Gemini 2.5 Pro
google/gemini-2-5-proОт Google · семейство: gemini-pro · выпуск 2025-06-17 · дата знаний: 2025-01
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Возможности
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding100
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)20/20
- Provider availability10/10
Agents100
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output80
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume0/20
Cost efficiency41
- Headline price (log-scaled)36/95
- Has prompt-cache pricing5/5
Long context91
- Context window (100K → 2M)81/90
- Has published price for full window10/10
Vision100
- Accepts image input50/50
- Context window (10K → 1M)30/30
- Has published price10/10
- Provider availability10/10
Production-readiness94
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers4/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $11.25 $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $22.50 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $7.50 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $20.00 $0.02 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $21.00 $0.02 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Детализация цен
Рекомендованная цена от google · gemini-2.5-pro
Самый дешёвый провайдер: poe · $0.870 вход + $7.00 выход
Доступна у 28 провайдеров
| Провайдер | ID модели провайдера | Вход / 1M | Выход / 1M | Контекст | Выпуск |
|---|---|---|---|---|---|
| Google google | gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| Vertex google-vertex | gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| OpenRouter openrouter | google/gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| Vercel AI Gateway vercel | google/gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| Requesty requesty | google/gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| Qiniu qiniu-ai | gemini-2.5-pro | Unknown | Unknown | 1.05M | 2025-08-05 |
| 302.AI 302ai | gemini-2.5-pro | $1.25 | $10.00 | 1M | 2025-06-17 |
| Cortecs cortecs | gemini-2.5-pro | $1.65 | $11.02 | 1.05M | 2025-03-20 |
| Auriko auriko | gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| AnyAPI anyapi | google/gemini-2.5-pro | Unknown | Unknown | 1.05M | 2025-06-17 |
| ZenMux zenmux | google/gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| Merge Gateway merge-gateway | google/gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| OrcaRouter orcarouter | google/gemini-2.5-pro | $2.50 | $15.00 | 1.05M | 2025-06-17 |
| Helicone helicone | gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| NEAR AI Cloud nearai | google/gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| LLM Gateway llmgateway | gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| Abacus abacus | gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-03-25 |
| SAP AI Core sap-ai-core | gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-03-25 |
| Poe poe | google/gemini-2.5-pro | $0.870 | $7.00 | 1.07M | 2025-02-05 |
| Perplexity Agent perplexity-agent | google/gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-03-20 |
| Kilo Gateway kilo | google/gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-03-20 |
| FrogBot frogbot | gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-03-20 |
| Jiekou.AI jiekou | gemini-2.5-pro | $1.13 | $9.00 | 1.05M | 2026-01 |
| FastRouter fastrouter | google/gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| AIHubMix aihubmix | gemini-2.5-pro | $1.25 | $10.00 | 1.05M | 2025-03-20 |
| NanoGPT nano-gpt | gemini-2.5-pro | $2.50 | $10.00 | 1.05M | 2025-06-05 |
| Neon neon | gemini-2-5-pro | $1.25 | $10.00 | 1.05M | 2025-06-17 |
| GitHub Copilot github-copilot | gemini-2.5-pro | $1.25 | $10.00 | 128K | 2025-06-17 |
Расхождения данных между провайдерами
- context_window varies: 1000000, 1048000, 1048576, 1048756, 1065535, 128000
- release_date varies (span 330d): 2025-02-05, 2025-03-20, 2025-03-25, 2025-06-05, 2025-06-17, 2025-08-05, 2026-01
- modalities varies across offerings
Провайдеры сообщают разные значения для этой модели. Сводка выше использует репрезентативного провайдера; детали — в таблице.
Frequently asked questions
How much does Gemini 2.5 Pro cost?
Gemini 2.5 Pro costs $1.25 per 1M input tokens and $10.00 per 1M output tokens, sourced from google. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Gemini 2.5 Pro?
Gemini 2.5 Pro has a context window of 1.05M tokens, with a max output of 66K tokens per reply. This is the total combined size of prompt + completion.
Does Gemini 2.5 Pro support tool calling?
Yes. Gemini 2.5 Pro supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Gemini 2.5 Pro support structured output / JSON mode?
Yes. Gemini 2.5 Pro supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can Gemini 2.5 Pro accept image input?
Yes. Gemini 2.5 Pro accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check Google's docs for the exact rule.
Is Gemini 2.5 Pro open-weight?
No. Gemini 2.5 Pro is a proprietary model — only Google (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.
What are the best alternatives to Gemini 2.5 Pro?
If Gemini 2.5 Pro doesn't fit, consider Gemini 2.5 Flash, Gemma 4 31B IT, Gemini 3 Flash Preview. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
Direct comparisons
- Gemini 2.5 Pro vs GPT-5flagship
- Gemini 2.5 Pro vs Claude Sonnet 4.5 (latest)flagship
- Gemini 2.5 Pro vs Claude Sonnet 4.5 (latest)long-context
More Google models
- Gemini 2.5 Flash$0.30 in / $2.50 out
- Gemma 4 31B IT$0.10 in / $0.30 out
- Gemini 3 Flash Preview$0.50 in / $3.00 out
- Gemini 3.1 Pro Preview$2.00 in / $12.00 out
- Gemini 2.5 Flash-Lite$0.10 in / $0.40 out
Capability lists this model is in
Последнее обновление:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.