Chat model
gpt-5.3-codex-spark
gpt-5.3-codex-spark is a chat model available through the LLM7 API. It supports text input, tool calling, streaming, JSON mode, reasoning. It provides a 400,000 tokens context window. Current pricing is available below.
gpt-5.3-codex-sparkCurrent LLM7 pricing
Simple, pay-as-you-go pricing
Checking current pricing…
Capability scores
AI-estimated ratings on 30 criteria from head-to-head comparisons against 86 other text models in the LLM7 catalog, judged by TypeSafe Jev from public information (2026-10-20). Each score is the win rate against the field, relative to the strongest model for that criterion (100%). Not a benchmark.
Below 50%50–79%80–94%95%+
Overall score
71%
Moderate
Knowledge & reasoning
- General knowledge73%
- Logical reasoning72%
- Mathematics78%
- Scientific and technical depth74%
- Planning and task decomposition73%
Coding & tools
- Code generation100%
- Debugging and code review100%
- Agentic coding94%
- Tool and function calling79%
- SQL and query writing96%
Writing & language
- Creative writing60%
- Professional writing66%
- Conversational quality65%
- Multilingual ability61%
- Translation67%
- Summarization57%
Data & professional work
- Data analysis70%
- Professional domains66%
- Information extraction70%
- Classification and labeling74%
- Long-context handling54%
Reliability & control
- Instruction following71%
- Structured output81%
- Factual accuracy65%
- Safety and alignment63%
- Steerability69%
- Output consistency78%
Speed, cost & vision
- Response speed43%
- Cost efficiency52%
- Image understandingNo image input
Start building
A verified request for this exact model. Add your API key and run it.
curl https://api.llm7.io/v1/chat/completions \
-H "Authorization: Bearer $LLM7_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.3-codex-spark",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'