Browse provider-agnostic model specs, compare prices across providers, and open a model page for the details. No cart needed — just a fast way to pick your next model.
Last D1 sync Jul 6, 04:55 PM · +0 / ~0 / -0 models
This page's cache
This is the actual header object returned by this route. Returning these headers is the caching code: Cache-Control sets freshness/SWR and Cache-Tag gives us a precise purge handle.
/public, max-age=300, stale-while-revalidate=3600catalogcatalog:indexWorkers Cache derives the key from this path/query, plus the Worker entrypoint and current Worker version.
export const Route = createFileRoute('/')({
headers: () => ({
'Cache-Control': 'public, max-age=300, stale-while-revalidate=3600',
'Cache-Tag': 'catalog,catalog:index',
}),
})Nothing pinged yet.
235 models
Claude Sonnet 5
Everyday Claude agent model for coding, planning, browsing, and general work
From $2 · 1M ctx
11 providers
LongCat-2.0
Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window
From Quote · 1M ctx
0 providers
Ornith 1.0 31B
Open coding-reasoning model for repository tasks and self-improving agents
From Quote · 262.1K ctx
0 providers
Ornith 1.0 35B
Large coding-reasoning model for agentic software tasks and RL search
From Quote · 262.1K ctx
0 providers
Ornith 1.0 397B
Large coding-reasoning model for agentic software tasks and RL search
From Quote · 262.1K ctx
0 providers
Ornith 1.0 9B
Open coding-reasoning model for repository tasks and self-improving agents
From Quote · 262.1K ctx
0 providers
Fugu
Multi-agent model for routing expert agents across complex analytical tasks
From Quote · 1M ctx
1 provider
Fugu Ultra
Quality-first multi-agent model for hard research, analysis, and competitions
From $5 · 1M ctx
3 providers
GLM-5.2
Open flagship GLM for long-horizon coding agents and million-token context work
From $1.4 · 1M ctx
1 provider
Kimi K2.7 Code
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking
From $0.74 · 262.1K ctx
6 providers
Kimi K2.7 Code Highspeed
Lower-latency Kimi Code variant for interactive edits and coding-agent loops
From $1.9 · 262.1K ctx
4 providers
Claude Fable 5
Claude model for creative writing, analysis, and controlled agent workflows
From $10 · 1M ctx
9 providers
North Mini Code
Cohere coding model for practical software engineering and agentic edits
From Free · 256K ctx
1 provider
MiMo-V2.5-Pro-UltraSpeed
MiMo pro model for strong multimodal reasoning and agent execution
From $1.31 · 1.0M ctx
1 provider
Nemotron 3 Ultra 550B A55B
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
From $0.5 · 1M ctx
4 providers
Nemotron 3.5 Content Safety
Safety model for policy screening, moderation, and risk-aware routing workflows
From Quote · 128K ctx
0 providers
MAI-Code-1-Flash
Microsoft coding model built for fast, efficient assistance in everyday developer workflows
From Quote · 256K ctx
0 providers
Qwen3.7 Plus
Multimodal Qwen workhorse for long-context agents, visual inputs, and coding
From $0.4 · 1M ctx
2 providers
MiniMax-M3
MiniMax multimodal model for long-context coding, perception, and agent planning
From $0.3 · 512K ctx
1 provider
Step 3.7 Flash
Newer StepFun flash model for faster agents, coding, and multimodal prompts
From $0.2 · 256K ctx
4 providers
Claude Opus 4.8
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents
From $5 · 1M ctx
9 providers
Qwen3.7 Max
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
From $1.25 · 1M ctx
3 providers
Command A Plus
Cohere's stronger command model for multilingual agents and enterprise workflows
From $2.5 · 128K ctx
1 provider
Gemini 3.5 Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
From $1.5 · 1.0M ctx
10 providers
Gemini 3.1 Flash Lite
Low-latency Gemini model for high-volume multimodal and agent workloads
From $0.25 · 1.0M ctx
9 providers
GPT-5.5 Instant
Compact GPT model for low-latency assistance and high-volume workloads
From $5 · 400K ctx
1 provider
Mistral Medium (latest)
Balanced Mistral model for enterprise assistants, multilingual work, and tools
From $0.4 · 262.1K ctx
2 providers
Mistral Medium 3.5
Balanced Mistral model for enterprise assistants, multilingual work, and tools
From $1.5 · 262.1K ctx
1 provider
Nemotron 3 Nano Omni 30B A3B Reasoning
Open Nemotron omni model combining reasoning with text, vision, and audio
From Free · 256K ctx
2 providers
Qwen3.6 Flash
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $0.1875 · 1M ctx
2 providers
DeepSeek V4 Flash
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
From $0.09 · 1M ctx
10 providers
DeepSeek V4 Pro
Open MoE flagship with million-token context for coding and long agent runs
From $0.435 · 1M ctx
11 providers
GPT-5.5
Default frontier GPT for coding, computer use, research, and knowledge work
From $4.55 · 1.1M ctx
15 providers
GPT-5.5 Pro
Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding
From $27.27 · 1.1M ctx
8 providers
MiMo-V2.5
Open MiMo model for multimodal coding agents and long-context automation
From $0.105 · 1.0M ctx
6 providers
MiMo-V2.5-Pro
Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution
From $0.435 · 1.0M ctx
6 providers
Qwen3.6 27B
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $0.203 · 262.1K ctx
3 providers
GPT-Image-2
Image model for prompt-driven generation, editing, and visual design workflows
From $5 · 0 ctx
4 providers
Kimi K2.6
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
From Free · 262.1K ctx
12 providers
Hy3 preview
Tencent Hy reasoning model for coding, instruction following, and agent tasks
From $0.063 · 256K ctx
4 providers
Qwen3.6 Max Preview
Flagship Qwen model for complex reasoning, coding, and agentic workflows
From $1.3 · 262.1K ctx
1 provider
Grok 4.3
xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk
From $1.25 · 1M ctx
5 providers
Qwen3.6 35B-A3B
Open multimodal Qwen MoE for local agents that need vision, audio, and code
From $0.248 · 262.1K ctx
1 provider
Claude Opus 4.7
Stronger Opus tier for advanced software work and high-stakes reasoning
From $5 · 1M ctx
11 providers
Grok Build 0.1
Fast Grok coding model tuned for agentic engineering and iterative edits
From $1 · 256K ctx
2 providers
Nemotron 3 Content Safety
Safety model for policy screening, moderation, and risk-aware routing workflows
From Free · 128K ctx
1 provider
GLM-5.1
Strong GLM coding model for agentic engineering, terminals, and repository generation
From $1.4 · 200K ctx
1 provider
Gemma 4 26B A4B IT
Open Gemma instruction model for efficient chat and self-hosted deployments
From $0.06 · 262.1K ctx
8 providers
Gemma 4 31B IT
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
From Free · 262.1K ctx
11 providers
Gemma 4 E2B IT
Open Gemma instruction model for efficient chat and self-hosted deployments
From Quote · 131.1K ctx
0 providers
Gemma 4 E4B IT
Open Gemma instruction model for efficient chat and self-hosted deployments
From Quote · 131.1K ctx
0 providers
Qwen3.6 Plus
Earlier Qwen multimodal workhorse for million-token agent and document tasks
From $0.5 · 1M ctx
3 providers
Step 3.5 Flash 2603
StepFun flash model for efficient multimodal reasoning, coding, and tool use
From $0.1 · 256K ctx
1 provider
GLM-5V-Turbo
Fast GLM vision model for screenshots, documents, and multimodal agent tasks
From $5 · 200K ctx
1 provider
Llama Nemotron Rerank VL 1B v2
