All Models
Access 360 AI models from 22 leading providers through a single, unified API. No vendor lock-in. Switch models with one line of code.
Anthropic
40 modelsClaude Fable 5.1 for agent workflows.
claude-fable-5-1
Claude Sonnet 5.5 for multimodal and agent workflows.
claude-sonnet-5-5
Claude Opus 5.5 for coding and agent workflows.
claude-opus-5-5
Claude Opus 5.5 for coding and agent workflows.
claude-opus-5.5
Per-request Claude Opus 5.5 for coding and agent workflows.
claude-opus-5-5-request
Claude Opus 5 Thinking for multimodal and agent workflows.
claude-opus-5-thinking
Claude Opus 5 for coding and multi-step reasoning.
claude-opus-5
Opus 5 for multi-step reasoning.
opus-5
Per-request Claude Opus 5 for coding and multi-step reasoning.
claude-opus-5-request
Claude Sonnet 5 for agent workflows.
claude-sonnet-5
Claude Sonnet 5 Medium for text generation.
stali/claude-sonnet-5-medium
Per-request Claude Sonnet 5 for agent workflows.
claude-sonnet-5-request
Bedrock Claude Fable 5 for text generation.
bedrock-claude-fable-5
Claude Fable 5 for agent workflows.
claude-fable-5
Per-request Claude Fable 5 for sustained agent workflows.
claude-fable-5-premium
Per-request Claude Fable 5 for agent workflows.
claude-fable-5-request
Claude Fable 5 Vip for agent workflows.
claude-fable-5-vip
Agentgw Fable 5 for coding and agent workflows.
agentgw-fable-5
Claude Opus 5 Thinking Kiro for coding and multi-step reasoning.
claude-opus-5-thinking-kiro
Per-request Agentgw Fable 5 for coding and agent workflows.
agentgw-fable-5-request
Per-request Claude Opus 5 Oh for coding and multi-step reasoning.
claude-opus-5-oh-request
Per-request Opus 5 for coding and multi-step reasoning.
opus-5-request
Claude Opus 4.8 for coding and agent workflows.
claude-opus-4-8
Claude Opus 4.8 Medium for text generation.
stali/claude-opus-4-8-medium
Per-request Claude Opus 4.8 for coding and agent workflows.
claude-opus-4-8-request
Agentgw Opus 4 8 for coding and agent workflows.
agentgw-opus-4-8
Per-request Agentgw Opus 4 8 for coding and agent workflows.
agentgw-opus-4-8-request
Per-request Claude Opus 4 8 Premium for coding and multi-step reasoning.
claude-opus-4-8-premium-request
Claude Opus 4.7 for coding and multi-step reasoning.
claude-opus-4-7
Claude Opus 4.7 Medium for text generation.
stali/claude-opus-4-7-medium
Per-request Claude Opus 4.7 for coding and multi-step reasoning.
claude-opus-4-7-request
Claude Sonnet 4.6 for coding and agent workflows.
claude-sonnet-4-6
Per-request Claude Sonnet 4.6 for coding and agent workflows.
claude-sonnet-4-6-request
Claude Opus 4.6 Thinking for multi-step reasoning.
ag/claude-opus-4-6-thinking
Claude Opus 4.6 for coding and multi-step reasoning.
claude-opus-4-6
Per-request Claude Opus 4.6 for coding and multi-step reasoning.
claude-opus-4-6-request
Claude Haiku 4.5 for agent workflows.
claude-haiku-4-5
Claude Haiku 4.5.20251001 for agent workflows.
claude-haiku-4-5-20251001
Per-request Claude Haiku 4.5 for agent workflows.
claude-haiku-4-5-request
Claude Opus 4.6 for coding and multi-step reasoning on a free-tier lane.
free:claude-opus-4.6
OpenAI
49 modelsGPT 6 Astra for coding and multi-step reasoning.
gpt-6-astra
GPT 6.1 Sol marketplace route.
gpt-6.1-sol
GPT 6.1 Sol Request marketplace route.
gpt-6.1-sol-request
GPT 6 Luna for text generation.
gpt-6-luna
GPT 6 Sol for coding and agent workflows.
gpt-6-sol
Per-request GPT 6 Astra for coding and multi-step reasoning.
gpt-6-astra-request
Per-request GPT 6 Luna for coding and multi-step reasoning.
gpt-6-luna-request
GPT 6 Reasoning Pro for reasoning and tool-driven tasks.
gpt-6-reasoning-pro-request
Per-request GPT 6 Sol for coding and agent workflows.
gpt-6-sol-request
GPT 5.6 Luna for text generation.
gpt-5.6-luna
GPT 5.6 Sol for professional text tasks.
gpt-5.6-sol
GPT 5.6 Terra for text generation.
gpt-5.6-terra
Per-request GPT 5.6 Luna for text generation.
gpt-5.6-luna-request
GPT 5.6 Sol Cheap for text generation.
gpt-5.6-sol-cheap
Per-request GPT 5.6 Sol for professional text tasks.
gpt-5.6-sol-request
Per-request GPT 5.6 Terra for text generation.
gpt-5.6-terra-request
Per-request GPT 5.6 Terra Cheap for coding and multi-step reasoning.
gpt-5.6-terra-cheap-request
GPT 5.5 for text generation.
gpt-5.5
GPT 5.5 High for agent workflows.
gpt-5.5-high
GPT 5.5 XHigh for multi-step reasoning.
gpt-5.5-xhigh
Per-request GPT 5.5 XHigh for multi-step reasoning.
gpt-5.5-xhigh-request
GPT 5.5 Image for image generation.
cx/gpt-5.5-image
Per-request GPT 5.5 Cheap for coding and multi-step reasoning.
gpt-5.5-cheap-request
Per-request GPT 5.5 High for coding and agent workflows.
gpt-5.5-high-request
Per-request GPT 5.5 for coding and multi-step reasoning.
gpt-5.5-request
GPT 5.4 Mini for text generation.
gpt-5.4-mini
Per-request GPT 5.4 Mini for text generation.
gpt-5.4-mini-request
GPT 5.4 for multimodal reasoning.
gpt-5.4
GPT 5.4 Image for image generation.
cx/gpt-5.4-image
GPT 5.3 Codex Spark for coding and agent workflows.
gpt-5.3-codex-spark
GPT 5.3 Image for image generation.
cx/gpt-5.3-image
GPT Image 2.5 Flare for image generation.
gpt-image-2.5-flare
GPT Image 2.5 Sunburst for image generation.
gpt-image-2.5-sunburst
GPT Image 2.5 Flare for 4K image generation and editing.
4k-gpt-image-2.5-flare
4k GPT Image 2.5 Flare Slow for image generation.
4k-gpt-image-2.5-flare-slow
4k GPT Image 2.5 Slow for image generation.
4k-gpt-image-2.5-slow
4k GPT Image 2.5 Sunburst Slow for image generation.
4k-gpt-image-2.5-sunburst-slow
GPT Image 2 for image generation and editing at 2K resolution.
2k-gpt-image-2
4k GPT Image 2 for image generation and editing.
4k-gpt-image-2
GPT Image 2 for image generation and editing.
gpt-image-2
Per-request GPT Image 2 for image generation and editing.
gpt-image-2-req
GPT Oss 120b for coding and multi-step reasoning.
gpt-oss-120b
GPT Oss 20b for multi-step reasoning.
gpt-oss-20b
GPT Oss 20b for multi-step reasoning on a free-tier lane.
openai/gpt-oss-20b:free
GPT 4o Mini TTS for text-to-speech.
gpt-4o-mini-tts
Codex Auto Review for coding assistance.
codex-auto-review
Per-request GPT Oss Safeguard 20b for content safety review.
gpt-oss-safeguard-20b:free-request
Text Embedding 3 Large for text embeddings.
text-embedding-3-large
Text Embedding 3 Small for text embeddings.
text-embedding-3-small
Gemini 3.8 for coding and multi-step reasoning.
gemini-3.8
Gemma 4 26b A4b It for agent workflows.
