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

ModelVendorHostVariantInputOutputBlended ↑?Cache readCache writeBatch inBatch outContextTokenizerLast changeConfidence?Source
meta-llama/Meta-Llama-3-8B-Instructmetadeepinfra–0.0300n/a0.0600n/a0.0375n/a–n/a–n/a–n/a–n/a8192–2025-08-22 ↓aggregatorlitellm
gemini-flash-image-2-5togethertogether––n/a0.0390n/a0.0390n/a–n/a–n/a–n/a–n/a–––officialofficial-together
gpt-oss-20b (GovCloud)openrouterakashmlfp40.02000.00560.100.02820.04000.0113–n/a–n/a–n/a–n/a131072o200k–apiopenrouter
Ministral 3Bazureazure–0.0400n/a0.0400n/a0.0400n/a–n/a–n/a–n/a–n/a128000––aggregatorlitellm
Prompt Guard 2 86Mmetagroq–0.0400n/a0.0400n/a0.0400n/a–n/a–n/a–n/a–n/a512––aggregatorlitellm
Voxtral Mini 3B 2507mistralaws-bedrock–0.0400n/a0.0400n/a0.0400n/a–n/a–n/a–n/a–n/a32768––aggregatorlitellm
Llama 3 8B Instructmetanovita–0.0400n/a0.0400n/a0.0400n/a–n/a–n/a–n/a–n/a8192–2026-01-13 ↓aggregatorlitellm
Gemma 4 E4B ITgoogledeepinfra–0.0200n/a0.10n/a0.0400n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
Ministral 3B (latest)mistralmistral–0.0400n/a0.0400n/a0.0400n/a–n/a–n/a–n/a–n/a128000––aggregatormodelsdev
tev1-4b-experimentaltogethertogether–0.0400n/a–n/a0.0400n/a–n/a–n/a–n/a–n/a–––officialofficial-together
qwen-image-20togethertogether––n/a0.0400n/a0.0400n/a–n/a–n/a–n/a–n/a–––officialofficial-together
flux-1-kontext-protogethertogether–0.0400n/a–n/a0.0400n/a–n/a–n/a–n/a–n/a–––officialofficial-together
flux1-1-protogethertogether–0.0400n/a–n/a0.0400n/a–n/a–n/a–n/a–n/a–––officialofficial-together
google-imagen-4-0-previewtogethertogether–0.0400n/a–n/a0.0400n/a–n/a–n/a–n/a–n/a–––officialofficial-together
IBM: Granite 4.0 Microopenrouteropenrouter–0.0170n/a0.11n/a0.0408n/a–n/a–n/a–n/a–n/a131000––apiopenrouter
IBM: Granite 4.0 Microopenroutercloudflareunknown0.0170n/a0.11n/a0.0408n/a–n/a–n/a–n/a–n/a131000––apiopenrouter
IBM: Granite 4.0 Microopenroutercloudflare–0.0170n/a0.11n/a0.0408n/a–n/a–n/a–n/a–n/a131000––apiopenrouter
Sao10K: Llama 3 8B Lunarisopenrouteropenrouter–0.04000.01200.05000.01500.04250.0128–n/a–n/a–n/a–n/a8192llama3–apiopenrouter
Sao10K: Llama 3 8B Lunarisopenrouterparasail–0.04000.01200.05000.01500.04250.0128–n/a–n/a–n/a–n/a8192llama3–apiopenrouter
Sao10K: Llama 3 8B Lunarisopenrouterdeepinfrafp80.04000.01200.05000.01500.04250.0128–n/a–n/a–n/a–n/a8192llama3–apiopenrouter
Sao10K/L3-8B-Lunaris-v1-Turbodeepinfradeepinfra–0.0400n/a0.0500n/a0.0425n/a–n/a–n/a–n/a–n/a8192–2025-10-04 ↑aggregatorlitellm
Nex AGI: Nex-N2.5-Miniopenrouteropenrouter–0.02500.00750.100.03020.04380.01320.00250.0008–n/a–n/a–n/a262144qwen2–apiopenrouter
Nex AGI: Nex-N2.5-Miniopenrouternex-agi–0.02500.00750.100.03020.04380.01320.00250.0008–n/a–n/a–n/a262144qwen2–apiopenrouter
meta-llama/Llama-3.2-11B-Vision-Instructmetadeepinfra–0.0490n/a0.0490n/a0.0490n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
Sao10K: Llama 3 8B Lunarisopenrouternovita–0.05000.01500.05000.01500.05000.0150–n/a–n/a–n/a–n/a8192llama3–apiopenrouter
