Compare

GPT-6 Astra vs Claude Sonnet 5

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
GPT-6 Astra
openai/gpt-6-astra
Claude Sonnet 5
anthropic/claude-sonnet-5
Provider
OpenAI
Anthropic
Family
Claude 4
Modality
text
text
Context window
1,050,000 tok
1,000,000 tok
Max output
128,000 tok
128,000 tok
Released
2026-09-10
2026-07-07
License
Open-weight
Proprietary
Input price
$10.00 /1M
$2.00 /1M
Output price
$50.00 /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 →
GPT-6 Astra
openai/gpt-6-astra
Full spec →

GPT-6 Astra is OpenAI's most capable model, built for complex reasoning, coding, computer use, research, and document creation.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
Claude Sonnet 5
anthropic/claude-sonnet-5
Full spec →

Claude Sonnet 5 is Anthropic's most agentic Sonnet model yet, built for coding, tool use, reasoning, and long-horizon professional work at lower cost than Opus-class models.

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

Compare with another

GPT-6 Astra vs Claude Fable 5.1
openai/gpt-6-astra · anthropic/claude-fable-5.1
GPT-6 Astra vs Gemini 3.8 Flash
openai/gpt-6-astra · google/gemini-3.8-flash
GPT-6 Astra vs Claude Opus 5
openai/gpt-6-astra · anthropic/claude-opus-5
GPT-6 Astra vs Glm-5.3
openai/gpt-6-astra · zai-org/glm-5.3
GPT-6 Astra vs Grok 4.6
openai/gpt-6-astra · xai/grok-4.6
GPT-6 Astra vs Qwen3.8 Max
openai/gpt-6-astra · alibaba/qwen3.8-max
GPT-6 Astra vs Kimi K3
openai/gpt-6-astra · moonshot/kimi-k3
GPT-6 Astra vs Qwen3.6 Plus
openai/gpt-6-astra · alibaba/qwen3.6-plus
GPT-6 Astra vs GPT-5.6 Sol
openai/gpt-6-astra · openai/gpt-5.6-sol
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-...",
)

# GPT-6 Astra
client.chat.completions.create(
    model="openai/gpt-6-astra",
    messages=[{"role":"user","content":"hello"}],
)

# Claude Sonnet 5
client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →