o3
o3 is an Azure OpenAI model available in SteelEngine. It supports a 200k token context window. Pricing starts at $2/1M input tokens and $8/1M output tokens. Key capabilities include Tool choice, Structured outputs, Reasoning low, medium, high.
Mid-priced reasoning model for everyday agent steps that need deliberate thinking. Handles 200k tokens of context and writes up to 100k tokens.
INPUT / 1M
$2
CACHED INPUT / 1M
$0.5
OUTPUT / 1M
$8
CONTEXT WINDOW
200k
MAX OUTPUT
100k
PRICING
What o3 costs to run.
List prices in USD per 1M tokens. Cached input applies when a request reuses a prompt the provider has already cached.
01 / INPUT
$2
per 1M input tokens
02 / CACHED INPUT
$0.5
per 1M cached input tokens
03 / OUTPUT
$8
per 1M output tokens
LONG CONTEXT
SUPPORTED CAPABILITIES
What o3 supports.
Capabilities show up as model settings on SteelEngine workflow blocks and agents, so teams can tune each step without changing providers.
CAPABILITIES
Tool choice, Structured outputs, Reasoning low, medium, high, Max output 100k, Image input
CONTEXT WINDOW
200k
MAX OUTPUT TOKENS
100k
MODEL ID
azure/o3
PROVIDER
Azure OpenAI
MORE MODELS
More from Azure OpenAI
Compare nearby options from the same provider before you pick a default for your workflow.
Azure OpenAI
GPT-6 Astra
The highest-priced model in the Azure OpenAI lineup, for the hardest reasoning and planning work. Reads up to 1.05M tokens of context in one call and writes up to 128k tokens.
IN / 1M
$10
OUT / 1M
$50
CONTEXT
1.05M
Azure OpenAI
GPT-6.1 Sol
Higher-priced reasoning model for complex planning and multi-step agent work. Reads up to 1.05M tokens of context in one call and writes up to 128k tokens. Released Sep 29, 2026.
IN / 1M
$2
OUT / 1M
$10
CONTEXT
1.05M
Azure OpenAI
GPT-6 Sol
Higher-priced reasoning model for complex planning and multi-step agent work. Reads up to 1.05M tokens of context in one call and writes up to 128k tokens. Released Sep 22, 2026.
IN / 1M
$2
OUT / 1M
$10
CONTEXT
1.05M
BUILD WITH STEELENGINE
Put o3 to work.
Use this model in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.