Compare

Claude Haiku 5.5 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 Haiku 5.5
anthropic/claude-haiku-5.5
O3
openai/o3
Provider
Anthropic
OpenAI
Family
Claude 4
o-series
Modality
text
text
Context window
1,000,000 tok
200,000 tok
Max output
128,000 tok
100,000 tok
Released
2026-10-12
2026-05-22
License
Proprietary
Open-weight
Input price
$0.100 /1M
$2.00 /1M
Output price
$0.500 /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 Haiku 5.5
anthropic/claude-haiku-5.5
Full spec →

Claude Haiku 5.5 is a fast, cost-efficient model for high-volume, latency-sensitive tasks such as classification, extraction, routing, and subagent work.

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

Gemini 4 Argon vs Claude Haiku 5.5
google/gemini-4-argon · anthropic/claude-haiku-5.5
Gemini 4 Argon vs O3
google/gemini-4-argon · openai/o3
Claude Sonnet 5.5 vs Claude Haiku 5.5
anthropic/claude-sonnet-5.5 · anthropic/claude-haiku-5.5
Claude Sonnet 5.5 vs O3
anthropic/claude-sonnet-5.5 · openai/o3
GPT-6.1 Sol vs Claude Haiku 5.5
openai/gpt-6.1-sol · anthropic/claude-haiku-5.5
GPT-6.1 Sol vs O3
openai/gpt-6.1-sol · openai/o3
Claude Opus 5.5 vs Claude Haiku 5.5
anthropic/claude-opus-5.5 · anthropic/claude-haiku-5.5
Claude Opus 5.5 vs O3
anthropic/claude-opus-5.5 · openai/o3
Grok 4.7 vs Claude Haiku 5.5
xai/grok-4.7 · anthropic/claude-haiku-5.5
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 Haiku 5.5
client.chat.completions.create(
    model="anthropic/claude-haiku-5.5",
    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 →