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
gpt-oss-20b (GovCloud)openrouternovita–0.04000.01130.150.04230.06750.0190–n/a–n/a–n/a–n/a131072o200k2026-01-13 ↓aggregatorlitellm
DeepSeek R1 0528 Qwen3 8Bdeepseeknovita–0.0600n/a0.0900n/a0.0675n/a–n/a–n/a–n/a–n/a128000–2026-01-13 ↓aggregatorlitellm
Inception: Mercury 2.5openrouterinception–0.0400n/a0.15n/a0.0675n/a0.0040n/a–n/a–n/a–n/a260000––apiopenrouter
GPT-5 nanoopenaiopenaiunknown0.02500.00700.200.05630.06880.01940.00250.0007–n/a–n/a–n/a400000o200k–apiopenrouter
GPT-5 nanoopenaiopenai–0.02500.00700.200.05630.06880.01940.00250.0007–n/a–n/a–n/a400000o200k–apiopenrouter
nvidia/NVIDIA-Nemotron-Nano-9B-v2deepinfradeepinfra–0.0400n/a0.16n/a0.0700n/a–n/a–n/a–n/a–n/a131072––aggregatorlitellm
pplx-7b-onlineperplexityperplexity–freen/a0.28n/a0.0700n/a–n/a–n/a–n/a–n/a4096–2024-01-31 ↓aggregatorlitellm
sonar-small-onlineperplexityperplexity–freen/a0.28n/a0.0700n/a–n/a–n/a–n/a–n/a12000––aggregatorlitellm
baichuan-m2-32bnovitanovita–0.0700n/a0.0700n/a0.0700n/a–n/a–n/a–n/a–n/a131072–2026-01-13 ↓aggregatorlitellm
Qwen2.5 7B Instructalibabanovita–0.0700n/a0.0700n/a0.0700n/a–n/a–n/a–n/a–n/a32000–2026-01-13 ↓aggregatorlitellm
flux-2-maxtogethertogether–0.0700n/a–n/a0.0700n/a–n/a–n/a–n/a–n/a–––officialofficial-together
gpt-oss-120bopenrouteropenrouter–0.03700.01040.170.04790.07030.0198–n/a–n/a0.02960.00830.140.0383131072o200k–apiopenrouter
gpt-oss-120bopenrouterdeepinfra–0.03700.01040.170.04790.07030.0198–n/a–n/a–n/a–n/a131072o200k–apiopenrouter
gpt-oss-120bopenrouterdeepinfra–0.03700.01040.170.04790.07030.0198–n/a–n/a–n/a–n/a131072o200k2026-08-27 ↓aggregatorlitellm
Meta: Llama 3.2 1B Instructopenrouteropenrouter–0.02700.00810.200.06050.07050.0212–n/a–n/a–n/a–n/a60000llama3–apiopenrouter
Meta: Llama 3.2 1B Instructopenroutercloudflareunknown0.02700.00810.200.06050.07050.0212–n/a–n/a–n/a–n/a60000llama3–apiopenrouter
Meta: Llama 3.2 1B Instructopenroutercloudflare–0.02700.00810.200.06050.07050.0212–n/a–n/a–n/a–n/a60000llama3–apiopenrouter
arcee-ai/trinity-minitogethertogether–0.0450n/a0.15n/a0.0713n/a–n/a–n/a–n/a–n/a128000––aggregatorlitellm
Mistral Nemoopenrouternovitafp80.04000.01420.170.06050.07250.0258–n/a–n/a–n/a–n/a60288mistral–apiopenrouter
Mistral Nemoopenrouternovita–0.04000.01420.170.06050.07250.0258–n/a–n/a–n/a–n/a60288mistral2026-01-13 ↓aggregatorlitellm
us-gov-west-1/amazon.nova-micro-v1:0aws-bedrockaws-bedrock–0.0420n/a0.17n/a0.0735n/a0.0105n/a–n/a–n/a–n/a128000––aggregatorlitellm
Nemotron 3.5 Lightning 30B A3Bopenrouterdarkbloomint40.0390n/a0.18n/a0.0743n/a0.0195n/a–n/a–n/a–n/a262144––apiopenrouter
gpt-oss-120bopenrouterakashml–0.03700.01040.190.05270.07450.02100.03700.0104–n/a–n/a–n/a131072o200k–apiopenrouter
Laguna XS 2.1openrouteropenrouter–0.0600n/a0.12n/a0.0750n/a0.0300n/a–n/a–n/a–n/a262144––apiopenrouter
