Model Catalog
54 models across 10 providers. Filter by tier, provider, or search by name.
All prices in credits per 1K tokens. 1 credit = $0.001 USD. Prices updated March 29, 2026.
Showing 54 of 54 models
| Model | Provider | Tier | Context | Max Out | $/1M In | $/1M Out | Notes |
|---|---|---|---|---|---|---|---|
| gpt-4.1 | OpenAI | ultra | 1M | 32,768 | $2.0 | $8.0 | Latest flagship, 1M context |
| gpt-4.1-mini | OpenAI | pro | 1M | 32,768 | $0.40 | $1.6 | Fast, cheap, 1M context |
| gpt-4.1-nano | OpenAI | core | 1M | 32,768 | $0.10 | $0.40 | Cheapest GPT-4 class |
| gpt-4o | OpenAI | ultra | 128K | 16,384 | $2.5 | $10.0 | Vision + text flagship |
| gpt-4o-mini | OpenAI | core | 128K | 16,384 | $0.15 | $0.60 | Best value general model |
| o1 | OpenAI | ultra | 200K | 100,000 | $15.0 | $60.0 | Deep reasoning, expensive |
| o3 | OpenAI | ultra | 200K | 100,000 | $2.0 | $8.0 | Reasoning, great value |
| o3-mini | OpenAI | pro | 200K | 100,000 | $1.1 | $4.4 | Fast reasoning |
| o4-mini | OpenAI | pro | 200K | 100,000 | $1.1 | $4.4 | Newest reasoning, 75% cached savings |
| codex-mini-latest | OpenAI | pro | 200K | 100,000 | $1.5 | $6.0 | Fine-tuned for coding (Codex CLI) |
| claude-opus-4.6 | Anthropic | ultra | 1M | 128,000 | $5.0 | $25.0 | Most intelligent, extended thinking |
| claude-sonnet-4.6 | Anthropic | ultra | 1M | 64,000 | $3.0 | $15.0 | Best balance of IQ and cost |
| claude-haiku-4.5 | Anthropic | core | 200K | 64,000 | $1.0 | $5.0 | Fast, cheap Claude |
| claude-opus-4.5 | Anthropic | ultra | 1M | 128,000 | $5.0 | $25.0 | Previous flagship |
| claude-sonnet-4.5 | Anthropic | ultra | 1M | 64,000 | $3.0 | $15.0 | Previous gen Sonnet |
| claude-3.5-haiku | Anthropic | core | 200K | 8,192 | $0.80 | $4.0 | Legacy fast model |
| gemini-2.5-pro | ultra | 1M | 65,536 | $1.3 | $10.0 | Context-tiered pricing at 200K | |
| gemini-2.5-flash | pro | 1M | 65,536 | $0.30 | $2.5 | Best value large context | |
| gemini-2.5-flash-lite | core | 1M | 65,536 | $0.10 | $0.40 | Absurdly cheap, 1M context | |
| grok-4.20 | xAI | ultra | 2M | 16,384 | $2.0 | $6.0 | Latest flagship, lowest hallucination |
| grok-4.1-fast | xAI | core | 2M | 16,384 | $0.20 | $0.50 | 2M context at $0.20 — insane value |
| grok-3 | xAI | ultra | 131K | 16,384 | $3.0 | $15.0 | Premium reasoning |
| grok-3-mini | xAI | core | 131K | 16,384 | $0.25 | $0.50 | Affordable reasoning |
| grok-code-fast | xAI | pro | 256K | 16,384 | $0.20 | $1.5 | Coding optimized |
| deepseek-chat | DeepSeek | core | 64K | 8,192 | $0.27 | $1.1 | Ultra-cheap general use ($0.07 cached) |
| deepseek-reasoner | DeepSeek | pro | 64K | 8,192 | $0.55 | $2.2 | Cheapest reasoning model |
| mistral-large-3 | Mistral | pro | 128K | 4,096 | $0.50 | $1.5 | Flagship, EU data residency |
| mistral-medium-3.1 | Mistral | pro | 32K | 4,096 | $0.40 | $2.0 | Balanced mid-tier |
| mistral-small-3.2 | Mistral | core | 32K | 4,096 | $0.07 | $0.20 | Cheapest Mistral |
| codestral-2508 | Mistral | pro | 32K | 8,192 | $0.30 | $0.90 | Code generation specialist |
| pixtral-12b | Mistral | core | 32K | 4,096 | $0.10 | $0.10 | Vision model |
| ministral-3b | Mistral | core | 32K | 4,096 | $0.10 | $0.10 | Tiny, ultra-cheap |
| ministral-8b | Mistral | core | 32K | 4,096 | $0.15 | $0.15 | Small, cheap |
| ministral-14b | Mistral | core | 32K | 4,096 | $0.20 | $0.20 | Mid-small, cheap |
| gpt-oss-120b-cerebras | Cerebras | pro | 128K | 8,192 | $0.22 | $0.68 | Open-source 120B, 3K t/s |
| llama-3.1-8b-cerebras | Cerebras | core | 128K | 8,192 | $0.06 | $0.14 | Cheapest, 2.2K t/s, free tier |
| glm-4.7-cerebras | Cerebras | ultra | 128K | 8,192 | $1.2 | $3.6 | Highest IQ on Cerebras |
| llama-3.3-70b-groq | Groq | core | 128K | 32,768 | $0.59 | $0.79 | 394 t/s, fast inference |
| llama-4-scout-groq | Groq | core | 128K | 32,768 | $0.11 | $0.34 | 594 t/s, newest Llama |
| llama-3.1-8b-groq | Groq | core | 128K | 32,768 | $0.05 | $0.08 | Cheapest Groq model |
| gpt-oss-120b-groq | Groq | pro | 128K | 32,768 | $0.15 | $0.60 | Open-source 120B at 500 t/s |
| qwen3-32b-groq | Groq | pro | 128K | 32,768 | $0.29 | $0.59 | Qwen on Groq hardware |
| kimi-k2-groq | Groq | pro | 128K | 32,768 | $1.0 | $3.0 | Moonshot AI Kimi |
| llama-3.3-70b-cf | Cloudflare | core | 128K | 8,192 | $0.29 | $2.3 | 70B on edge, FP8 |
| llama-4-scout-cf | Cloudflare | core | 128K | 8,192 | $0.10 | $0.44 | Llama 4 with vision |
| gpt-oss-120b-cf | Cloudflare | pro | 128K | 8,192 | $0.35 | $0.75 | Open-source 120B on edge |
| llama-3.1-8b-cf | Cloudflare | core | 128K | 8,192 | $0.04 | $0.38 | Cheapest Cloudflare model |
| mistral-small-cf | Cloudflare | core | 32K | 8,192 | $0.35 | $0.56 | Mistral on Cloudflare edge |
| qwen-coder-cf | Cloudflare | pro | 32K | 8,192 | $0.30 | $0.55 | Qwen coding model on edge |
| deepseek-r1-cf | Cloudflare | pro | 32K | 8,192 | $0.50 | $4.9 | Distilled reasoning on edge |
| gemma-3-12b-cf | Cloudflare | core | 32K | 8,192 | $0.15 | $0.75 | Google Gemma on edge |
| mimo-v2-flash | Mimo | core | 256K | 8,192 | $0.09 | $0.29 | 309B MoE, cheapest Xiaomi model |
| mimo-v2-pro | Mimo | ultra | 1M | 16,384 | $1.0 | $3.0 | 1T+ params, 1M context flagship |
| mimo-v2-omni | Mimo | pro | 262K | 8,192 | $0.40 | $2.0 | Multimodal: vision, audio, video |
Tier Guide
Core — Fast, cheap. Good for simple tasks.
Pro — Balanced quality/cost. Workhorses.
Ultra — Best quality. Use sparingly.
Pricing
Prices are in USD per 1 million tokens.
1 credit = $0.001 USD.
Cached/batch pricing may be lower.
Need a Model?
We add new models weekly based on demand.
Contact us to request a specific model.