gemma-4-26b-a4b-it
Gemma 4 31b It for coding and multi-step reasoning.
gemma-4-31b-it
Gemini 3.8 Flash Medium for agent workflows.
gemini-3.8-flash-medium
Gemini 3.8 Flash High for coding and agent workflows.
antigravity/gemini-3.8-flash-high
Gemini 3.8 Flash for coding and agent workflows.
gemini-3.8-flash
Per-request Gemini 3.8 Flash for coding and agent workflows.
gemini-3.8-flash-request
Gemini 3.8 Flash Low for coding and multi-step reasoning.
gemini-3.8-flash-low
Gemini 3.8 Flash Tts for text-to-speech.
gemini-3.8-flash-tts
Gemini 3.7 Flash Tiered (high) for multi-step reasoning.
ag/gemini-3.7-flash-tiered (high)
Gemini 3.7 Flash High for text generation.
gemini-3.7-flash-high
Gemini 3.7 Flash Low for agent workflows.
gemini-3.7-flash-low
Gemini 3.7 Flash Medium for agent workflows.
gemini-3.7-flash-medium
Gemini 3.7 Flash for coding and agent workflows.
llms/gemini-3.7-flash
Gemini 3.6 Flash Medium for agent workflows.
gemini-3.6-flash-medium
Gemini 3.6 Flash Low for agent workflows.
ag/gemini-3.6-flash-low
Gemini 3.6 Flash for coding and agent workflows.
gemini-3.6-flash
Gemini 3.6 Flash High for text generation.
gemini-3.6-flash-high
Per-request Gemini 3.6 Flash High for text generation.
gemini-3.6-flash-high-request
Gemini 3.5 Flash Lite for agent workflows.
gemini-3.5-flash-lite
Gemini 3.5 Flash Low for agent workflows.
gemini-3.5-flash-low
Gemini 3.5 Flash for multi-step reasoning.
sell/gemini-3.5-flash
2k Gemini 3.1 Flash Image for image generation.
2k-gemini-3.1-flash-image
Gemini 3.1 Flash Image for image generation and editing.
gemini-3.1-flash-image
Gemini 3.1 Flash Lite for coding assistance.
gemini-3.1-flash-lite
Per-request Gemini 3.1 Flash Lite for coding and multi-step reasoning.
gemini-3.1-flash-lite-request
Veo 3.1 Lite for video generation.
veo-3.1-lite
Gemini 3.1 Pro Preview for multimodal reasoning.
gemini-3.1-pro-preview
Veo 3.1 Fast for video generation.
veo-3.1-fast
Veo 3.1 Quality for video generation.
veo-3.1-quality
Gemini 3.1 Flash Image Preview for image generation.
gemini-3.1-flash-image-preview
Gemini 3 Pro Image for image generation and editing.
gemini-3-pro-image
Gemini 3.0 Pro Image for image generation.
gemini-3.0-pro-image
Gemini 3 Flash Agent for agent workflows.
ag/gemini-3-flash-agent
Gemini 3 Flash Preview for multimodal understanding.
gemini-3-flash-preview
Gemini 3 Flash for multimodal and agent workflows.
gemini-3-flash
Gemini 3 Pro Image Preview for image generation.
gemini-3-pro-image-preview
Gemini Flash 3 Image for image generation.
gemini-flash-3-image
Gemini 2.5 Flash Lite for text generation.
gemini-2.5-flash-lite
Per-request Gemini 2.5 Flash Lite for text generation.
gemini-2.5-flash-lite-request
Gemini 2.5 Flash for text generation.
gemini-2.5-flash
Gemini 2.5 Pro for multi-step reasoning.
gemini-2.5-pro
Per-request Gemini 2.5 Flash for text generation.
gemini-2.5-flash-request
Gemini 2.5 Flash Preview Tts for text-to-speech.
gemini-2.5-flash-preview-tts
Gemini 2.5 Pro Preview Tts for text-to-speech.
gemini-2.5-pro-preview-tts
Gemini Embedding 2 Preview for text embeddings.
gemini/gemini-embedding-2-preview
2k Flow Nano Banana 2 for image generation.