Gemma 3 12Bopenrouteropenrouter–0.0500n/a0.15n/a0.0750n/a–n/a–n/a–n/a–n/a131072gemini–apiopenrouter
Laguna XS 2.1openrouterpoolsidefp80.0600n/a0.12n/a0.0750n/a0.0300n/a–n/a–n/a–n/a262144––apiopenrouter
gpt-oss-20b (GovCloud)openroutersiliconflowfp80.04000.01130.180.05070.07500.0211–n/a–n/a–n/a–n/a131072o200k–apiopenrouter
Gemma 3 12Bopenrouterdeepinfra–0.0500n/a0.15n/a0.0750n/a–n/a–n/a–n/a–n/a131072gemini–apiopenrouter
Gemma 3 12Bopenrouterdeepinfra–0.0500n/a0.15n/a0.0750n/a–n/a–n/a–n/a–n/a131072gemini2026-08-27 ↑aggregatorlitellm
text-embedding-ada-002azureazure–0.10n/afreen/a0.0750n/a–n/a–n/a–n/a–n/a8192––aggregatormodelsdev
Embed v3 Multilingualazureazure–0.10n/afreen/a0.0750n/a–n/a–n/a–n/a–n/a512––aggregatormodelsdev
Embed v3 Englishazureazure–0.10n/afreen/a0.0750n/a–n/a–n/a–n/a–n/a512––aggregatormodelsdev
Mistral Embedmistralmistral–0.10n/afreen/a0.0750n/a–n/a–n/a–n/a–n/a8000––aggregatormodelsdev
text-embedding-ada-002azureopenai–0.10n/afreen/a0.0750n/a–n/a–n/a–n/a–n/a8192––aggregatormodelsdev
gemma-3-12b-itdeepinfradeepinfra–0.0500n/a0.15n/a0.0750n/a–n/a–n/a–n/a–n/a–––officialofficial-deepinfra
Tencent: Hy-MT2-1.8Bopenrouteropenrouter–0.0440n/a0.18n/a0.0773n/a–n/a–n/a–n/a–n/a8192––apiopenrouter
Tencent: Hy-MT2-1.8Bopenroutertencentfp80.0440n/a0.18n/a0.0773n/a–n/a–n/a–n/a–n/a8192––apiopenrouter
Tongyi Intent Detect V3alibabaalibaba–0.0580n/a0.14n/a0.0795n/a–n/a–n/a–n/a–n/a8192––aggregatormodelsdev
Embed 5 Fastcoherecohere–0.0800n/a–n/a0.0800n/a–n/a–n/a–n/a–n/a–––officialofficial-cohere
qwen-image-20-protogethertogether––n/a0.0800n/a0.0800n/a–n/a–n/a–n/a–n/a–––officialofficial-together
flux-1-kontext-maxtogethertogether–0.0800n/a–n/a0.0800n/a–n/a–n/a–n/a–n/a–––officialofficial-together
Amazon Nova Microamazonaws-bedrock–0.0460n/a0.18n/a0.0805n/a0.0115n/a–n/a–n/a–n/a128000––aggregatorlitellm
Qwen3-30B-A3B-Instruct-2507openrouteropenrouter–0.04820.01450.190.05820.08440.0254–n/a–n/a–n/a–n/a262144qwen2–apiopenrouter
Qwen3-30B-A3B-Instruct-2507openrouterstreamlakeunknown0.04820.01450.190.05820.08440.0254–n/a–n/a–n/a–n/a262144qwen2–apiopenrouter
Qwen3-30B-A3B-Instruct-2507openrouterstreamlake–0.04820.01450.190.05820.08440.0254–n/a–n/a–n/a–n/a262144qwen2–apiopenrouter
Nemotron 3.5 Lightning 30B A3Bopenrouterdeepinfra–0.0600n/a0.16n/a0.0850n/a0.0300n/a–n/a–n/a–n/a262144––apiopenrouter
NVIDIA-Nemotron-3.5-Lightningdeepinfradeepinfra–0.0600n/a0.16n/a0.0850n/a0.0300n/a–n/a–n/a–n/a–––officialofficial-deepinfra
Gemma 4 26B A4Bopenrouterdarkbloomunknown0.04200.01260.220.06590.08650.02590.02100.0063–n/a–n/a–n/a262144gemma–apiopenrouter
Gemma 4 26B A4Bopenrouterdarkbloom–0.04200.01260.220.06590.08650.02590.02100.0063–n/a–n/a–n/a262144gemma–apiopenrouter
Nemotron 3.5 Lightning 30B A3Bopenrouteropenrouter–0.0595n/a0.17n/a0.0871n/a0.0298n/a–n/a–n/a–n/a262144––apiopenrouter

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