cached-token discount, is offered here.

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenBazaar. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (1)
  • Published provider limits; maximum-capacity requests have not been independently exercised through TokenBaazar. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.