Reranking model for improving retrieval quality in search and recommendation systems
From Free · 128K ctx
1 provider
Nemotron Cascade 2 30B A3B
Nemotron model for efficient reasoning, coding, and specialized AI agents
From Quote · 256K ctx
0 providers
MiMo-V2-Omni
MiMo omni model for text, image, video, audio, and agents
From $0.14 · 262.1K ctx
4 providers
MiMo-V2-Pro
Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks
From $0.435 · 1.0M ctx
5 providers
MiniMax-M2.7
Open MiniMax flagship for coding agents, office automation, and complex environments
From $0.3 · 204.8K ctx
1 provider
MiniMax-M2.7-highspeed
Low-latency M2.7 variant for interactive coding plans and agent loops
From $0.6 · 204.8K ctx
1 provider
GPT-5.4 mini
Strong small GPT for coding subagents, quick tool use, and high-volume work
From $0.68 · 400K ctx
11 providers
GPT-5.4 nano
Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation
From $0.18 · 400K ctx
11 providers
GLM-5-Turbo
Faster GLM-5 lane for coding agents that need lower latency
From Quote · 200K ctx
0 providers
Mistral Small (latest)
Efficient Mistral model for fast chat, extraction, and production assistants
From $0.15 · 256K ctx
2 providers
Mistral Small 4
Fast Mistral production model for chat, extraction, and cost-sensitive agents
From $0.15 · 256K ctx
1 provider
Nemotron VoiceChat
Nemotron multimodal model for visual reasoning and agentic AI workflows
From Free · 128K ctx
1 provider
Nemotron 3 Super 120B A12B
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
From $0.05 · 262.1K ctx
7 providers
Grok 4.20 (Non-Reasoning)
Grok model for agentic tool use, reasoning, coding, and live assistance
From $1.25 · 1M ctx
1 provider
Grok 4.20 (Reasoning)
Reasoning Grok for document-heavy analysis and long-horizon tool use
From $1.25 · 1M ctx
2 providers
GPT-5.4
Agent-ready GPT for coding and computer-use workflows at a lower cost
From $2.2 · 1.1M ctx
15 providers
GPT-5.4 Pro
More exact GPT-5.4 tier for demanding professional reasoning and agent tasks
From $27 · 1.1M ctx
9 providers
GPT-5.3 Chat (latest)
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
From $1.75 · 128K ctx
3 providers
Gemini 3.1 Flash Lite Preview
Low-latency Gemini model for high-volume multimodal and agent workloads
From $0.25 · 1.0M ctx
7 providers
Nano Banana 2
Image model for prompt-driven generation, editing, and visual design workflows
From $0.5 · 65.5K ctx
5 providers
Qwen3.5 122B-A10B
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $0.4 · 262.1K ctx
1 provider
Qwen3.5 27B
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $0.3 · 262.1K ctx
1 provider
Qwen3.5 35B-A3B
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $0.25 · 262.1K ctx
1 provider
Qwen3.5 9B
Qwen instruction model for multilingual chat, reasoning, and tool use
From Quote · 262.1K ctx
0 providers
Gemini 3.1 Pro Preview
Reasoning-first Gemini preview for agentic coding and complex problem solving
From $2 · 1.0M ctx
10 providers
Gemini 3.1 Pro Preview Custom Tools
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
From $2 · 1.0M ctx
6 providers
Sarvam 30B
Efficient Indian-language reasoning model for chat, coding, and multilingual work
From $0.02 · 128K ctx
2 providers
Claude Sonnet 4.6
Claude workhorse for coding agents, careful analysis, and production cost control
From $3 · 1M ctx
13 providers
Qwen3.5 Plus
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $0.4 · 1M ctx
2 providers
Qwen3.5 397B-A17B
Large open Qwen multimodal MoE for visual agents and long technical tasks
From $0.6 · 262.1K ctx
1 provider
MiniMax-M2.5-highspeed
High-speed MiniMax model for low-latency coding and agent workflows
From $0.6 · 204.8K ctx
1 provider
GLM-5
General GLM flagship for coding, analysis, and tool-heavy engineering workflows
From $1 · 204.8K ctx
1 provider
MiniMax-M2.5
Prior MiniMax coding model for agent workflows, office edits, and automation
From $0.3 · 204.8K ctx
1 provider
Llama Nemotron Embed VL 1B v2
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
From Free · 32.8K ctx
1 provider
Claude Opus 4.6
High-end Claude for difficult coding, planning, and slower expert reasoning
From $5 · 1M ctx
7 providers
GPT-5.3 Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
From $1.6 · 400K ctx
11 providers
Step 3.5 Flash
StepFun flash lane for quick multimodal reasoning and coding assistance
From $0.09 · 256K ctx
6 providers
Nemotron Content Safety Reasoning 4B
Safety model for policy screening, moderation, and risk-aware routing workflows
From Free · 128K ctx
1 provider
GLM-4.7-Flash
Budget GLM lane for fast coding help, routing, and everyday automation
From Free · 200K ctx
1 provider
GLM-4.7-FlashX
Efficient GLM model for fast reasoning, coding, and agent workflows
From $0.07 · 200K ctx
1 provider
Kimi K2.5
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
From $0.3 · 262.1K ctx
12 providers
MiniMax-M2.1
Earlier MiniMax agent model for practical coding and productivity tasks
From $0.3 · 204.8K ctx
1 provider
GLM-4.7
Mature GLM model for dependable coding, reasoning, and structured agent tasks
From $0.6 · 204.8K ctx
1 provider
Gemini 3 Flash Preview
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
From $0.5 · 1.0M ctx
10 providers
MiMo-V2-Flash
MiMo flash model for fast multimodal assistance and agent workflows
From $0.09 · 262.1K ctx
6 providers
Nemotron 3 Nano 30B A3B
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
From Free · 262.1K ctx
5 providers
GPT-5.2
Reliable GPT generation for broad coding, writing, and tool-assisted product work
From $1.6 · 400K ctx
15 providers
GPT-5.2 Chat
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
From $1.75 · 128K ctx
3 providers
GPT-5.2 Codex
Code-specialist GPT for repository edits, reviews, and long-running software agents
From $1.6 · 400K ctx
10 providers
GPT-5.2 Pro
Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows
From $19 · 400K ctx
9 providers
Devstral 2
Mistral's coding-agent model for repository work, terminal tasks, and software fixes
From $0.4 · 262.1K ctx
2 providers
GLM-4.6V
GLM vision model for visual reasoning, documents, and multimodal agents
From $0.3 · 128K ctx
1 provider
Devstral 2 (latest)
Mistral coding agent model for repository tasks and software engineering workflows
From $0.4 · 262.1K ctx
2 providers
DeepSeek Chat
DeepSeek chat model for instruction following, coding, and analysis
From $0.14 · 1M ctx
6 providers
DeepSeek Reasoner
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
From $0.14 · 1M ctx
2 providers
GPT-Image-1.5
Image model for prompt-driven generation, editing, and visual design workflows
From $5 · 0 ctx
3 providers
Claude Opus 4.5 (latest)
Flagship Claude model for deep reasoning, coding, and long-horizon agents
From $5 · 200K ctx
4 providers
Nano Banana Pro
Nano Banana Pro for higher-fidelity image generation and design-heavy edits
From $2 · 65.5K ctx
4 providers
Gemini 3 Pro Preview
Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts
From $2 · 1.0M ctx
6 providers
GPT-5.1
Sharper GPT-5 generation for coding, product work, and tool-assisted tasks
From $1.1 · 400K ctx
13 providers
GPT-5.1 Chat
Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations
From $1.25 · 128K ctx
3 providers
GPT-5.1 Codex
Codex GPT for repository edits, code review, and practical software agents
From $1.1 · 400K ctx
