Compare

Claude Sonnet 4.6 vs Gemini 3.1 Pro

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 Sonnet 4.6
anthropic/claude-sonnet-4.6
Gemini 3.1 Pro
google/gemini-3.1-pro
Provider
Anthropic
Google
Family
Claude 4
Gemini 3
Modality
text
text
Context window
200,000 tok
1,000,000 tok
Max output
128,000 tok
65,536 tok
Released
2026-05-22
2026-05-22
License
Proprietary
Proprietary
Input price
$3.00 /1M
$2.00 /1M
Output price
$15.00 /1M
$12.00 /1M
Cache read
$0.300 /1M
$0.200 /1M
Cache write
$3.75 /1M
Tools
yes
yes
Streaming
yes
yes
Vision
yes
yes
JSON mode
yes
yes
Reasoning
yes
yes
Prompt caching
yes
yes
Batch API
Try it
Open in playground →
Open in playground →
Claude Sonnet 4.6
anthropic/claude-sonnet-4.6
Full spec →

Claude Sonnet 4.6 is Anthropic's latest balanced model offering strong coding, reasoning, and agentic capabilities with improved instruction following.

Strengths
  • Best cost/quality ratio for agentic workloads
  • Low latency
  • Strong tool calling
Use cases
Production agentsRAGCustomer-facing chatData extraction
Gemini 3.1 Pro
google/gemini-3.1-pro
Full spec →

Google's most intelligent Gemini model with improved reasoning, a medium thinking level, and a 1M token context window.

Strengths
  • 2M-token context
  • Native video + audio input
  • Cheapest long-context reasoning
Use cases
Video understandingVery long-document RAGCodebase-scale reasoning

Benchmarks

Claude Sonnet 4.6
Gemini 3.1 Pro
HumanEval
93.4
Long-Context
94.2
MMLU
87.2
89.6
SWE-Bench
62.1

Source: each provider's published benchmarks. Higher is better. Run an eval to compare on your own data.

Compare with another

Gemini 3.1 Pro vs Claude Opus 4.7
google/gemini-3.1-pro · anthropic/claude-opus-4.7
Gemini 3.1 Pro vs GPT-5.4
google/gemini-3.1-pro · openai/gpt-5.4
Claude Sonnet 4.6 vs GPT-5.4
anthropic/claude-sonnet-4.6 · openai/gpt-5.4
Claude Sonnet 4.6 vs GPT-5.4 Mini
anthropic/claude-sonnet-4.6 · openai/gpt-5.4-mini
Gemini 3.1 Pro vs Kimi-K2.6
google/gemini-3.1-pro · moonshot/kimi-k2.6
Claude Sonnet 4.6 vs Llama-4-Scout-17b-16e-Instruct
anthropic/claude-sonnet-4.6 · meta/llama-4-scout-17b-16e-instruct
Claude Sonnet 4.6 vs O4-Mini
anthropic/claude-sonnet-4.6 · openai/o4-mini
Claude Opus 4.8 vs Gemini 3.1 Pro
anthropic/claude-opus-4.8 · google/gemini-3.1-pro
Claude Opus 4.8 vs Claude Sonnet 4.6
anthropic/claude-opus-4.8 · anthropic/claude-sonnet-4.6
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-...",
)

# Claude Sonnet 4.6
client.chat.completions.create(
    model="anthropic/claude-sonnet-4.6",
    messages=[{"role":"user","content":"hello"}],
)

# Gemini 3.1 Pro
client.chat.completions.create(
    model="google/gemini-3.1-pro",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →