STEELENGINE / MODELS
Every model your agents need, priced and ready.
Compare list pricing, context windows, and capabilities for the models you can run in SteelEngine workflows and agents. One catalog, kept current from the platform itself.
PRICING
USD PER 1M TOKENS
DETAILS
CONTEXT, OUTPUT, CAPABILITIES
SOURCE
STEELENGINE MODEL CATALOG
MODEL PROVIDERS
Start with the providers your team already runs on.
Each provider page lists its models with list pricing, context limits, and the settings SteelEngine exposes for them.
MODEL LIBRARY
Find the right model.
Filter by provider, then open any model for its full price sheet, limits, and supported capabilities.
OpenAI
RECOMMENDED
GPT-6.1 Sol
Mid-priced reasoning model for everyday agent steps that need deliberate thinking. A recommended default among SteelEngine’s OpenAI models. Released Sep 29, 2026.
IN / 1M
$2
OUT / 1M
$10
CONTEXT
1.05M
OpenAI
RECOMMENDED
GPT-6 Sol
Mid-priced reasoning model for everyday agent steps that need deliberate thinking. A recommended default among SteelEngine’s OpenAI models. Released Sep 22, 2026.
IN / 1M
$2
OUT / 1M
$10
CONTEXT
1.05M
OpenAI
RECOMMENDED
GPT-5.6 Sol
Higher-priced reasoning model for complex planning and multi-step agent work. A recommended default among SteelEngine’s OpenAI models.
IN / 1M
$4
OUT / 1M
$20
CONTEXT
1.05M
OpenAI
GPT-6 Astra
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 3, 2026.
IN / 1M
$10
OUT / 1M
$50
CONTEXT
1.05M
OpenAI
GPT-6 Luna
Fast, lower-priced reasoning model for high-volume steps that still benefit from thinking. Reads up to 1.05M tokens of context in one call and writes up to 128k tokens. Released Sep 22, 2026.
IN / 1M
$0.1
OUT / 1M
$0.5
CONTEXT
1.05M
OpenAI
GPT-5.6 Terra
Mid-priced reasoning model for everyday agent steps that need deliberate thinking. Reads up to 1.05M tokens of context in one call and writes up to 128k tokens.
IN / 1M
$2
OUT / 1M
$12
CONTEXT
1.05M
OpenAI
GPT-5.6 Luna
Fast, lower-priced reasoning model for high-volume steps that still benefit from thinking. Reads up to 1.05M tokens of context in one call and writes up to 128k tokens. Released Jul 9, 2026.
IN / 1M
$0.2
OUT / 1M
$1.2
CONTEXT
1.05M
OpenAI
GPT-5.5 Pro
Among the highest-priced models in the 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. Released Apr 23, 2026.
IN / 1M
$30
OUT / 1M
$180
CONTEXT
1.05M
OpenAI
GPT-5.5
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 Apr 23, 2026.
IN / 1M
$5
OUT / 1M
$30
CONTEXT
1.05M
OpenAI
GPT-5.4 Pro
Among the highest-priced models in the 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
$30
OUT / 1M
$180
CONTEXT
1.05M
OpenAI
GPT-5.4
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.
IN / 1M
$2.5
OUT / 1M
$15
CONTEXT
1.05M
OpenAI
GPT-5.4 Mini
Fast, lower-priced reasoning model for high-volume steps that still benefit from thinking. Handles 400k tokens of context and writes up to 128k tokens. The mini size in its family.
IN / 1M
$0.75
OUT / 1M
$4.5
CONTEXT
400k
OpenAI
GPT-5.4 Nano
Fast, lower-priced reasoning model for high-volume steps that still benefit from thinking. Handles 400k tokens of context and writes up to 128k tokens. The nano size in its family.
IN / 1M
$0.2
OUT / 1M
$1.25
CONTEXT
400k
OpenAI
GPT-5.3 Codex
Coding model for writing, reviewing, and refactoring code in agent workflows. Handles 400k tokens of context and writes up to 128k tokens.
IN / 1M
$1.75
OUT / 1M
$14
CONTEXT
400k
OpenAI
GPT-5.2 Pro
Higher-effort variant for problems where answer quality matters more than latency or cost. Handles 400k tokens of context and writes up to 128k tokens.
IN / 1M
$21
OUT / 1M
$168
CONTEXT
400k
OpenAI
GPT-5.2
Mid-priced reasoning model for everyday agent steps that need deliberate thinking. Handles 400k tokens of context and writes up to 128k tokens.
IN / 1M
$1.75
OUT / 1M
$14
CONTEXT
400k
OpenAI
GPT-5.1
Mid-priced reasoning model for everyday agent steps that need deliberate thinking. Handles 400k tokens of context and writes up to 128k tokens.
IN / 1M
$1.25
OUT / 1M
$10
CONTEXT
400k
OpenAI
GPT-5 Pro
Higher-effort variant for problems where answer quality matters more than latency or cost. Handles 400k tokens of context and writes up to 272k tokens.
IN / 1M
$15
OUT / 1M
$120
CONTEXT
400k
OpenAI
GPT-5
Mid-priced reasoning model for everyday agent steps that need deliberate thinking. Handles 400k tokens of context and writes up to 128k tokens.
IN / 1M
$1.25
OUT / 1M
$10
CONTEXT
400k
OpenAI
GPT-5 Mini
Fast, lower-priced reasoning model for high-volume steps that still benefit from thinking. Handles 400k tokens of context and writes up to 128k tokens. The mini size in its family.
IN / 1M
$0.25
OUT / 1M
$2
CONTEXT
400k
OpenAI
GPT-5 Nano
The lowest-cost model in the OpenAI lineup, for high-volume steps that still benefit from thinking. Handles 400k tokens of context and writes up to 128k tokens.
IN / 1M
$0.05
OUT / 1M
$0.4
CONTEXT
400k
OpenAI
o3
Lower-priced reasoning model for high-volume steps that still benefit from thinking. Handles 200k tokens of context and writes up to 100k tokens.
IN / 1M
$2
OUT / 1M
$8
CONTEXT
200k
OpenAI
GPT-4.1
Lower-priced model for high-volume classification, extraction, and routing. Reads up to 1.05M tokens of context in one call and writes up to 33k tokens.
IN / 1M
$2
OUT / 1M
$8
CONTEXT
1.05M
OpenAI
GPT-4.1 Mini
Fast, lower-priced model for high-volume classification, extraction, and routing. Reads up to 1.05M tokens of context in one call and writes up to 33k tokens.
IN / 1M
$0.4
OUT / 1M
$1.6
CONTEXT
1.05M
BUILD WITH ANY MODEL
Put the right model to work.
Route each step of a workflow to the model that fits it, with approvals, guardrails, and a full audit trail around every call.