10 providers
GPT-5.1 Codex Max
Coding-optimized GPT model for repository edits, reviews, and agentic software work
From $1.1 · 400K ctx
8 providers
GPT-5.1 Codex mini
Coding-optimized GPT model for repository edits, reviews, and agentic software work
From $0.22 · 400K ctx
9 providers
Kimi K2 Thinking
Thinking Kimi model for slower research passes, planning, and hard technical questions
From $0.3 · 262.1K ctx
9 providers
Kimi K2 Thinking Turbo
Kimi reasoning model for long-horizon research, planning, and tool use
From $1.15 · 262.1K ctx
2 providers
Claude Opus 4.5
Flagship Claude model for deep reasoning, coding, and long-horizon agents
From $5 · 200K ctx
2 providers
GPT OSS Safeguard 120B
Safety model for policy screening, moderation, and risk-aware routing workflows
From $0.15 · 131.1K ctx
1 provider
Llama 3.1 Nemotron Safety Guard 8B v3
Safety model for policy screening, moderation, and risk-aware routing workflows
From Quote · 128K ctx
0 providers
Nemotron Nano 12B v2 VL
Nemotron multimodal model for visual reasoning and agentic AI workflows
From $0.2 · 128K ctx
1 provider
MiniMax-M2
Efficient open MiniMax model built for coding agents and tool-heavy workflows
From $0.3 · 196.6K ctx
1 provider
Claude Haiku 4.5
Fast Claude model for responsive assistance, classification, and lightweight agents
From $1 · 200K ctx
2 providers
Claude Haiku 4.5 (latest)
Fast Claude lane for lightweight agents, office tasks, and responsive chat
From $1 · 200K ctx
6 providers
GPT-5 Pro
Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning
From $14 · 400K ctx
8 providers
GLM-4.6
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
From $0.6 · 204.8K ctx
1 provider
Gemini 2.5 Flash TTS
Speech generation model for controllable voice, narration, and audio delivery
From Quote · 32.8K ctx
0 providers
Gemini 2.5 Pro TTS
Speech generation model for controllable voice, narration, and audio delivery
From Quote · 32.8K ctx
0 providers
Claude Sonnet 4.5
Balanced Claude model for coding, analysis, agent workflows, and cost control
From $3 · 200K ctx
2 providers
Claude Sonnet 4.5 (latest)
Balanced Claude model for coding, analysis, agent workflows, and cost control
From $3 · 200K ctx
6 providers
Gemini Flash Latest
Fast Gemini model balancing multimodal reasoning, tool use, and cost
From $0.3 · 1.0M ctx
4 providers
Gemini Flash-Lite Latest
Low-latency Gemini model for high-volume multimodal and agent workloads
From $0.1 · 1.0M ctx
4 providers
Qwen3 Max
Flagship Qwen3 model for coding agents, complex reasoning, and tool use
From $1.2 · 262.1K ctx
2 providers
Qwen3-VL Plus
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $0.2 · 262.1K ctx
1 provider
GPT-5-Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
From $1.1 · 400K ctx
9 providers
Sarvam 105B
Flagship Indian-language reasoning model for enterprise multilingual applications
From $0.04 · 131.1K ctx
2 providers
Qwen3-Next 80B-A3B (Thinking)
Efficient Qwen thinking model for local reasoning, math, and coding agents
From $0.15 · 131.1K ctx
2 providers
Qwen3-Next 80B-A3B Instruct
Qwen instruction model for multilingual chat, reasoning, and tool use
From $0.15 · 131.1K ctx
2 providers
Nano Banana
Nano Banana image model for fast generation, edits, and character-consistent assets
From $0.3 · 32.8K ctx
4 providers
Nemotron Nano 9B v2
Compact Nemotron model for efficient reasoning and deployable AI agents
From $0.04 · 131.1K ctx
3 providers
GLM-4.5V
GLM vision model for visual reasoning, documents, and multimodal agents
From $0.6 · 64K ctx
1 provider
GPT-5
Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
From $1.1 · 400K ctx
14 providers
GPT-5 Chat (latest)
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
From $1.25 · 400K ctx
3 providers
GPT-5 Mini
Small GPT-5 for responsive agents, coding help, and everyday automation
From $0.22 · 400K ctx
13 providers
GPT-5 Nano
Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs
From $0.045 · 400K ctx
11 providers
Claude Opus 4.1
Flagship Claude model for deep reasoning, coding, and long-horizon agents
From $15 · 200K ctx
2 providers
Claude Opus 4.1 (latest)
Flagship Claude model for deep reasoning, coding, and long-horizon agents
From $15 · 200K ctx
3 providers
GPT OSS 120B
Open GPT reasoning model for self-hosted agents and controllable deployments
From Free · 131.1K ctx
24 providers
GPT OSS 20B
Open GPT reasoning model for self-hosted agents and controllable deployments
From Free · 131.1K ctx
16 providers
GLM-4.5
Hybrid-reasoning GLM release that made the 4.5 line broadly useful
From $0.6 · 131.1K ctx
1 provider
GLM-4.5-Air
Lighter GLM-4.5 variant for fast coding assistance and cheaper agents
From $0.2 · 131.1K ctx
1 provider
GLM-4.5-Flash
Efficient GLM model for fast reasoning, coding, and agent workflows
From Free · 131.1K ctx
1 provider
Qwen Flash
Efficient Qwen model for fast chat, extraction, and high-volume workloads
From $0.05 · 1M ctx
1 provider
Qwen3 Coder Flash
Qwen coding model for software agents, repository edits, and code reasoning
From $0.3 · 1M ctx
1 provider
Llama 3.3 Nemotron Super 49B v1.5
Nemotron model for efficient reasoning, coding, and specialized AI agents
From $0.1 · 131.1K ctx
2 providers
Qwen3 Coder Plus
Hosted Qwen coder for software agents, repo edits, and long-context code
From $1 · 1.0M ctx
2 providers
Devstral Medium
Mistral coding agent model for repository tasks and software engineering workflows
From $0.4 · 128K ctx
2 providers
Devstral Small
Mistral coding agent model for repository tasks and software engineering workflows
From $0.1 · 128K ctx
2 providers
Mistral Small 3.2
Efficient Mistral model for fast chat, extraction, and production assistants
From $0.1 · 128K ctx
1 provider
Gemini 2.5 Flash
Fast Gemini workhorse for multimodal apps where latency and price matter
From $0.21 · 1.0M ctx
13 providers
Gemini 2.5 Flash-Lite
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents
From $0.07 · 1.0M ctx
10 providers
Gemini 2.5 Pro
Google's proven reasoning model for coding, math, and multimodal analysis
From $0.87 · 1.0M ctx
13 providers
Mistral Nemotron
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
From Quote · 128K ctx
0 providers
o3-pro
High-effort o3 tier for difficult technical reasoning and careful answers
From $18 · 200K ctx
6 providers
Claude Opus 4
Flagship Claude model for deep reasoning, coding, and long-horizon agents
From $15 · 200K ctx
1 provider
Claude Opus 4 (latest)
Flagship Claude model for deep reasoning, coding, and long-horizon agents
From Quote · 200K ctx
0 providers
Claude Sonnet 4
Balanced Claude model for coding, analysis, agent workflows, and cost control
From $3 · 200K ctx
1 provider
Claude Sonnet 4 (latest)
Balanced Claude model for coding, analysis, agent workflows, and cost control
From Quote · 200K ctx
0 providers
Gemini Embedding 001
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
From $0.15 · 2.0K ctx
2 providers
Mistral Medium 3
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
From $0.4 · 131.1K ctx
2 providers
GPT-Image-1
OpenAI image model for production generation, edits, and brand-safe visual workflows
From $5 · 0 ctx
3 providers
o3
Deliberate o-series reasoner for hard math, coding, and multi-step analysis
From Free · 200K ctx
11 providers
o4-mini
Fast o-series model for compact reasoning, coding, and tool use
From Free · 200K ctx
12 providers
Llama 3.1 Nemotron 70B Instruct
Nemotron model for efficient reasoning, coding, and specialized AI agents
From Quote · 128K ctx
0 providers
GPT-4.1
Long-lived GPT workhorse for coding, instruction following, and production apps
From Free · 1.0M ctx
13 providers
GPT-4.1 mini
Affordable GPT-4.1 lane for fast coding help and structured extraction
From Free · 1.0M ctx
12 providers
GPT-4.1 nano
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks
From Free · 1.0M ctx
10 providers
Llama 3.1 Nemotron Ultra 253B
Flagship Nemotron model for high-throughput reasoning and complex agents
From Quote · 128K ctx
0 providers
Llama 3.3 Nemotron Super 49B v1
Nemotron model for efficient reasoning, coding, and specialized AI agents
From Quote · 131.1K ctx
0 providers
Llama 4 Maverick 17B Instruct
Open multimodal Llama for strong reasoning with efficient everyday serving
From Quote · 1M ctx
0 providers
Llama 4 Scout 17B Instruct
Open Llama with long-context vision for efficient multimodal agents
From Quote · 3.5M ctx
0 providers
Qwen3 235B-A22B
Large open Qwen MoE for multilingual reasoning, coding, and tool use
From $0.7 · 131.1K ctx
1 provider
Qwen3 32B
Dense open Qwen model for self-hosted chat, reasoning, and coding
From $0.7 · 131.1K ctx
1 provider
Qwen3-Coder 30B-A3B Instruct
Smaller Qwen coder for efficient local agents and repo-level fixes
From $0.45 · 262.1K ctx
1 provider
Qwen3-Coder 480B-A35B Instruct
Open Qwen coding heavyweight for repository reasoning and agentic engineering
From $1.5 · 262.1K ctx
1 provider
o1-pro
O-series reasoning model for hard analysis, math, coding, and planning
From $140 · 200K ctx
5 providers
Magistral Medium (latest)
Mistral reasoning model for transparent analysis, math, and complex decisions
From $2 · 128K ctx
2 providers
Command A
Cohere command model for multilingual enterprise agents, tools, and chat
From $2.5 · 256K ctx
2 providers
QwQ Plus
Qwen reasoning model for deliberate problem solving, math, and coding
From $0.8 · 131.1K ctx
1 provider
Claude Sonnet 3.7
Balanced Claude model for coding, analysis, agent workflows, and cost control
From Quote · 200K ctx
0 providers
DeepSeek-R1
Classic open reasoning model for transparent math, coding, and deliberate problem solving
From Free · 128K ctx
5 providers
Qwen-Omni Turbo
Qwen omni model for text, vision, audio, and multimodal agent tasks
From $0.07 · 32.8K ctx
1 provider
o3-mini
Smaller o-series reasoner for economical coding, math, and planning tasks
From Free · 200K ctx
11 providers
Gemini 2.0 Flash
Earlier Gemini Flash workhorse for responsive multimodal apps and tool use
From $0.1 · 1.0M ctx
2 providers
Gemini 2.0 Flash-Lite
Low-latency Gemini model for high-volume multimodal and agent workloads
From $0.052 · 1.0M ctx
2 providers
Llama-3.3-70B-Instruct
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
From Free · 128K ctx
2 providers
o1
O-series reasoning model for hard analysis, math, coding, and planning
From Free · 200K ctx
9 providers
Command R7B
Cohere retrieval model for long-context chat and enterprise RAG workflows
From $0.0375 · 128K ctx
4 providers
GPT-4o (2024-11-20)
GPT model for general reasoning, writing, coding, and tool-assisted tasks
From $2.5 · 128K ctx
6 providers
Mistral Large 2.1
Flagship Mistral model for advanced reasoning, coding, and multilingual work
From $2 · 131.1K ctx
2 providers
Mistral Large (latest)
Flagship Mistral model for advanced reasoning, coding, and multilingual work
From $0.5 · 262.1K ctx
2 providers
Mistral Large 3
Mistral's largest general model for enterprise agents, coding, and multilingual reasoning
From $0.5 · 262.1K ctx
