Compare

Claude Opus 5.5 vs Gemini 4 Carbon

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
Claude Opus 5.5
anthropic/claude-opus-5.5
Gemini 4 Carbon
google/gemini-4-carbon
Provider
Anthropic
Google
Family
Claude 4
Modality
text
text
Context window
1,000,000 tok
1,048,576 tok
Max output
128,000 tok
65,536 tok
Released
2026-09-23
2026-11-11
License
Proprietary
Proprietary
Input price
$4.00 /1M
$2.00 /1M
Output price
$20.00 /1M
$10.00 /1M
Tools
yes
—
Streaming
yes
yes
Vision
yes
—
JSON mode
yes
—
Reasoning
yes
—
Prompt caching
—
—
Batch API
—
—
Try it
Open in playground →
Open in playground →
Claude Opus 5.5
anthropic/claude-opus-5.5
Full spec →

Claude Opus 5.5 is Anthropic's model for long-running agentic coding and knowledge work. It combines a one million token context window with adaptive thinking that is always on, a 128K token maximum output, and a medium default effort level.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
Gemini 4 Carbon
google/gemini-4-carbon
Full spec →

Google's most capable Gemini 4 reasoning model, built for complex software engineering, math and science problems, autonomous multi-step agents, and long outputs up to 1M tokens.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows

Compare with another

Gemini 4 Carbon vs Claude Sonnet 5.5
google/gemini-4-carbon · anthropic/claude-sonnet-5.5
Gemini 4 Carbon vs Kimi-K3.1-Pro
google/gemini-4-carbon · moonshot/kimi-k3.1-pro
Gemini 4 Carbon vs Deepseek-V4.1-Flash-1017
google/gemini-4-carbon · deepseek/deepseek-v4.1-flash-1017
Gemini 4 Carbon vs Grok 4.7
google/gemini-4-carbon · xai/grok-4.7
Gemini 4 Carbon vs Qwen3.8-Max
google/gemini-4-carbon · alibaba/qwen3.8-max
Gemini 4 Carbon vs Glm-5.3
google/gemini-4-carbon · zai-org/glm-5.3
Gemini 4 Carbon vs MiniMax M3.1 Flash
google/gemini-4-carbon · minimax/m3.1-flash
Gemini 4 Carbon vs GPT-5.5 Pro
google/gemini-4-carbon · openai/gpt-5.5-pro
Gemini 4 Carbon vs GLM-5.3-Prime
google/gemini-4-carbon · zai-org/glm-5.3-prime
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-...",
)

# Claude Opus 5.5
client.chat.completions.create(
    model="anthropic/claude-opus-5.5",
    messages=[{"role":"user","content":"hello"}],
)

# Gemini 4 Carbon
client.chat.completions.create(
    model="google/gemini-4-carbon",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →