← Model list
Gemini 2.5 Pro
google·google/gemini-2.5-pro·GA·Closed·gemini-pro series
Google's proven reasoning model for coding, math, and multimodal analysis
At a glance
Official price$1.25 / $10.00 per 1M
Cache read $0.125 · Vertex
Lowest paid$0.87 / $7.00
Poe Gateway · 2.9× spread
Context1,048,576
⚠ Providers report 1,000,000–1,065,535; the table below is authoritative
Output limit65,536
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoAudioPDF
Knowledge cutoff2025-01
Released / updated2025-06-17 / 2025-06-17
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence25.9
Value11
Coding33.3
Agentic7.2
Output speed133 tok/s
TTFT20.46 s
Cost per task$0.2164
Value formulaIQ 25.9 ÷ min blended $2.402 = 11
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 29 providers27 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Poe | Gateway | $0.87 | $7.00 | $0.087 | — | 1,065,535 ⚠ | 65,535 | |
| Jiekou.AI | Gateway | $1.13 | $9.00 | — | — | 1,048,576 | 65,535 | |
| NanoGPT | Gateway | $1.25 | $10.00 | $0.125 | $0.375 | 1,048,756 ⚠ | 65,536 | |
| VertexOfficial | First-party | $1.25 tiered >200K: $2.50 | $10.00 | $0.125 | — | 1,048,576 | 65,536 | |
| GoogleOfficial | First-party | $1.25 tiered >200K: $2.50 | $10.00 | $0.125 | — | 1,048,576 | 65,536 | |
| Impossibl | Gateway | $1.25 tiered >200K: $2.50 | $10.00 | $0.125 | — | 1,048,576 | 65,536 | |
| OpenRouter | Gateway | $1.25 tiered >200K: $2.50 | $10.00 | $0.125 | $0.375 | 1,048,576 | 65,536 | |
| Auriko | Gateway | $1.25 tiered >200K: $2.50 | $10.00 | $0.125 | — | 1,048,576 | 65,536 | |
| CrossModel | Gateway | $1.25 tiered >200K: $2.50 | $10.00 | $0.125 | $1.25 | 1,048,576 | 65,536 | |
| Databricks databricks-gemini-2-5-pro | Cloud | $1.25 tiered >200K: $2.50 | $10.00 | $0.125 | — | 1,048,576 | 65,536 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1Poe$430.04
2NanoGPT$615.00
3Vertex · Official$615.00
4Google · Official$615.00
5Impossibl$615.00
6OpenRouter$615.00
Switch to Poe to save $184.96/mo (30%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark4 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 83.1 | percent correct | Source ↗ |
| Artificial Analysis Coding Index | — | 32 | index | Source ↗ |
| SciCode | — | 42.8 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 26.5 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
budget_tokenseffort = noneeffort = loweffort = mediumeffort = higheffort = xhigheffort = maxeffort = minimal
5 / 29 providers expose no reasoning control (reasoning_options: []).
Related models
Gemini 3.5 Live Translate Previewsame series$3.50 / $21.00Gemini 3 Pro Imagesame series$2.00 / $12.00Nano Banana Prosame series$2.00 / $120DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44MiniMax-M3cheaper alternative$0.30 / $1.20
Price historyone sample accumulated per data sync
Input listOutput listMin blended