Supported Models

Complete list of AI models available through GateFlow.

Chat Models

OpenAI

Model	Context	Quality	Input $/1M	Output $/1M	Best For
gpt-5.2	128k	10/10	$1.75	$14.00	Complex reasoning, best balanced
gpt-5.2-codex	128k	10/10	$1.75	$14.00	Code generation
gpt-5	128k	9/10	$0.50	$4.00	General purpose with vision
gpt-5-mini	128k	8/10	$0.15	$0.60	Fast, cost-effective
gpt-5-nano	128k	7/10	$0.10	$0.40	Simple Q&A, best value
gpt-4.1	128k	9/10	$0.60	$1.80	Legacy, code-optimized
o3	128k	10/10	$10.00	$40.00	Advanced reasoning
o4-mini	128k	9/10	$3.00	$12.00	Fast reasoning

Anthropic

Model	Context	Quality	Input $/1M	Output $/1M	Best For
claude-opus-4-5-20251107	200k	10/10	$15.00	$75.00	Complex analysis, vision
claude-opus-4-1-20250805	200k	10/10	$15.00	$75.00	Code, reasoning
claude-sonnet-4-5-20250929	200k	9/10	$3.00	$15.00	Code, vision, balanced
claude-haiku-4-5-20251015	200k	8/10	$0.25	$1.25	Fast, cost-effective

No Embeddings

Anthropic does not provide embedding models. Use OpenAI, Google, Cohere, or Mistral for embeddings.

Google

Model	Context	Quality	Input $/1M	Output $/1M	Best For
gemini-3-pro	2M	9/10	$1.25	$5.00	Complex reasoning, vision
gemini-3-flash	1M	9/10	$0.10	$0.40	Fast, coding, vision
gemini-3-deep-think	1M	10/10	$3.50	$14.00	Advanced reasoning
gemini-2.5-pro	1M	9/10	$1.00	$4.00	General purpose
gemini-2.5-flash	1M	8/10	$0.075	$0.30	Fast, vision, best value
gemini-2.5-flash-lite	512k	7/10	$0.025	$0.10	Cheapest

Mistral

Model	Context	Quality	Input $/1M	Output $/1M	Best For
mistral-large-3	128k	9/10	$2.00	$6.00	Complex reasoning
mistral-small-3	128k	8/10	$0.20	$0.60	General purpose
ministral-8b	128k	7/10	$0.10	$0.30	Simple Q&A
ministral-3b	128k	6/10	$0.04	$0.04	Cheapest
pixtral-large-latest	128k	8/10	$0.40	$1.20	Vision tasks
devstral-2	128k	9/10	$0.40	$2.00	Code (SWE-bench: 72.2%)
devstral-small-2	128k	8/10	$0.20	$1.00	Fast code tasks

Cohere

Model	Context	Output	Input $/1M	Output $/1M
command-r-plus	128k	4,096	$2.50	$10.00
command-r-plus-08-2024	128k	4,096	$2.50	$10.00
command-r	128k	4,096	$0.15	$0.60
command-r-03-2024	128k	4,096	$0.15	$0.60

Reasoning Models

Model	Provider	Context	Output	Input $/1M	Output $/1M
o3	OpenAI	200k	100,000	$10.00	$40.00
o4-mini	OpenAI	128k	65,536	$1.10	$4.40

Embedding Models

Model	Provider	Dimensions	Max Tokens	$/1M Tokens
text-embedding-3-large	OpenAI	3,072	8,191	$0.13
text-embedding-3-small	OpenAI	1,536	8,191	$0.02
text-embedding-004	Google	768	2,048	$0.025
embed-english-v3.0	Cohere	1,024	512	$0.10
embed-multilingual-v3.0	Cohere	1,024	512	$0.10
embed-english-light-v3.0	Cohere	384	512	$0.05
embed-multilingual-light-v3.0	Cohere	384	512	$0.05
mistral-embed	Mistral	1,024	8,192	$0.10

Audio Models

Speech-to-Text

Model	Provider	Languages	$/minute
whisper-1	OpenAI	50+	$0.006
voxtral-mini-latest	Mistral	100+	$0.02
voxtral-mini-2602	Mistral	100+	$0.02
gemini-2.5-flash	Google	100+	Audio via chat API
gemini-2.5-pro	Google	100+	Audio via chat API

Text-to-Speech

Model	Provider	Voices	$/1M chars
tts-1	OpenAI	6	$15.00
tts-1-hd	OpenAI	6	$30.00
eleven_multilingual_v2	ElevenLabs	100+	$24.00
eleven_turbo_v2_5	ElevenLabs	100+	$12.00
eleven_flash_v2_5	ElevenLabs	100+	$6.00
eleven_monolingual_v1	ElevenLabs	6	$18.00

ElevenLabs Voice IDs

Voice Name	Voice ID
Rachel	21m00Tcm4TlvDq8ikWAM
Josh	TxGEqnHWrfWFTfGW9XjX
Bella	EXAVITQu4vr4xnSDxMaL
Adam	pNInz6obpgDQGcFmaJgB
Antoni	ErXwobaYiN019PkySvjV
Domi	AZnzlk1XvdvUeBnXmlld
Fin	D38z5RcWu1voky8WS1ja

Reranking Models

Model	Provider	$/1k searches
rerank-english-v3.0	Cohere	$1.00
rerank-multilingual-v3.0	Cohere	$1.00

OCR Models

Model	Provider	$/page
mistral-ocr-latest	Mistral	$0.01

Model Capabilities

Vision Support

Models that accept image inputs:

• gpt-5.2 | gpt-5.2-codex | gpt-5 | gpt-5-mini
• claude-opus-4-5 | claude-sonnet-4-5 | claude-haiku-4-5
• gemini-3-pro | gemini-3-flash | gemini-2.5-pro | gemini-2.5-flash
• pixtral-large-latest

Function Calling

Models that support tool use:

• All OpenAI GPT-5 and o-series models
• All Anthropic Claude 4 models
• All Gemini 2.5+ models
• mistral-large-3 | mistral-small-3

JSON Mode

Models with structured JSON output:

• All OpenAI models
• All Anthropic models
• All Gemini models
• All Mistral models

Streaming

All chat models support streaming responses.

Model Comparison

Best for Code

1. devstral-2 - Purpose-built for code
2. gpt-5.2-codex - Excellent code understanding
3. claude-sonnet-4-5 - Strong code generation

Best for Long Context

1. gemini-3-pro - 2M tokens
2. claude-opus-4-5 - 200k tokens
3. gpt-5.2 - 256k tokens

Best for Cost

1. gemini-2.5-flash-lite - $0.025/1M input
2. ministral-3b - $0.04/1M input
3. gpt-5-nano - $0.05/1M input

Best for Quality

1. claude-opus-4-5 - Highest capability
2. gpt-5.2 - Excellent all-around
3. gemini-3-pro - Strong reasoning

Best for Reasoning

1. o3 - Advanced reasoning
2. o4-mini - Fast reasoning
3. claude-opus-4-5 - Complex analysis

Deprecated Models

Model	Provider	Sunset Date	Replacement
gpt-4-turbo	OpenAI	2025-09-01	gpt-5
gpt-4	OpenAI	2025-06-01	gpt-5-mini
gpt-3.5-turbo	OpenAI	2025-03-01	gpt-5-nano
claude-3-opus-20240229	Anthropic	2025-12-01	claude-opus-4-5
gemini-1.5-pro	Google	2026-03-01	gemini-2.5-pro
mistral-medium	Mistral	2025-06-01	mistral-small-3
text-embedding-ada-002	OpenAI	2025-06-01	text-embedding-3-small
rerank-english-v2.0	Cohere	2025-06-01	rerank-english-v3.0
textembedding-gecko	Google	2025-03-01	text-embedding-004

GateFlow automatically falls back to replacement models. See Model Change Management.

Model Aliases

GateFlow provides convenient aliases:

Alias	Resolves To
gpt-5-latest	gpt-5.2
claude-opus	claude-opus-4-5-20251107
claude-sonnet	claude-sonnet-4-5-20250929
claude-haiku	claude-haiku-4-5-20251015
gemini-pro	gemini-3-pro
gemini-flash	gemini-3-flash

You can create custom aliases in the dashboard.

Requesting Models

Need a model not listed? Contact us to request new model support.

Pricing Notes

• Prices shown are GateFlow pass-through rates
• No markup on provider pricing
• Cached responses are free
• Volume discounts available for Enterprise