Compare

Claude Fable 5 vs O3

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 Fable 5
anthropic/claude-fable-5
O3
openai/o3
Provider
Anthropic
OpenAI
Family
o-series
Modality
text
text
Context window
1,000,000 tok
200,000 tok
Max output
128,000 tok
100,000 tok
Released
2026-06-09
2026-05-22
License
Proprietary
Open-weight
Input price
$10.00 /1M
$2.00 /1M
Output price
$50.00 /1M
$8.00 /1M
Tools
yes
Streaming
yes
yes
Vision
yes
JSON mode
yes
Reasoning
Prompt caching
Batch API
Try it
Open in playground →
Open in playground →
Claude Fable 5
anthropic/claude-fable-5
Full spec →

Claude Fable 5 is Anthropic's most capable widely released model, built for the most demanding reasoning and long-horizon agentic work. Adaptive thinking is always on, and the model supports a 1M token context window with up to 128k output tokens per request.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
O3
openai/o3
Full spec →

o3 is OpenAI’s general-purpose reasoning model, balancing strong analytical performance with reasonable latency and cost.

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

Compare with another

Grok 4.6 vs Claude Fable 5
xai/grok-4.6 · anthropic/claude-fable-5
Grok 4.6 vs O3
xai/grok-4.6 · openai/o3
Claude Opus 5 vs Claude Fable 5
anthropic/claude-opus-5 · anthropic/claude-fable-5
Claude Opus 5 vs O3
anthropic/claude-opus-5 · openai/o3
Qwen3.8 Max vs Claude Fable 5
alibaba/qwen3.8-max · anthropic/claude-fable-5
Qwen3.8 Max vs O3
alibaba/qwen3.8-max · openai/o3
DeepSeek V4 Pro vs Claude Fable 5
deepseek/deepseek-v4-pro · anthropic/claude-fable-5
DeepSeek V4 Pro vs O3
deepseek/deepseek-v4-pro · openai/o3
Kimi K3 vs Claude Fable 5
moonshot/kimi-k3 · anthropic/claude-fable-5
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 Fable 5
client.chat.completions.create(
    model="anthropic/claude-fable-5",
    messages=[{"role":"user","content":"hello"}],
)

# O3
client.chat.completions.create(
    model="openai/o3",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →