X (Twitter)

Docs

Supported Models

Complete list of AI models available through Elyxir.

Elyxir provides access to hundreds of AI models from major providers. This reference lists the currently active models with Elyxir pricing.

OpenAI Models

GPT-5 Series

Model	Context	Input/1M	Output/1M	Best For
gpt-5.5	128K	$6.00	$36.00	Current flagship
gpt-5.5-pro	128K	$36.00	$216.00	Maximum reasoning depth
gpt-5.5-instant	128K	$6.00	$36.00	Speed-optimized flagship
gpt-5.4	128K	$3.00	$18.00	Mid-tier flagship
gpt-5.2	128K	$2.10	$16.80	Previous flagship
gpt-5.1	128K	$0.75	$6.00	Budget tier
gpt-5-mini	128K	$0.30	$2.40	Balanced, cost-effective
gpt-5-nano	128K	$0.06	$0.48	Fast, budget-friendly

GPT-4.1 Series

Model	Context	Input/1M	Output/1M	Best For
gpt-4.1	1M	$2.40	$9.60	Long context, vision
gpt-4.1-mini	1M	$0.48	$1.92	Efficient, vision
gpt-4.1-nano	1M	$0.12	$0.48	Ultra-fast, cheap

GPT-4 Series

Model	Context	Input/1M	Output/1M	Best For
gpt-4o	128K	$3.00	$12.00	General, Vision
gpt-4o-mini	128K	$0.18	$0.72	Cost-effective

Embeddings

Model	Dimensions	Max Input	Price/1M
text-embedding-3-large	3072	8191	$0.16
text-embedding-3-small	1536	8191	$0.02

Anthropic Models

Claude 4.8 Series (Latest)

Model	Context	Input/1M	Output/1M	Best For
claude-opus-4.8	200K	$6.00	$30.00	Current flagship, agentic coding

Claude 4.7 Series

Model	Context	Input/1M	Output/1M	Best For
claude-opus-4.7	200K	$6.00	$30.00	Complex agentic tasks

Claude 4.6 Series

Model	Context	Input/1M	Output/1M	Best For
claude-sonnet-4.6	200K	$3.60	$18.00	Coding, Agents
claude-opus-4.6	200K	$6.00	$30.00	Most capable

Claude 4.5 Series

Model	Context	Input/1M	Output/1M	Best For
claude-sonnet-4.5	200K	$3.60	$18.00	Coding, Agents
claude-opus-4.5	200K	$6.00	$30.00	Most capable
claude-haiku-4.5	200K	$1.20	$6.00	Fast, affordable

Google Models

Gemini 3.5 Series (Latest)

Model	Context	Input/1M	Output/1M	Best For
gemini-3.5-flash	1M	$1.80	$10.80	Fast, beats 3.1 Pro on coding

Gemini 3.1 Series

Model	Context	Input/1M	Output/1M	Best For
gemini-3.1-pro-preview	1M	$2.40	$14.40	Most capable, reasoning

Gemini 3 Series

Model	Context	Input/1M	Output/1M	Best For
gemini-3-pro-preview	1M	$2.40	$14.40	Advanced reasoning
gemini-3-flash	1M	$0.60	$3.60	Fast, efficient

Gemini 2.5 Series

Model	Context	Input/1M	Output/1M	Best For
gemini-2.5-pro	1M	$1.50	$12.00	Balanced, long context
gemini-2.5-flash	1M	$0.36	$3.00	Fast
gemini-2.5-flash-lite	1M	$0.12	$0.48	Ultra-fast, low-cost

xAI Models

Grok 4.3 Series (Latest)

Model	Context	Input/1M	Output/1M	Best For
grok-4.3	1M	$1.50	$3.00	Current flagship, cost-efficient

Grok 4 Series

Model	Context	Input/1M	Output/1M	Best For
grok-4	100K	$3.60	$18.00	High-capability reasoning

Mistral AI Models

Model	Context	Best For
mistral-large-3	256K	Most capable
mistral-medium-3.1	128K	Balanced
mistral-small-4	256K	Multimodal, agentic coding
mistral-small-3.2	128K	Fast, efficient
codestral-22b	256K	Code generation

DeepSeek Models

Model	Context	Best For
deepseek-v4-pro	128K	Flagship reasoning and coding
deepseek-v4-flash	128K	Fast, cost-effective V4
deepseek-v3.2	128K	General purpose
deepseek-v3.1	128K	Fast, versatile

Cohere Models

Model	Context	Best For
command-a-plus	256K	Latest flagship, vision
command-a	256K	Enterprise RAG

Perplexity Models

Model	Context	Best For
sonar-deep-research	128K	Deep research with citations
sonar-reasoning-pro	128K	Reasoning with web search
perplexity-sonar-large	128K	General search
perplexity-sonar	128K	Fast search

Meta Models

Llama 4 Series

Model	Context	Best For
llama4-scout	320K	Efficient, vision
llama4-maverick	1M	Complex tasks, vision

Llama 3.3 Series

Model	Context	Best For
llama-3.3-70b	128K	High quality

Open-Weight Models (GLM, Kimi, MiniMax, Qwen)

GLM Series (Zhipu AI)

Model	Context	Best For
glm-5.1	202K	Coding, agentic workflows
glm-5	202K	General purpose
glm-5v-turbo	203K	Native multimodal (text + image)
glm-4.7	128K	Balanced
glm-4.6	202K	Cost-efficient

Kimi Series (Moonshot AI)

Model	Context	Best For
kimi-k2.6	256K	Multimodal, long-horizon coding
kimi-k2.5	256K	Agentic, top-ranked coding
kimi-k2	128K	Agentic workflows
kimi-k2-thinking	128K	Extended reasoning

MiniMax Series

Model	Context	Best For
minimax-m3	1M	Multimodal flagship
minimax-m2.7	200K	Balanced MoE
minimax-m2.5	196K	Cost-effective

Qwen Series (Alibaba)

Model	Context	Best For
qwen3.7-max	1M	Long-horizon agent tasks
qwen3.5	256K	Large-scale multilingual
qwen3-coder-next	256K	Code generation
qwen3-235b-thinking	128K	Extended reasoning
qwen3-32b	40K	Mid-size, versatile

NVIDIA Nemotron Series

Model	Context	Best For
nemotron-3-super-120b	1M	Flagship agentic reasoning
nemotron-3-nano-30b	256K	Fast, low-cost reasoning

Capability-Specific Models

Agentic Coding

Model	Context	Best For
grok-build-0.1	256K	xAI coding model (public beta)
gpt-5.3-codex	128K	OpenAI Responses API coding

Image Generation

Model	Best For
gpt-image-2	Next-gen OpenAI image generation
gpt-image-1.5	Fast OpenAI image generation
nano-banana	Gemini 2.5 Flash Image, precise text
nano-banana-pro	Gemini 3 Pro Image, studio quality
nano-banana-2	Gemini 3.1 Flash Image, local edits
imagen-4	Google Imagen 4 Standard
flux-2-pro	FLUX.2 [pro], SOTA open image
flux-dev	FLUX.1 dev, high quality
flux-schnell	FLUX.1 schnell, ultra-fast

Video Generation

Model	Best For
veo-3.1	Google Veo 3.1 GA, with audio
veo-3.1-fast	Veo 3.1 fast tier, 720p
veo-3	Google Veo 3, with audio
veo-3-fast	Google Veo 3 fast
veo-2	Google Veo 2
sora-2	OpenAI Sora 2
sora-2-pro	OpenAI Sora 2 Pro

Audio

Model	Best For
eleven-v3	ElevenLabs v3 TTS, natural voice
tts-1-hd	OpenAI HD text-to-speech
tts-1	OpenAI standard text-to-speech
scribe-v2	ElevenLabs speech-to-text (primary)
scribe-v1	ElevenLabs speech-to-text (legacy)
whisper-1	OpenAI Whisper transcription
gpt-4o-transcribe	GPT-4o powered transcription

Search

Model	Best For
sonar-deep-research	Deep multi-step research
sonar-reasoning-pro	Reasoning with real-time sources
perplexity-sonar-large	Web-grounded answers
perplexity-sonar	Fast web search

Model Selection Guide

By Task

Task	Recommended
General chat	gpt-5-mini, claude-haiku-4.5
Complex reasoning	gpt-5.5, claude-opus-4.8, deepseek-v4-pro
Code generation	claude-sonnet-4.6, grok-build-0.1
Long documents	gpt-4.1, gemini-2.5-pro
Web search	sonar-deep-research, perplexity-sonar-large
Embeddings	text-embedding-3-small
Fast inference	gpt-5-nano, gemini-2.5-flash-lite
Image generation	gpt-image-2, nano-banana-pro
Video generation	veo-3.1, sora-2
Text-to-speech	eleven-v3, tts-1-hd

By Budget

Budget	Recommended
Minimal	gpt-5-nano, gemini-2.5-flash-lite
Moderate	gpt-5-mini, claude-haiku-4.5
Premium	gpt-5.5, claude-opus-4.8

Using Model IDs

Use the full model ID in API requests:

response = client.chat.completions.create(
    model="gpt-4o-mini",  # Model ID
    messages=[...]
)

Or with provider prefix:

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4.5",
    messages=[...]
)

Model Availability

Model availability may vary. Check the Model Hub for current availability and pricing.

Model Hub - Browse models
Providers - Provider details
Comparison - Compare models

Build a Chatbot Providers