Compare

Claude Opus 4.8 vs Recraft V4.1 SVG

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 4.8
anthropic/claude-opus-4.8
Recraft V4.1 SVG
recraft/recraftv4-1-vector
Provider
Anthropic
Recraft
Family
Claude 4
Recraft
Modality
text
image
Context window
1,000,000 tok
Max output
128,000 tok
Released
2026-05-28
2026-05-22
License
Proprietary
Proprietary
Input price
$5.00 /1M
Output price
$25.00 /1M
Cache read
$0.500 /1M
Cache write
$6.25 /1M
Per image
$0.080 /img
Tools
yes
Streaming
yes
Vision
yes
JSON mode
yes
Reasoning
yes
Prompt caching
yes
Batch API
yes
Try it
Open in playground →
View model →
Claude Opus 4.8
anthropic/claude-opus-4.8
Full spec →

Claude Opus 4.8 is Anthropic's most capable generally available model, with a step-change improvement in agentic coding over Claude Opus 4.7. It uses adaptive thinking to calibrate reasoning per task and supports a one million token context window at standard pricing.

Strengths
  • Anthropic's most capable model — #1 on the Artificial Analysis Intelligence Index
  • Best computer-use / browser agent tested (84% on Online-Mind2Web)
  • Adaptive thinking — calibrates reasoning depth per task
Use cases
Autonomous coding agentsCodebase-scale migrationsComputer use / browser agentsHigh-stakes reasoning + analysisLong-document work (1M context)
Recraft V4.1 SVG
recraft/recraftv4-1-vector
Full spec →

Generate production-ready SVG vector graphics from text prompts with high aesthetic quality, clean geometry, structured layers, and editable paths.

Strengths
  • Text-to-image generation
  • Creative control
Use cases
Marketing assetsProduct mockupsConcept art

Benchmarks

Claude Opus 4.8
Recraft V4.1 SVG
AA Intelligence Index
61.0
Online-Mind2Web (computer use)
84.0

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

Compare with another

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
Claude Opus 4.8 vs GPT-5.5
anthropic/claude-opus-4.8 · openai/gpt-5.5
Claude Opus 4.8 vs Gemini 2.5 Pro
anthropic/claude-opus-4.8 · google/gemini-2.5-pro
Claude Opus 4.8 vs Kimi-K2.6
anthropic/claude-opus-4.8 · moonshot/kimi-k2.6
Claude Opus 4.8 vs MiniMax M3
anthropic/claude-opus-4.8 · minimax/m3
Claude Opus 4.8 vs Grok 4.20 Multi-Agent
anthropic/claude-opus-4.8 · xai/grok-4.20-multi-agent-0309
Claude Opus 4.8 vs GPT-5.4 Mini
anthropic/claude-opus-4.8 · openai/gpt-5.4-mini
Claude Opus 4.8 vs Qwen 3.5 397B A17B
anthropic/claude-opus-4.8 · alibaba/qwen3.5-397b-a17b
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 4.8
client.chat.completions.create(
    model="anthropic/claude-opus-4.8",
    messages=[{"role":"user","content":"hello"}],
)

# Recraft V4.1 SVG
client.chat.completions.create(
    model="recraft/recraftv4-1-vector",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →