AI - Model Reference

gpt-6-astra

✅

-

-

Most capable OpenAI model for the hardest end-to-end work.

gpt-6-sol

✅

-

-

Flagship GPT-6 tier for complex professional work, coding, and multi-step reasoning.

gpt-6-luna

✅

-

-

Cheapest, fastest GPT-6 tier for cost-sensitive, high-volume workloads.

gpt-5.6-sol

✅

-

-

Flagship GPT-5.6 tier for complex professional work, coding, and multi-step reasoning.

gpt-5.6-terra

✅

-

-

Balanced GPT-5.6 tier trading some quality for lower cost on everyday work.

gpt-5.6-luna

✅

-

-

Cheapest, fastest GPT-5.6 tier for cost-sensitive, high-volume workloads.

gpt-5.5

✅

-

-

Highest-quality OpenAI option for complex coding and multi-step reasoning.

gpt-5.4

✅

-

-

Balanced flagship GPT-5.4 option when you need stronger quality than mini/nano tiers.

gpt-5.4-mini

✅

-

-

Fast, efficient GPT-5.4 tier for coding, subagents, and high-volume workloads.

gpt-5.4-nano

✅

-

-

Smallest, cheapest GPT-5.4 for classification, extraction, and coding subagents.

gpt-5.1

✅

-

-

High-quality general reasoning and complex multi-step tasks.

gpt-5-2025-08-07

✅

-

-

Stable pinned GPT-5 behaviour for production workflows.

gpt-5-mini-2025-08-07

✅

-

-

Lower-latency GPT-5 tier for routine assistant tasks.

gpt-5-nano-2025-08-07

✅

-

-

Very fast, lightweight completions and high-throughput automation.

gpt-4.1

✅

-

-

Reliable balanced model for broad enterprise use cases.

gpt-4.1-mini

✅

-

-

Cost-sensitive general chat and classification workloads.

gpt-4.1-nano

✅

-

-

Ultra-fast short responses and basic transformations.

o4-mini

✅

-

-

Efficient reasoning tasks where speed and cost both matter.

gpt-4o

✅

-

-

Strong multimodal text and image understanding with broad compatibility.

gpt-4o-mini

✅

-

-

Budget-friendly multimodal interactions and assistant features.

gpt-audio

-

-

✅

General audio input/output through Chat Completions.

gpt-audio-mini

-

-

✅

Cost-efficient audio input/output through Chat Completions.

claude-fable-5-1

✅

-

-

Highest-capability Claude tier for demanding reasoning and long-horizon agentic work.

claude-fable-5

✅

-

-

Highest-capability Claude tier for long-running agents and the hardest reasoning work.

claude-opus-5-5

✅

-

-

Current flagship Opus for agentic coding and enterprise work.

claude-opus-5

✅

-

-

Prior flagship Opus for complex agentic coding and enterprise work.

claude-opus-4-8

✅

-

-

Prior flagship Opus for highest-quality autonomous coding and long-horizon reasoning workflows.

claude-sonnet-5

✅

-

-

Current flagship Sonnet tier for production copilots, fast agentic workflows, and balanced cost.

claude-opus-4-7

✅

-

-

Prior flagship Opus with strong deep-reasoning quality and broad agentic coding capability.

claude-opus-4-6

✅

-

-

Earliest 4.x Opus baseline in this list, useful for compatibility-sensitive production workloads.

claude-sonnet-4-6

✅

-

-

Best combination of speed and intelligence for production copilots.

claude-opus-4-5-20251101

✅

-

-

Deep analysis, nuanced writing, and difficult reasoning tasks.

claude-sonnet-4-5-20250929

✅

-

-

Balanced quality and speed for most production copilots.

claude-haiku-4-5-20251001

✅

-

-

Fast lightweight Claude option for shorter responses.

gemini-3.8-flash

✅

✅

✅

Most intelligent Gemini Flash model for long-horizon software engineering and autonomous agents.

gemini-3.7-flash

✅

✅

✅

High-speed Flash model for everyday coding, agentic tool use, and multi-step execution.

gemini-3.6-flash

✅

✅

✅

Previous-generation Flash model balancing speed and multimodal capability.

gemini-3.5-flash-lite

✅

✅

✅

Cost-efficient model for high-volume agentic tasks, translation, and simple data processing.

