Gemini 2.5 Pro

Google AI chat

Gemini 2.5 Pro is a Google AI chat model.It supports a 1,048,576-token context windowwith up to 65,535 output tokens.Input is priced at $1.25/M tokens and output at $10.00/M tokens. Capabilities include function calling, vision, reasoning, audio input. Route Gemini 2.5 Pro via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.

Pricing source: litellm Last verified: May 12, 2026 View source ↗
Cost calculator

Estimate Gemini 2.5 Pro spend

Pick a workload, fine-tune the sliders, and see the monthly bill.

~3K in / ~400 out · 5K req/day
3,000
01,048,576
400
065,535
5,000
01,000,000
cached @ $0.1250/M
Per request
$0.007750
in $0.003750 · out $0.004000
Per day
$38.75
5,000 requests
Per month
$1,179
152,188 requests

Estimate uses $1.25/M input · $10.00/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.

Pricing

Per-token rates, expressed in USD per 1M tokens. Verified May 12, 2026.

Input $1.25/M
Output $10.00/M
Cached input $0.125/M

Limits

Context window
1,048,576 tokens
Max input
1,048,576 tokens
Max output
65,535 tokens
Modalities
vision, audio_in, pdf, video, text

Capabilities

  • Function calling ✓ supported
  • Parallel tool calls — not advertised
  • Vision input ✓ supported
  • Audio input ✓ supported
  • Audio output — not advertised
  • PDF input ✓ supported
  • Streaming ✓ supported
  • Structured output ✓ supported
  • Prompt caching ✓ supported
  • Reasoning ✓ supported

Where it's strong

  • +pricing — cheaper than 79% of priced chat models on Future AGI
  • +long-context tasks — context window in the top 2% of peers
  • +audio input — only 4% of chat models on Future AGI advertise this
  • +PDF input — only 16% of chat models on Future AGI advertise this
  • +prompt caching — only 23% of chat models on Future AGI advertise this

Watch out for

  • No major caveats flagged from public spec.

Benchmark scores

Reported public benchmark numbers. Each row links to the source.

MATH-500math· 0-shot CoT
Captured May 12, 2026
HumanEvalcode· 0-shot
Captured May 12, 2026
Chatbot Arena ELOgeneral· overall
Captured May 12, 2026
AIME 2025math· 0-shot
Captured May 12, 2026
MMLU-Proreasoning· 0-shot
Captured May 12, 2026
GPQA Diamondreasoning· 0-shot CoT
Captured May 12, 2026
MMMUmultimodal· 0-shot
Captured May 12, 2026
BFCL v3agent· multi-turn
Captured May 12, 2026
Aider Polyglotcode· pass@1
Captured May 12, 2026
LiveCodeBenchcode· pass@1
Captured May 12, 2026
SWE-bench Verifiedagent· agentic
Captured May 12, 2026
Humanity's Last Examreasoning· 0-shot
Captured May 12, 2026
Try it

Call Gemini 2.5 Pro via Agent Command Center

One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.

SDK
Native Future AGI client (agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.
# Gemini 2.5 Pro via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC

client = AgentCC(
    api_key=os.environ["AGENTCC_API_KEY"],   # from app.futureagi.com → Settings → API Keys
    base_url="https://gateway.futureagi.com/v1",
)

resp = client.chat.completions.create(
    model="google/gemini-2-5-pro",
    messages=[{"role": "user", "content": "Hello, Gemini 2.5 Pro!"}],
)

print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")

# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
    model="google/gemini-2-5-pro",
    messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost:   ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache:  ", raw.headers.get("x-agentcc-cache"))
Set AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗
Advanced: fallback + cache config (YAML)
strategy: cost-optimized
targets:
  - model: gemini-2-5-pro
    provider: google
    weight: 80
fallbacks:
  - model: claude-opus-4-6
    provider: azure-ai-foundry
  - model: claude-opus-4-6-20260205
    provider: anthropic
guardrails: [pii, prompt-injection, secrets]
cache: { exact: true, semantic: true }

Same model on other providers

gemini-2-5-pro is also available via 2 other routes. Pricing, regions, and capabilities can differ — compare before routing production traffic.

ProviderInput / 1MOutput / 1MVerified
Google Vertex AI$1.25/M$10.00/MMay 12, 2026
GitHub CopilotMay 12, 2026

Compare with similar models

Grouped by Chatbot Arena tier (Gemini 2.5 Pro sits at 1448 ELO).

FAQ

How much does Gemini 2.5 Pro cost?

Input is priced at $1.25 per 1M tokens and output at $10.00 per 1M tokens (Google AI, last verified May 12, 2026).

What is the context window of Gemini 2.5 Pro?

Gemini 2.5 Pro supports a 1,048,576-token context window with up to 65,535 output tokens.

Does Gemini 2.5 Pro support function calling?

Yes — Gemini 2.5 Pro supports function (tool) calling.

Is Gemini 2.5 Pro good for production?

Gemini 2.5 Pro is well-suited for pricing — cheaper than 79% of priced chat models on Future AGI and long-context tasks — context window in the top 2% of peers.

How can I route to Gemini 2.5 Pro with fallback?

Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.

Useful links for Gemini 2.5 Pro

Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.