Compare

Gemini 2.5 Pro vs Gpt-Oss-120b

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Gemini 2.5 Pro
google/gemini-2.5-pro
Gpt-Oss-120b
openai/gpt-oss-120b
Provider
Google
OpenAI
Family
Modality
text
text
Context window
1,000,000 tok
131,072 tok
Max output
65,536 tok
4,096 tok
Released
2026-05-22
2025-08-05
License
Proprietary
Open-weight
Input price
$1.25 /1M
$0.350 /1M
Output price
$10.00 /1M
$0.750 /1M
Tools
yes
Streaming
yes
yes
Vision
JSON mode
yes
Reasoning
Prompt caching
Batch API
Try it
Open in playground →
Open in playground →
Gemini 2.5 Pro
google/gemini-2.5-pro
Full spec →

Google's most capable Gemini 2.5 model with strong reasoning, thinking support, and a 1M token context window.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
Gpt-Oss-120b
openai/gpt-oss-120b
Full spec →

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-120b is for production, general purpose, high reasoning use-cases.

Strengths
  • OpenAI's first open-weight release
  • Strong instruction following
  • Apache-2.0 license
Use cases
General chatOn-prem replacement for closed GPT

Compare with another

Claude Opus 4.8 vs Gemini 2.5 Pro
anthropic/claude-opus-4.8 · google/gemini-2.5-pro
Claude Opus 4.8 vs Gpt-Oss-120b
anthropic/claude-opus-4.8 · openai/gpt-oss-120b
Gemini 3.1 Pro vs Gemini 2.5 Pro
google/gemini-3.1-pro · google/gemini-2.5-pro
Gemini 3.1 Pro vs Gpt-Oss-120b
google/gemini-3.1-pro · openai/gpt-oss-120b
Claude Sonnet 4.6 vs Gemini 2.5 Pro
anthropic/claude-sonnet-4.6 · google/gemini-2.5-pro
Claude Sonnet 4.6 vs Gpt-Oss-120b
anthropic/claude-sonnet-4.6 · openai/gpt-oss-120b
GPT-5.5 vs Gemini 2.5 Pro
openai/gpt-5.5 · google/gemini-2.5-pro
GPT-5.5 vs Gpt-Oss-120b
openai/gpt-5.5 · openai/gpt-oss-120b
Gemini 2.5 Pro vs Kimi-K2.6
google/gemini-2.5-pro · moonshot/kimi-k2.6
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

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

# Gpt-Oss-120b
client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →