OpenAI
GPT-5.5
OpenAI's latest frontier flagship model for complex professional work, coding, and agentic workflows, with 1M+ context, text and image input, and text output
Context Length1,050,000 tokens
Max Output128K tokens
Model TypeLarge Language Model (LLM)
Pricing & Specs
π° Pricing
Input$5 / M tokens
Output$30 / M tokens
Cache Hit$0.50 / M tokens
βοΈ Specs
Context Length1,050,000 tokens
Max Output128K tokens
Model TypeLarge Language Model (LLM)
API AvailabilitySupports the Responses API, Chat Completions API, and Batch API
MultimodalSupports text and image input, text output
Reasoning EffortSupports none, low, medium (default), high, and xhigh
Caching SupportSupports cached-input pricing
Long-context PricingPrompts over 272K input tokens are priced at 2x input and 1.5x output for the full session
Data ResidencyRegional processing / data residency endpoints carry a 10% uplift
Snapshotgpt-5.5-2026-04-23
Knowledge CutoffDecember 1, 2025
Doc StatusUpdated from OpenAI's official model docs and API pricing page: $5 / 1M input, $0.50 / 1M cached input, $30 / 1M output
API Examples
Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
api_key="your-api-key",
base_url="https://api.xairouter.com/v1"
)
response = client.chat.completions.create(
model="gpt-5.5",
messages=[
{"role": "user", "content": "Summarize this requirement and break it into development tasks"}
]
)
print(response.choices[0].message.content)cURL (OpenAI API)
curl https://api.xairouter.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "gpt-5.5",
"messages": [
{"role": "user", "content": "Summarize this requirement and break it into development tasks"}
]
}'Developer Assist
# Configure ~/.codex/config.toml
cat > ~/.codex/config.toml << 'EOF'
model_provider = "xai"
model = "gpt-5.5"
model_reasoning_effort = "xhigh"
plan_mode_reasoning_effort = "xhigh"
model_reasoning_summary = "none"
model_verbosity = "medium"
model_context_window = 1050000
model_auto_compact_token_limit = 945000
tool_output_token_limit = 6000
approval_policy = "never"
sandbox_mode = "danger-full-access"
suppress_unstable_features_warning = true
[model_providers.xai]
name = "OpenAI"
base_url = "https://api.xairouter.com"
wire_api = "responses"
requires_openai_auth = false
env_key = "XAI_API_KEY"
[features]
multi_agent = true
[agents]
max_threads = 4
max_depth = 1
job_max_runtime_seconds = 1800
EOF
# Set environment variable (add to ~/.bashrc or ~/.zshrc)
export XAI_API_KEY="sk-Xvs..."
# Launch Codex
codex