Gemma 3 4B ITopenrouteraws-bedrock–0.0400n/a0.0800n/a0.0500n/a–n/a–n/a–n/a–n/a131072gemini–aggregatorlitellm
Sao10k L3 8B Lunaris novitanovita–0.0500n/a0.0500n/a0.0500n/a–n/a–n/a–n/a–n/a8192–2026-01-13 ↓aggregatorlitellm
L3 8B Stheno V3.2novitanovita–0.0500n/a0.0500n/a0.0500n/a–n/a–n/a–n/a–n/a8192–2026-01-13 ↓aggregatorlitellm
Gemma 4 E2B ITaws-bedrockaws-bedrock–0.0400n/a0.0800n/a0.0500n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
L3 8B Stheno V3.2novitanovita–0.0500n/a0.0500n/a0.0500n/a–n/a–n/a–n/a–n/a8192––aggregatormodelsdev
Sao10k L3 8B Lunaris novitanovita–0.0500n/a0.0500n/a0.0500n/a–n/a–n/a–n/a–n/a8192––aggregatormodelsdev
gemini-31-flash-imagetogethertogether––n/a0.0500n/a0.0500n/a–n/a–n/a–n/a–n/a–––officialofficial-together
perplexity/nemotron-3.5-lightning-30b-a3bnvidiaperplexity–0.0115n/a0.17n/a0.0511n/a0.0012n/a–n/a–n/a–n/a–––aggregatorlitellm
Qwen3.7 Flashalibabaalibaba–0.0296n/a0.12n/a0.0518n/a0.0030n/a0.0370n/a–n/a–n/a1000000–2026-10-04 ↓aggregatormodelsdev
LFM2-24B-A2Btogethertogether–0.0300n/a0.12n/a0.0525n/a–n/a–n/a–n/a–n/a32768––aggregatormodelsdev
gpt-image-2togethertogether––n/a0.0530n/a0.0530n/a–n/a–n/a–n/a–n/a–––officialofficial-together
Mistral Nemoopenrouterio-net–0.03210.01140.120.04150.05330.01900.02120.0075–n/a–n/a–n/a60288mistral–apiopenrouter
Qwen: Qwen3.7 Flashopenrouteropenrouter–0.03000.00900.130.03920.05500.01660.00600.00180.03800.0115–n/a–n/a1000000qwen2–apiopenrouter
Qwen: Qwen3.7 Flashopenrouteralibabaunknown0.03000.00900.130.03920.05500.01660.00600.00180.03800.0115–n/a–n/a1000000qwen2–apiopenrouter
gpt-oss-20b (GovCloud)openroutercoreweavefp40.03000.00850.130.03660.05500.01550.03000.0085–n/a–n/a–n/a131072o200k–apiopenrouter
Qwen2.5 7B Instructalibabadeepinfra–0.0400n/a0.10n/a0.0550n/a–n/a–n/a–n/a–n/a32000––aggregatorlitellm
meta-llama/Llama-Guard-3-8Bmetadeepinfra–0.0550n/a0.0550n/a0.0550n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
Qwen: Qwen3.7 Flashopenrouteralibaba–0.03000.00900.130.03920.05500.01660.00600.00180.03800.0115–n/a–n/a1000000qwen2–apiopenrouter
gpt-oss-20b (GovCloud)openrouterdekallm–0.02900.00820.140.03940.05680.01600.02900.0082–n/a–n/a–n/a131072o200k–apiopenrouter
Mistral: Mistral Small 3openrouteropenrouter–0.05000.01780.08000.02850.05750.0204–n/a–n/a–n/a–n/a32768mistral–apiopenrouter
Llama 3.1 8B Instructopenrouteropenrouter–0.05000.01500.08000.02410.05750.01730.02500.0075–n/a–n/a–n/a16384llama3–apiopenrouter
gpt-oss-20b (GovCloud)openrouterdeepinfra–0.03000.00850.140.03940.05750.0162–n/a–n/a–n/a–n/a131072o200k–apiopenrouter
Mistral: Mistral Small 3openrouterdeepinfrafp80.05000.01780.08000.02850.05750.0204–n/a–n/a–n/a–n/a32768mistral–apiopenrouter
Llama 3.1 8B Instructopenroutergroqunknown0.05000.01500.08000.02410.05750.01730.02500.0075–n/a–n/a–n/a16384llama3–apiopenrouter
Mistral: Mistral Small 3openrouterdeepinfra–0.05000.01780.08000.02850.05750.0204–n/a–n/a–n/a–n/a32768mistral–aggregatorlitellm

Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence