Models
Every model, one endpoint.
llm11 can call 334 text models from 54 labs. Prices below are what the providers charge per million tokens right now, read from the live catalogue and refreshed daily, so nothing on these pages is typed in by hand.
Browse by lab
OpenAI GPT
58 models, $0.036 to $263 per 1M
Qwen
53 models, $0.055 to $6.00 per 1M
Google Gemini
20 models, $0.063 to $4.50 per 1M
Mistral
19 models, $0.022 to $3.00 per 1M
Anthropic Claude
15 models, $2.00 to $30 per 1M
DeepSeek
14 models, $0.093 to $1.41 per 1M
Meta Llama
8 models, $0.057 to $0.400 per 1M
SpaceXAI Grok
7 models, $1.25 to $3.00 per 1M
Amazon Nova
5 models, $0.061 to $5.00 per 1M
Cohere Command
5 models, $0.066 to $4.38 per 1M
Newest
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Anthropic Claude Sonnet 5.5 | $2.00 | $10 | 1M | |
| Qwen Qwen3.8 Max Prime | $4.00 | $12 | 1M | |
| Anthropic Claude Opus 5.5 | $4.00 | $20 | 1M | |
| Cohere Command A+ | $0.300 | $1.50 | 192K | |
| OpenAI GPT-6 Luna | $0.100 | $0.500 | 1.05M | |
| OpenAI GPT-6 Luna Pro | $0.100 | $0.500 | 1.05M | |
| OpenAI GPT-6 Sol | $2.00 | $10 | 1.05M | |
| OpenAI GPT-6 Sol Pro | $2.00 | $10 | 1.05M |
What the router picks from
Each routing pack is a price band over this list, thinned to a spread of models. These are today’s members. Routing decisions are made by Jev, TypeSafe AI’s System One model.
llm11-fastThe cheapest end of the catalogue. Best for high-volume, low-stakes traffic.
llm11-balancedA working mix of cheap and capable models. The sane default.
llm11-smartThe most capable models available, priced at whatever that costs.
More labs
Callable by model id, outside the routing packs.
- Z.ai
- MiniMax
- MoonshotAI
- Tencent
- AionLabs
- ByteDance Seed
- Meta
- NVIDIA
- Perplexity
- Xiaomi
- Sakana
- inclusionAI
- Nous
- Sao10K
- TheDrummer
- Upstage
- IBM
- Inception
- Inference.net
- Microsoft
- Morph
- Nex AGI
- Perceptron
- Poolside
- rekaai
- Relace
- StepFun
- Thinking Machines
- anthracite-org
- Arcee AI
- Baidu
- ByteDance
- Fireworks
- gryphe
- Kwaipilot
- Mancer
- Meituan
- OpenRouter
- PrismML
- stealth
- unbiased
- undi95
- Venice
- Writer