the models · 64
Every model, one room.
The union of the wire catalog: each model names the providers that serve it, the window it reads, the exact-match price rows and the measured energy rows. What the catalog does not carry, the room says plainly · a missing number is a fact, never a zero.
Vendored from the released binary · supernovae-st/nika@5d61b7e13f1f (v0.107.0) · digest-verified, re-derived at build, gated in CI
The context axis
The axis draws the canonical catalog · the spec-named seats whose models declare a window. The register below is the wider wire union; each count names its facet.
29 models the catalog knows, from 32k to 1049k tokens of context. 7 of them want no key at all.
- mistral-small-latest32k
- deepseek-chat64k
- qwen3.5:4b128k
- llama3.2:3b128k
- qwen3.5-4b128k
- llamacpp/default128k
- localai/default128k
- Qwen/Qwen3-8B128k
- mistral-large-latest128k
- llama-3.3-70b-versatile128k
- llama-3.1-8b-instant128k
- anthropic/claude-sonnet-4-20250514128k
- anthropic/claude-haiku-4-5-20251001128k
- meta/llama-3.1-70b-instruct128k
- kimi-k2128k
- grok-3131k
- grok-3-mini-fast131k
- claude-sonnet-4-20250514200k
- claude-haiku-4-5-20251001200k
- kimi-k2.5256k
- Qwen/Qwen3.5-397B-A17B:fastest262k
- Qwen/Qwen3.5-9B:cheapest262k
- nvidia/nemotron-3-super-120b-a12b262k
- nvidia/nemotron-3-nano-30b-a3b262k
- gpt-5.2272k
- gpt-5-mini272k
- mock-default1000k
- gemini-2.5-flash1049k
- gemini-2.0-flash1049k
○ no key needed · ● a key, held by you · ◇ declared reasoning · ◆ takes images. A log scale, because the range is five doublings wide. Context and capabilities derive from the catalog the engine ships; the pricing rows it carries are empty today, so this page does not draw a price it does not have.
The register
cloudflare · 128k context
cloudflare · 128k context
sambanova · 128k context
sambanova · 128k context
- MiniMax-M21 seat
minimax · 245k context
- MiniMax-VL-011 seat
minimax · 100k context
- Qwen/Qwen3-8B2 seats
native · vllm · 128k context
huggingface · 262k context
- Qwen/Qwen3.5-9B:cheapest1 seat
huggingface · 262k context
fireworks · 128k context
fireworks · 128k context
bedrock · 128k context
bedrock · 128k context
openrouter · 128k context
openrouter · 128k context
- claude-haiku-4-5-202510011 seat · priced
anthropic · 200k context
- claude-sonnet-4-202505141 seat
anthropic · 200k context
- command-r1 seat
cohere · 128k context
- command-r-plus1 seat
cohere · 128k context
databricks · 128k context
- deepseek-chat1 seat · priced
deepseek · 64k context
- default2 seats
llamacpp · localai · 128k context
- gemini-2.0-flash2 seats
gemini · vertex · 1.0m context
- gemini-2.5-flash2 seats
gemini · vertex · 1.0m context
- glm-4-flash1 seat
zhipu · 128k context
- glm-4.51 seat
zhipu · 128k context
- gpt-4o1 seat
azure · 128k context
- gpt-4o-mini1 seat
azure · 128k context
- gpt-5-mini1 seat · priced
openai · 272k context
- gpt-5.21 seat · priced
openai · 272k context
- grok-31 seat · priced
xai · 131k context
- grok-3-mini-fast1 seat · priced
xai · 131k context
- jamba-1.5-large1 seat
ai21 · 256k context
- jamba-1.5-mini1 seat
ai21 · 256k context
- kimi-k21 seat
moonshot · 128k context
- kimi-k2.51 seat
moonshot · 256k context
- llama-3.1-8b1 seat
cerebras · 128k context
- llama-3.1-8b-instant1 seat · priced
groq · 128k context
- llama-3.3-70b1 seat
cerebras · 128k context
- llama-3.3-70b-versatile1 seat · priced
groq · 128k context
- llama3.2:3b1 seat
ollama · 128k context
together · 128k context
hyperbolic · 128k context
together · 128k context
deepinfra · 1.0m context
deepinfra · 128k context
- meta/llama-3.1-70b-instruct1 seat · priced
nvidia · 128k context
replicate · 8k context
replicate · 8k context
- mistral-large-latest1 seat · priced
mistral · 128k context
- mistral-small-latest1 seat · priced
mistral · 32k context
- mock-default1 seat
mock · 1m context
- nvidia/nemotron-3-nano-30b-a3b1 seat · priced
nvidia · 262k context
- nvidia/nemotron-3-super-120b-a12b1 seat · priced
nvidia · 262k context
- palmyra-x-0041 seat
writer · 128k context
- qwen-max1 seat
qwen · 32k context
- qwen-turbo1 seat
qwen · 1m context
- qwen-vl-plus1 seat
qwen · 32k context
- qwen3.5-4b1 seat
lmstudio · 128k context
- qwen3.5:4b1 seat
ollama · 128k context
- sonar1 seat
perplexity · 128k context
- sonar-pro1 seat
perplexity · 200k context
- voyage-3-large1 seat
voyage · 32k context
- voyage-3-lite1 seat
voyage · 32k context