2k-flow-nano-banana-2
Flow Nano Banana 2 for image generation.
flow-nano-banana-2
Nano Banana 2 for 4K image generation.
4k-flow-nano-banana-2
Flow Nano Banana 2 Lite for image generation.
flow-nano-banana-2-lite
Gemini Omni 1.1 Flash for video generation.
gemini-omni-1.1-flash
Gemini Embedding 001 for text embeddings.
gemini-embedding-001
Diffusiongemma 26b A4b It for multimodal reasoning.
llms/diffusiongemma-26b-a4b-it
Gemini Flash for coding and multi-step reasoning.
gemini-flash
2k Flow Nano Banana Pro for image generation.
2k-flow-nano-banana-pro
Flow Nano Banana Pro for image generation.
flow-nano-banana-pro
Gemini Pro Agent for agent workflows.
ag/gemini-pro-agent
Nano Banana Pro for 4K image generation and editing.
4k-flow-nano-banana-pro
Nano Banana Pro for image generation.
nano-banana-pro
Z Image Turbo for image generation.
z-image-turbo
XAI
22 modelsGrok 4.7 for coding and agent workflows.
grok-4.7
Grok 4.7 Build Fast for coding and multi-step reasoning.
grok-4.7-build-fast
Per-request Grok 4.7 Build Fast for coding and multi-step reasoning.
grok-4.7-build-fast-request
Per-request Grok 4.7 for coding and agent workflows.
grok-4.7-request
Grok 4.6 from xAI for coding and multi-step reasoning.
grok-4.6
Per-request Grok 4.6 from xAI for coding and multi-step reasoning.
grok-4.6-request
Per-request Grok 4.6 Xhigh for coding and multi-step reasoning.
grok-4.6-xhigh-request
Grok 4.5 from xAI for coding and multi-step reasoning.
grok-4.5
Grok 4.5_console for multi-step reasoning.
grok-4.5_console
Per-request Grok 4.5 from xAI for coding and multi-step reasoning.
grok-4.5-request
Grok 4.3 for multi-step reasoning.
x-ai/grok-4.3
4k Grok Imagine Image 2.0 for image generation.
4k-grok-imagine-image-2.0
Grok Imagine Image 2.0 for image generation.
grok-imagine-image-2.0
Grok Voice Latest for text-to-speech.
grok-voice-latest
Grok Imagine Image Quality for image generation.
grok-imagine-image-quality
Grok Stt for speech-to-text transcription.
grok-stt
Grok Image for image generation.
grok-image
Grok Imagine Image for image generation.
grok-imagine-image
Grok Imagine Image Lite for image generation.
grok-imagine-image-lite
Grok Imagine Video for video generation.
grok-imagine-video
Grok 1k for image generation.
grok-1k
Grok 2k for image generation.
grok-2k
DeepSeek
24 modelsDeepSeek V4.1 Flash for coding and agent workflows.
deepseek-v4.1-flash
DeepSeek 4.1 for text generation.
deepseek-4.1
Per-request DeepSeek V4.1 Flash for coding and agent workflows.
deepseek-v4.1-flash-request
Per-request DeepSeek V4.1 Flash Req for coding and multi-step reasoning.
deepseek-v4.1-flash-req-request
Per-request DeepSeek V4.1 Flash for coding and multi-step reasoning.
deepseek-v4.1-flash:free-request
DeepSeek V4 Flash Vision Exp for multimodal and agent workflows.
deepseek-v4-flash-vision-exp
DeepSeek V4 Pro 0813 for text generation.
deepseek-v4-pro-0813
DeepSeek V4 Pro 0873 for multimodal reasoning.
deepseek-v4-pro-0873
Per-request DeepSeek V4 Pro 0813 for text generation.
deepseek-v4-pro-0813-request
DeepSeek V4 Flash 0731 for coding and agent workflows.
deepseek-v4-flash-0731
Per-request DeepSeek V4 Flash 0731 for coding and agent workflows.
deepseek-v4-flash-0731-request
DeepSeek Pro V4 for coding and multi-step reasoning.
deepseek-pro-v4
DeepSeek V4 Flash for coding and agent workflows.
deepseek-v4-flash
DeepSeek V4 Flash[1m] for text generation.
deepseek-v4-flash[1m]
DeepSeek V4 Pro for coding and multi-step reasoning.
deepseek-v4-pro
Per-request DeepSeek Pro V4 for coding and multi-step reasoning.
deepseek-pro-v4-request
Per-request DeepSeek V4 Flash for coding and agent workflows.
deepseek-v4-flash-request
Per-request DeepSeek V4 Pro for coding and multi-step reasoning.
deepseek-v4-pro-request
DeepSeek V3.2 for coding and multi-step reasoning.
deepseek-v3.2
Per-request DeepSeek V3.2 for coding and multi-step reasoning.
deepseek-v3.2-request
Per-request DeepSeek Chat V3.1 for text generation.
deepseek/deepseek-chat-v3.1-request
DeepSeek R1 Distill Qwen 32b for coding and multi-step reasoning.
deepseek-r1-distill-qwen-32b
DeepSeek for coding and multi-step reasoning.
deepseek
Per-request Qoder DeepSeek Flash for coding and multi-step reasoning.
qoder-deepseek-flash-request
Moonshot AI
9 modelsKimi K3 for multimodal understanding.
kimi-k3
Kimi K3 Er for multi-step reasoning.
kimi-k3-er
Per-request Kimi K3 for multimodal understanding.
kimi-k3-request
Per-request Kmi K3 for coding and multi-step reasoning.
kmi-k3-request
Kimi 2.7 for coding and agent workflows.
kimi-2.7
Kimi 2.7 Code for coding assistance.
kimi-2.7-code
Kimi K2.7 Code for text generation.
kimi-k2.7-code
Kimi K2.6 for coding assistance.
kimi-k2.6
Kimi K2.5 for multimodal and agent workflows.
kimi-k2.5
Alibaba
46 modelsQwen3.8 Max for coding and agent workflows.
qwen3.8-max
Qwen 3.8 Flash Next for agent workflows.
qwen3.8-flash-next
Qwen 3.8 Omni Flash for multimodal and agent workflows.
qwen3.8-omni-flash
Qwen 3.8 Max Premium for coding and agent workflows.
qwen3.8-max-premium
Qwen 3.8 Max 0902 for multimodal and agent workflows.
qwen3.8-max-0902
Qwen 3.8 Flash for coding and agent workflows.
qwen-3.8-flash
Qwen3.8 Flash for coding and agent workflows.
qwen3.8-flash
Qwen3.8 27b for multi-step reasoning.
qwen3.8-27b
Per-request Qwen3.8 27b for multi-step reasoning.
qwen3.8-27b-request
Qwen 3.8 Max for coding and agent workflows.
qwen-3.8-max
Per-request Qwen 3.8 Max for coding and agent workflows.
qwen-3.8-max-request
Per-request Qwen3.8 Max for coding and agent workflows.
qwen3.8-max-request
Qwen3.8 Max Agent for agent workflows.
qwen3.8-max-agent
Qwen3.8 Open Source for text generation.
qwen3.8-open-source
Qwen3.8 Fast for coding assistance.
qwen3.8-fast
Per-request Qwen3.8 Max 0902 Req for coding and multi-step reasoning.
qwen3.8-max-0902-req
Per-request Qwen3.8 27b for coding and multi-step reasoning.
qwen3.8-27b:free-request
Per-request Qwen3.8 Flash Next for coding and agent workflows.
qwen3.8-flash-next-request
Per-request Qwen3.8 Flash for coding and agent workflows.
qwen3.8-flash-request
Qwen3.7 Flash for coding and agent workflows.
qwen3.7-flash
Qwen 3.7 Plus for coding and agent workflows.
llms/qwen-3.7-plus
Qwen3.7 Plus for coding and agent workflows.
qwen3.7-plus
Qwen 3.7 for multi-step reasoning.
qwen-3.7
Qwen3.7 Max for coding and multi-step reasoning.
qwen3.7-max
Per-request Qwen3.7 Max for coding and multi-step reasoning.
qwen3.7-max-request
Per-request Qwen3.7 Plus for coding and agent workflows.
qwen3.7-plus-request
Qwen3.6 35b A3b for coding and multi-step reasoning.
ds/qwen3.6-35b-a3b
Qwen3.6 27b for coding and multi-step reasoning.
qwen3.6-27b
Qwen3.6 Flash for multi-step reasoning.
qwen3.6-flash
Per-request Qwen3.6 27b for coding and multi-step reasoning.
qwen3.6-27b-request
Qwen3.6 Plus for text generation.
qwen3.6-plus
Qwen3.5 122b A10b for coding and multi-step reasoning.
ds/qwen3.5-122b-a10b
Qwen3.5 Flash for multimodal reasoning.
qwen3.5-flash
Qwen3.5 397b A17b for multimodal understanding.
ds/qwen3.5-397b-a17b
Qwen3.5 Plus for multimodal and agent workflows.
qwen3.5-plus
Qwen3 Codex Aws for coding and agent workflows.
qwen3-codex-aws
Qwen3 Codex for coding and agent workflows.
stali/qwen3-codex
Qwen Image 3.0 Pro for image generation.
qwen-image-3.0-pro
Qwen3 Coder Plus for coding assistance.
qwen3-coder-plus
Qwen3 235b A22b 2507 for coding and multi-step reasoning.
qwen/qwen3-235b-a22b-2507
Qwen3 Coder 480b for coding assistance.
qwen3-coder-480b
Qwen Image 3.0 Pro for 4K image generation and editing.
4k-qwen-image-3.0-pro
Qwen3 30b A3b Fp8 for coding and multi-step reasoning.
qwen3-30b-a3b-fp8
Qwen Image 2.0 Pro for image generation.
qwen-image-2.0-pro
Qwen Image Plus for image generation.
qwen-image-plus
Qwen for coding and multi-step reasoning.
qwen
Zhipu
17 modelsGLM 5.3 for coding and multi-step reasoning.
glm-5.3
GLM 5.3 Premium for agent workflows.
glm-5.3-premium
GLM 5.3 Flash for coding assistance.
glm-5.3-flash
Per-request GLM 5.3 Flash for coding assistance.
glm-5.3-flash-request
Per-request GLM 5.3 for coding and multi-step reasoning.
glm-5.3-request
GLM 5.3 Flashx for coding and multi-step reasoning.
glm-5.3-flashx
Per-request GLM 5.3 Flash Search for coding and multi-step reasoning.
glm-5.3-flash-search:free-request
Per-request GLM 5.3 Flash Think Search for coding and multi-step reasoning.
glm-5.3-flash-think-search:free-request
GLM 5.2 for coding and agent workflows.
glm-5.2
Per-request GLM 5.2 for coding and agent workflows.
glm-5.2-request
512K-context GLM 5.2 512k for coding and agent workflows.
glm-5.2-512k
GLM 5.1 for coding and multi-step reasoning.
glm-5.1
Per-request GLM 5.1 for coding and multi-step reasoning.
glm-5.1-request
GLM 5 Turbo for coding and agent workflows.
glm-5-turbo
GLM 5 for agent workflows.
glm-5
GLM 4.7 Flash for coding assistance.
z-ai/glm-4.7-flash
GLM 4.7 for coding and agent workflows.
glm-4.7
MiniMax
9 modelsPer-request MiniMax M3.1 Flash Preview for coding and multi-step reasoning.
MiniMax-M3.1-Flash-Preview-request
512K-context MiniMax M3 512k for multimodal understanding.
minimax-m3-512k
MiniMax M3 for multimodal understanding.
minimax-m3
Per-request MiniMax M3 for multimodal understanding.
minimax-m3-request
MiniMax M2.7 for agent workflows.
minimax-m2.7
MiniMax M2.7 Highspeed for coding and agent workflows.
minimax-m2.7-highspeed
Per-request MiniMax M2.7 for agent workflows.
minimax-m2.7-request
MiniMax M2.5 for text generation.
stali/minimax-m2.5
MiniMax M2.1 for multi-step reasoning.
stali/minimax-m2.1
MiMo
8 modelsMiMo V2.6 Pro for multimodal and agent workflows.
mimo-v2.6-pro
MiMo V2.6 for multi-step reasoning.
mimo-v2.6
Per-request MiMo V2.6 Flash for text generation.
mimo-v2.6-flash-request
Per-request MiMo V2.6 Pro for multi-step reasoning.
mimo-v2.6-pro-request
MiMo V2.5 for coding and multi-step reasoning.
mimo-v2.5
MiMo V2.5 Pro for coding assistance.
mimo-v2.5-pro
Per-request MiMo V2.5 for coding and multi-step reasoning.
mimo-v2.5-request
MiMo for coding and multi-step reasoning.
mimo
ByteDance
8 modelsDoubao Seedream 5.0 Pro 260628 for image generation.
doubao-seedream-5-0-pro-260628
Doubao Seedream 5.0.260128 for image generation.
doubao-seedream-5-0-260128
Wan2.7 Image for image generation.
wan2.7-image
Wan2.7 Image Pro for image generation.
wan2.7-image-pro
Wan2.7 I2V for video generation.
wan2.7-i2v
Wan2.6 Image for image generation.
wan2.6-image
Wan T2V for video generation.
wan-t2v
Wan T2I for image generation.
wan-t2i
NVIDIA
3 modelsNemotron 3 Ultra 550b A55b for multi-step reasoning.
nvidia/nemotron-3-ultra-550b-a55b
Nemotron 3 Super for agent workflows.
nemotron-3-super
Nemotron 3 Super 120b A12b for multi-step reasoning.
nvidia/nemotron-3-super-120b-a12b
Meta
5 modelsLlama 3.3 70b Versatile for coding and multi-step reasoning.
llms/llama-3.3-70b-versatile
Muse Spark 1.3 for multimodal and agent workflows.
muse-spark-1.3
Muse Spark 1.3 Contributor for coding and agent workflows.
muse-spark-1.3-contributor
Muse Spark 1.3 Contributor for text generation and tool-driven tasks.
muse-spark-1.3-contributor-request
Muse Spark 1.2 for agent workflows.
muse-spark-1.2
Mistral
4 modelsMistral Small 3.1 24b Instruct for coding and multi-step reasoning.
mistral-small-3.1-24b-instruct
Mistral Medium for multi-step reasoning.
sell/mistral-medium
Mistral Large for coding and multi-step reasoning.
llms/mistral-large
Mistral Embed for text embeddings.
mistral/mistral-embed
Groq
3 modelsWhisper Large V3 Turbo for speech-to-text transcription.
groq/whisper-large-v3-turbo
Whisper Large V3 for speech-to-text transcription.
groq/whisper-large-v3
Faster Whisper Chat for speech-to-text transcription.
faster-whisper-chat
Step
1 modelStep 5 Preview for text generation and tool-driven tasks.
step-5-preview-request
StepFun
2 modelsStep 3.7 Flash for multimodal and agent workflows.
step-3.7-flash
Per-request Step 3.7 Flash for multimodal and agent workflows.
step-3.7-flash-request
Poolside
1 modelLaguna S 2.1 for coding and agent workflows.
laguna-s-2.1
Intern
4 modelsAgnes Image 2.1 Flash for image generation.
imgs/agnes-image-2.1-flash
Agnes 2.0 Flash for coding and agent workflows.
llms/agnes-2.0-flash
Kat Coder Pro V2.5 for coding assistance.
kat-coder-pro-v2.5
Intern S1 for coding and multi-step reasoning.
llms/intern-s1
Stability AI
1 modelFLUX for image generation.
pln/flux
OpenCode
1 modelBig Pickle for agent workflows.
big-pickle
Boltch
43 modelsAutomatic model routing for text requests on a free-tier lane.
free:service/auto
Venice Uncensored 1.2 for text generation.
llms/venice-uncensored-1.2
Mini 256 for coding and multi-step reasoning.
Mini-256
Per-request Hy4 Preview for coding and multi-step reasoning.
tencent/hy4-preview-request
GEM PIX 2 for image generation.
GEM_PIX_2
Narwhal for image generation.
NARWHAL
SenseNova 6.8 Flash Lite for text generation on a free-tier lane.
free:sensenova-6.8-flash-lite
Grok 4.7 for text generation on a free-tier lane.
free:grok-4.7-free
Claude Sonnet 4.6 for coding and agent workflows on a free-tier lane.
free:claude-sonnet-4.6
Grok 4.5 for text generation on a free-tier lane.
free:grok-4.5-free
Gemma 4 26B for text generation on a free-tier lane.
free:gemma-4-26b
Gemma 4 31B for coding and multi-step reasoning on a free-tier lane.
free:gemma-4-31b
DeepSeek V4 Flash Vision (experimental) for multimodal text generation on a free-tier lane.
free:deepseek-v4-flash-vision-exp-free
Qwen 3.8 Flash Next for coding and agent workflows on a free-tier lane.
free:qwen-3.8-flash-next
Qwen 3.8 27B for multi-step reasoning on a free-tier lane.
free:qwen-3.8-27b
Nemotron 3.5 Lightning for text generation on a free-tier lane.
free:nemotron-3.5-lightning-free
Ling 3.1 Flash for text generation on a free-tier lane.
free:ling-3.1-flash
Moondream 3.1 for multimodal understanding on a free-tier lane.
free:moondream3.1
Compatibility route for Kimi K3 on shared free capacity.
free:kimi-k3-fast
Agnes 3.0 Flash for text generation on a free-tier lane.
free:agnes-3.0-flash
Dots 3 Note Preview for text generation on a free-tier lane.
free:dots-3-note-preview
Nova 3 for speech-to-text transcription on a free-tier lane.
free:nova-3
MiMo V2.6 Flash for text generation on a free-tier lane.
free:mimo-v2.6-flash
LFM 2.5 2.6B for lightweight text generation on a free-tier lane.
free:lfm-2.5-2.6b
MiMo V2.5 for agent workflows on a free-tier lane.
free:mimo-v2.5-free
Agnes 2.5 Flash for text generation on a free-tier lane.
free:agnes-2.5-flash
LongCat 2.5 Preview for text generation on a free-tier lane.
free:longcat-2.5-preview
Laguna XS 2.1 for coding and text generation on a free-tier lane.
free:laguna-xs-2.1
FLUX 2 Klein 9B for image generation and editing on a free-tier lane.
free:flux-2-klein-9b
FLUX 2 Klein 4B for image generation and editing on a free-tier lane.
free:flux-2-klein-4b
Aura 2 EN for text-to-speech on a free-tier lane.
free:aura-2-en
FLUX 2 Dev for image generation on a free-tier lane.
free:flux-2-dev
Kimi K2 Thinking for multi-step reasoning on a free-tier lane.
free:kimi-k2-thinking
Muse Spark 1.3 for multimodal reasoning on a free-tier lane.
free:muse-spark-1.3-contributor-free
Apodex 1.1 Mini for coding and text generation on a free-tier lane.
free:apodex-1.1-mini
FLUX 1 Schnell for image generation and editing on a free-tier lane.
free:flux-1-schnell
Phoenix 1.0 for image generation on a free-tier lane.
free:phoenix-1.0
Space Bunny Alpha and Space Bunny Free are one preview model for coding, reasoning and multimodal input on a free-tier lane.
free:space-bunny-free
Lucid Origin for image generation and editing on a free-tier lane.
free:lucid-origin
Atria Dawn Preview for text generation on a free-tier lane.
free:atria-dawn-preview
Fledge Alpha for text generation on a free-tier lane.
free:fledge-alpha
MeloTTS for text-to-speech on a free-tier lane.
free:melotts
SDXL Lightning for image generation on a free-tier lane.
free:sdxl-lightning