OpenAI models on Felo

Compare the OpenAI models currently available through Felo, including model IDs, pricing, context windows, and Quick Start examples.

models

1.05M

max context

protocols

Flagships first

ModelContextPricing

GPT-5.6 Sol Pro

OpenAIgpt-5.6-sol-pro

The strongest GPT-5.6 route for pro reasoning, difficult coding, complex analysis, and agent workflows that need maximum deliberation.

Maximum reasoningDifficult codingComplex analysisLong-horizon agents

Context

1.05M

Max output

128K

Input tokens

$5.00 /M

Output tokens

$30.00 /M

GPT-5.6 Sol

OpenAIgpt-5.6-sol

The flagship GPT-5.6 tier for complex reasoning, advanced coding, long-context analysis, and high-capability agent workflows.

Flagship reasoningAdvanced codingLong-context analysisAgent orchestration

Context

1.05M

Max output

128K

Input tokens

$5.00 /M

Output tokens

$30.00 /M

GPT-5.6 Terra Pro

OpenAIgpt-5.6-terra-pro

A balanced pro reasoning route for coding agents, complex tool workflows, and production tasks that need stronger step-by-step reasoning.

Pro reasoningComplex codingAgent planningProduction workflows

Context

1.05M

Max output

128K

Input tokens

$2.50 /M

Output tokens

$15.00 /M

GPT-5.5 Pro

OpenAIgpt-5.5-pro

A premium model route for deep reasoning, complex software engineering, long-horizon planning, and high-value agent workflows.

Deep reasoningComplex codingPlanningHigh-value analysis

Context

1.05M

Max output

128K

Input tokens

$30.00 /M

Output tokens

$180.00 /M

GPT-5.6 Terra

OpenAIgpt-5.6-terra

The balanced GPT-5.6 tier for production coding agents, reasoning tasks, tool use, and multi-step app workflows.

CodingAgent workflowsBalanced reasoningTool use

Context

1.05M

Max output

128K

Input tokens

$2.50 /M

Output tokens

$15.00 /M

GPT-5.5

OpenAIgpt-5.5

A strong general-purpose model route for coding, reasoning, research, and production agent workloads through Responses and Chat Completions compatible APIs.

Coding agentsReasoning tasksResearch workflowsApp assistants

Context

1.05M

Max output

128K

Input tokens

$5.00 /M

Output tokens

$30.00 /M

GPT-5.6 Luna Pro

OpenAIgpt-5.6-luna-pro

The cost-efficient GPT-5.6 tier with pro reasoning mode for agent tasks that need more deliberate reasoning without moving to the highest tier.

Budget reasoningCoding agentsTool workflowsResearch drafts

Context

400K

Max output

128K

Input tokens

$1.00 /M

Output tokens

$6.00 /M

GPT-5.6 Luna

OpenAIgpt-5.6-luna

The efficient GPT-5.6 tier for fast coding loops, chat, extraction, search synthesis, and high-volume agent workflows.

Fast agent loopsHigh-volume chatExtractionCost-sensitive coding

Context

400K

Max output

128K

Input tokens

$1.00 /M

Output tokens

$6.00 /M