2 providers
Pixtral Large (latest)
Mistral's larger vision model for document-heavy image understanding and chat
From $2 · 128K ctx
2 providers
Qwen Turbo
Efficient Qwen model for fast chat, extraction, and high-volume workloads
From $0.05 · 1M ctx
1 provider
Claude Haiku 3.5
Fast Claude model for responsive assistance, classification, and lightweight agents
From Quote · 200K ctx
0 providers
Claude Sonnet 3.5 v2
Balanced Claude model for coding, analysis, agent workflows, and cost control
From Quote · 200K ctx
0 providers
Whisper 3 Large
Open Whisper checkpoint for robust multilingual transcription and captioning
From Free · 448 ctx
3 providers
Whisper Large v3 Turbo
Speech transcription model for accurate audio-to-text and captioning workflows
From $0.0023 · 448 ctx
1 provider
Pixtral 12B
Mistral vision-language model for image understanding and multimodal chat
From $0.15 · 128K ctx
2 providers
Qwen2.5-VL 72B Instruct
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $2.8 · 131.1K ctx
1 provider
Command R
Cohere retrieval model for long-context chat and enterprise RAG workflows
From $0.15 · 128K ctx
4 providers
Command R+
Cohere's RAG workhorse for long-context enterprise search and tool use
From $2.5 · 128K ctx
6 providers
Nemotron Mini 4B Instruct
Compact Nemotron model for efficient reasoning and deployable AI agents
From Free · 128K ctx
1 provider
GPT-4o (2024-08-06)
GPT model for general reasoning, writing, coding, and tool-assisted tasks
From $2.5 · 128K ctx
6 providers
GPT-4o mini
Small omni GPT for cheap multimodal assistance and production-scale traffic
From Free · 128K ctx
11 providers
Mistral Nemo
Efficient Mistral-NVIDIA open model for multilingual chat and local deployment
From $0.15 · 128K ctx
2 providers
o3-deep-research
Research model for long-horizon investigation, synthesis, and analytical reports
From $9 · 200K ctx
6 providers
o4-mini-deep-research
Research model for long-horizon investigation, synthesis, and analytical reports
From $1.8 · 200K ctx
5 providers
Codestral (latest)
Mistral code model for completions, refactors, and developer IDE workflows
From $0.3 · 256K ctx
2 providers
GPT-4o
Omni-era GPT for multimodal chat, practical coding, and general assistants
From Free · 128K ctx
10 providers
GPT-4o (2024-05-13)
GPT model for general reasoning, writing, coding, and tool-assisted tasks
From $5 · 128K ctx
5 providers
Qwen-VL Max
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $0.8 · 131.1K ctx
1 provider
Qwen Max
Flagship Qwen model for complex reasoning, coding, and agentic workflows
From $1.6 · 32.8K ctx
1 provider
Claude Haiku 3
Legacy model retained for compatibility with older integrations
From Quote · 200K ctx
0 providers
Qwen Plus
Qwen instruction model for multilingual chat, reasoning, and tool use
From $0.4 · 1M ctx
1 provider
Qwen-VL Plus
Qwen vision-language model for visual reasoning, documents, and agent tasks
From $0.21 · 131.1K ctx
1 provider
Sonar
Fast web-grounded Sonar for current answers, citations, and lightweight retrieval
From $0.25 · 128K ctx
5 providers
Sonar Pro
Deeper Sonar search model with broader retrieval and stronger synthesis
From $3 · 200K ctx
5 providers
Sonar Reasoning Pro
Web-grounded Sonar for multi-step research questions that need cited reasoning
From $2 · 128K ctx
5 providers
GPT-4
GPT model for general reasoning, writing, coding, and tool-assisted tasks
From $30 · 8.2K ctx
5 providers
GPT-4 Turbo
Compact GPT model for low-latency assistance and high-volume workloads
From $9 · 128K ctx
8 providers
GPT-3.5-turbo
Compact GPT model for low-latency assistance and high-volume workloads
From $0.45 · 16.4K ctx
8 providers