gemini-3.5-flash

✅

✅

✅

Stable Gemini 3.x chat model for agentic workflows, coding, and long-context assistants.

gemini-3.1-flash-lite

✅

✅

✅

Lowest-cost current Gemini 3.x option for high-volume classification, extraction, routing, and lightweight multimodal tasks.

gemini-3.1-pro-preview

✅

✅

✅

Advanced multimodal reasoning with strong media handling.

gemini-2.5-pro

✅

✅

✅

Deprecated by Google; use gemini-3.1-pro-preview for higher-capability multimodal tasks.

gemini-2.5-flash

✅

✅

✅

Deprecated by Google; use gemini-3.5-flash for general multimodal chat and assistants.

gemini-2.5-flash-lite

-

✅

✅

Deprecated by Google; use gemini-3.1-flash-lite for lowest-cost lightweight workloads.

groq-openai/gpt-oss-120b

-

-

-

Open model inference with strong text quality on Groq.

groq-openai/gpt-oss-20b

-

-

-

Faster open model option for practical general chat.

groq-openai/gpt-oss-safeguard-20b

-

-

-

Safety-sensitive open model scenarios needing stricter behaviour.

groq-llama-3.3-70b-versatile

-

-

-

High-quality Groq-hosted general-purpose text generation.

gpt-3.5-turbo-0125

gpt-4o-mini

gpt-3.5-turbo-1106

gpt-4o-mini

gpt-3.5-turbo

gpt-4o-mini

gpt-3.5-turbo-16k

gpt-4o-mini

gpt-4

gpt-4o

gpt-4-turbo

gpt-4o

gpt-4-turbo-2024-04-09

gpt-4o

gpt-4-turbo-preview

gpt-4o

gpt-4-0125-preview

gpt-4o

gpt-4-1106-preview

gpt-4o

gemini-1.0-pro

gemini-2.5-pro

gemini-1.5-pro

gemini-2.5-pro

gemini-1.5-flash

gemini-2.5-flash

gemini-2.0-flash

gemini-2.5-flash

gemini-2.0-flash-lite

gemini-2.5-flash-lite

gemini-3-flash-preview

gemini-3.5-flash

gemini-3-pro-preview

gemini-3.1-pro-preview

claude-3-opus-20240229

claude-opus-5

claude-3-sonnet-20240229

claude-sonnet-5

claude-3-5-sonnet-20240620

claude-sonnet-5

claude-3-5-sonnet-20241022

claude-sonnet-5

claude-3-7-sonnet-20250219

claude-sonnet-5

claude-3-haiku-20240307

claude-haiku-4-5-20251001

claude-3-5-haiku-20241022

claude-haiku-4-5-20251001

claude-sonnet-4-20250514

claude-sonnet-5

claude-opus-4-20250514

claude-opus-5

groq-mixtral-8x7b

groq-llama-3.3-70b-versatile

groq-gemma2-9b-it

groq-openai/gpt-oss-20b

llama-3.1-70b-versatile

groq-llama-3.3-70b-versatile

groq-llama-3.1-70b-versatile

groq-llama-3.3-70b-versatile

llama3-70b-8192

groq-llama-3.3-70b-versatile

groq-llama3-70b-8192

groq-llama-3.3-70b-versatile

mixtral-8x7b-32768

groq-llama-3.3-70b-versatile

groq-mixtral-8x7b-32768

groq-llama-3.3-70b-versatile

groq-llama-3.1-8b-instant

groq-openai/gpt-oss-20b

llama-3.1-8b-instant

groq-openai/gpt-oss-20b

llama3-8b-8192

groq-openai/gpt-oss-20b

groq-llama3-8b-8192

groq-openai/gpt-oss-20b

gemma-7b-it

groq-openai/gpt-oss-20b

groq-gemma-7b-it

groq-openai/gpt-oss-20b

groq-meta-llama/llama-4-maverick-17b-128e-instruct

groq-openai/gpt-oss-120b

llama-4-maverick-17b-128e-instruct

groq-openai/gpt-oss-120b

gpt-image-1

openai:gpt-image-2

openai:dall-e-2

openai:gpt-image-2

openai:dall-e-3

openai:gpt-image-2