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@25f502adb7ec (v0.111.0) · digest-verified, re-derived at build, gated in CI
The bench
1 published receipt: a room shows a measured answer only when a receipt names its model, with the evidence pack served beside it. Every other seat: run it yourself · the model-bench workflow in the public registry measures YOUR machine, and the first receipt shows what an honest one looks like.
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-4-6128k
- anthropic/claude-haiku-4-5-20251001128k
- meta/llama-3.1-70b-instruct128k
- kimi-k2128k
- grok-3131k
- grok-3-mini-fast131k
- claude-sonnet-4-6200k
- 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 price axis
Every priced model, seated at its cheapest recorded output seat. The taller accent ticks are open weights: the seats you could also host yourself.
12 priced · $0.08 → $15 out/Mtok · log scale · 6 open weights
The register
- @cf/meta/llama-3.1-8b-instruct1 seat · 128k
cloudflare · 128k context
- @cf/meta/llama-3.3-70b-instruct-fp8-fast1 seat · 128k
cloudflare · 128k context
- Meta-Llama-3.1-8B-Instruct1 seat · 128k
sambanova · 128k context
- Meta-Llama-3.3-70B-Instruct1 seat · 128k
sambanova · 128k context
- MiniMax-M21 seat · 245k
minimax · 245k context
- MiniMax-VL-011 seat · 100k
minimax · 100k context
- Qwen/Qwen3-8B2 seats · 128k
native · vllm · 128k context
- Qwen/Qwen3.5-397B-A17B:fastest1 seat · 262k
huggingface · 262k context
- Qwen/Qwen3.5-9B:cheapest1 seat · 262k
huggingface · 262k context
- accounts/fireworks/models/llama-v3p1-8b-instruct1 seat · 128k
fireworks · 128k context
- accounts/fireworks/models/llama-v3p3-70b-instruct1 seat · 128k
fireworks · 128k context
- anthropic.claude-haiku-4-5-20251001-v1:01 seat · 128k
bedrock · 128k context
- anthropic.claude-sonnet-4-6-v1:01 seat · 128k
bedrock · 128k context
- anthropic/claude-haiku-4-5-202510011 seat · 128k
openrouter · 128k context
- anthropic/claude-sonnet-4-61 seat · 128k
openrouter · 128k context
- claude-haiku-4-5-202510011 seat · 200k · $5 out
anthropic · 200k context
- claude-sonnet-4-61 seat · 200k · $15 out
anthropic · 200k context
- command-r1 seat · 128k
cohere · 128k context
- command-r-plus1 seat · 128k
cohere · 128k context
- databricks-meta-llama-3-1-70b-instruct1 seat · 128k
databricks · 128k context
- deepseek-chat1 seat · 64k · $0.28 out⬡ open
deepseek · 64k context
- default2 seats · 128k
llamacpp · localai · 128k context
- gemini-2.0-flash2 seats · 1.0m
gemini · vertex · 1.0m context
- gemini-2.5-flash2 seats · 1.0m
gemini · vertex · 1.0m context
- glm-4-flash1 seat · 128k
zhipu · 128k context
- glm-4.51 seat · 128k
zhipu · 128k context
- gpt-4o1 seat · 128k
azure · 128k context
- gpt-4o-mini1 seat · 128k
azure · 128k context
- gpt-5-mini1 seat · 272k · $2 out
openai · 272k context
- gpt-5.21 seat · 272k · $14 out
openai · 272k context
- grok-31 seat · 131k · $15 out
xai · 131k context
- grok-3-mini-fast1 seat · 131k · $4 out
xai · 131k context
- jamba-1.5-large1 seat · 256k
ai21 · 256k context
- jamba-1.5-mini1 seat · 256k
ai21 · 256k context
- kimi-k21 seat · 128k
moonshot · 128k context
- kimi-k2.51 seat · 256k
moonshot · 256k context
- llama-3.1-8b1 seat · 128k
cerebras · 128k context
- llama-3.1-8b-instant1 seat · 128k · $0.08 out⬡ open
groq · 128k context
- llama-3.3-70b1 seat · 128k
cerebras · 128k context
- llama-3.3-70b-versatile1 seat · 128k · $0.79 out⬡ open
groq · 128k context
- llama3.2:3b1 seat · 128k
ollama · 128k context
- meta-llama/Llama-3.1-8B-Instruct-Turbo1 seat · 128k
together · 128k context
- meta-llama/Llama-3.3-70B-Instruct1 seat · 128k
hyperbolic · 128k context
- meta-llama/Llama-3.3-70B-Instruct-Turbo1 seat · 128k
together · 128k context
- meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP81 seat · 1.0m
deepinfra · 1.0m context
- meta-llama/Meta-Llama-3.1-8B-Instruct1 seat · 128k
deepinfra · 128k context
- meta/llama-3.1-70b-instruct1 seat · 128k⬡ open
nvidia · 128k context
- meta/meta-llama-3-70b-instruct1 seat · 8k
replicate · 8k context
- meta/meta-llama-3-8b-instruct1 seat · 8k
replicate · 8k context
- mistral-large-latest1 seat · 128k · $1.5 out⬡ open
mistral · 128k context
- mistral-small-latest1 seat · 32k · $0.6 out⬡ open
mistral · 32k context
- mock-default1 seat · 1m
mock · 1m context
- nvidia/nemotron-3-nano-30b-a3b1 seat · 262k⬡ open
nvidia · 262k context
- nvidia/nemotron-3-super-120b-a12b1 seat · 262k · $0.8 out⬡ open
nvidia · 262k context
- palmyra-x-0041 seat · 128k
writer · 128k context
- qwen-max1 seat · 32k
qwen · 32k context
- qwen-turbo1 seat · 1m
qwen · 1m context
- qwen-vl-plus1 seat · 32k
qwen · 32k context
- qwen3.5-4b1 seat · 128k
lmstudio · 128k context
- qwen3.5:4b1 seat · 128k
ollama · 128k context
- sonar1 seat · 128k
perplexity · 128k context
- sonar-pro1 seat · 200k
perplexity · 200k context
- voyage-3-large1 seat · 32k
voyage · 32k context
- voyage-3-lite1 seat · 32k
voyage · 32k context