Offerings

Every active offering: a model as served by one host, with its current canonical price. Sort by clicking a column header; filter with the row below. Prices are USD per 1M tokens unless the unit toggle is set to per 1M characters (an approximation using a measured, blended tokens-per-character ratio).

Showing every active offering, including the long tail. Show curated models only

ModelVendorHostVariantInput ↑OutputCache readCache writeBatch inBatch outContextTokenizerLatency / throughput soonLast changeConfidenceSource
Google: Gemma 4 31B (free)openroutergoogle–0.0000000.0000000.0000000.000000–n/a–n/a–n/a–n/a262144gemma––mediumlitellm
learnlm-1.5-pro-experimentalgooglegoogle–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a32767–––mediumlitellm
Google: Lyria 3 Clip Previewopenroutergoogle–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a1048576–––mediumlitellm
Google: Lyria 3 Pro Previewopenroutergoogle–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a1048576–––mediumlitellm
pplx-70b-onlineperplexityperplexity–0.000000n/a2.800000n/a–n/a–n/a–n/a–n/a4096–––mediumlitellm
pplx-7b-onlineperplexityperplexity–0.000000n/a0.280000n/a–n/a–n/a–n/a–n/a4096–––mediumlitellm
sonar-medium-onlineperplexityperplexity–0.000000n/a1.800000n/a–n/a–n/a–n/a–n/a12000–––mediumlitellm
sonar-small-onlineperplexityperplexity–0.000000n/a0.280000n/a–n/a–n/a–n/a–n/a12000–––mediumlitellm
Prism-ML/Ternary-Bonsai-27Btogethertogether–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a262144–––mediumlitellm
meta/llama-3.1-70b-instruct-maasmetagoogle-vertex–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediumlitellm
meta/llama-3.1-8b-instruct-maasmetagoogle-vertex–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediumlitellm
meta/llama-3.2-90b-vision-instruct-maasmetagoogle-vertex–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediumlitellm
meta/llama3-405b-instruct-maasmetagoogle-vertex–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a32000–––mediumlitellm
meta/llama3-70b-instruct-maasmetagoogle-vertex–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a32000–––mediumlitellm
meta/llama3-8b-instruct-maasmetagoogle-vertex–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a32000–––mediumlitellm
GLM-4.7-Flashzhipuzhipu–0.000000n/a0.000000n/a0.000000n/a0.000000n/a–n/a–n/a202752–––mediumlitellm
GLM-4.5-Flashzhipuzhipu–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a131072–––mediumlitellm
labs-leanstral-1-5mistralmistral–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a262144–––mediumlitellm
labs-leanstral-1-5-1mistralmistral–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a262144–––mediumlitellm
lyria-3.5-clip-previewgooglegoogle–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a131072–––mediumlitellm
lyria-3.5-pro-previewgooglegoogle–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a131072–––mediumlitellm
lyria-3.5googlegoogle–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a131072–––mediumlitellm
lyria-realtime-expgooglegoogle–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a1048576–––mediumlitellm
ALLaM-2-7bsdaiagroq–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a4096–––mediummodelsdev
GLM-4.6V-Flashzhipuzhipu–0.000000n/a0.000000n/a0.000000n/a0.000000n/a–n/a–n/a128000–––mediummodelsdev
Meta: Llama 4 Maverickmetameta–0.0000000.0000000.0000000.000000–n/a–n/a–n/a–n/a1048576llama3––mediummodelsdev
Groq-Llama-4-Maverick-17B-128E-Instructmetameta–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediummodelsdev
Llama-4-Scout-17B-16E-Instruct-FP8metameta–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediummodelsdev
Cerebras-Llama-4-Maverick-17B-128E-Instructmetameta–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediummodelsdev
Meta: Llama 3.3 70B Instructmetameta–0.0000000.0000000.0000000.000000–n/a–n/a–n/a–n/a128000llama3––mediummodelsdev
Llama-3.3-8B-Instructmetameta–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediummodelsdev
Cerebras-Llama-4-Scout-17B-16E-Instructmetameta–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediummodelsdev
North Mini Codecoherecohere–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a256000–––mediummodelsdev
North Small Translatecoherecohere–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a32768–––mediummodelsdev
BGE M3nvidianvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a8192–––mediummodelsdev
Poolside: Laguna XS 2.1 (free)openrouternvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a262144–––mediummodelsdev
dracarys-llama-3.1-70b-instructnvidianvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediummodelsdev
GLM-5.3-Flashzhipunvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a1048575–––mediummodelsdev
GLM-5.2zhipunvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a1048575–––mediummodelsdev
GLM-5.3zhipunvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a1048576–––mediummodelsdev
Thinking Machines: Inkling (free)openrouternvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a524288–––mediummodelsdev
FLUX.1-schnellnvidianvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a77–––mediummodelsdev
FLUX.1-devnvidianvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a4096–––mediummodelsdev
FLUX.1-Kontext-devnvidianvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a40960–––mediummodelsdev
FLUX.2 Klein 4Bnvidianvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a40960–––mediummodelsdev
Llama Guard 4 12Bmetanvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediummodelsdev
Meta: Muse Glimmer 30Bopenrouternvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a131072–––mediummodelsdev
esmfoldnvidianvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediummodelsdev
Meta: Llama 3.3 70B Instructmetanvidia–0.0000000.0000000.0000000.000000–n/a–n/a–n/a–n/a128000llama3––mediummodelsdev
Llama-3.2-90B-Vision-Instructmetanvidia–0.000000n/a0.000000n/a–n/a–n/a–n/a–n/a128000–––mediummodelsdev