Roar AI
DiscordGet started
Models

AI Models & APIs in Sri Lanka

200+ frontier and open-source models on one API, priced in Sri Lankan rupees and billed on one monthly invoice in LKR.

Every model, by provider

Anthropic Claude

Claude API in Sri Lanka
ModelInput / 1MOutput / 1MContextBest forProcessed in
LKR 3,330LKR 16,6501MLong-running agents and the hardest problemsGlobal
Cached inputLKR 83.25LKR 4,163 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 1,665LKR 8,325Results within 24 hours, for work nobody is waiting on.
Everything about Claude Fable 5.1
LKR 1,665LKR 8,3251MProducts already built on Opus 5Global
Cached inputLKR 167LKR 2,081 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 833LKR 4,163Results within 24 hours, for work nobody is waiting on.
Everything about Claude Opus 5
LKR 1,332LKR 6,6601MComplex coding and knowledge workGlobal
Cached inputLKR 66.60LKR 1,665 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 666LKR 3,330Results within 24 hours, for work nobody is waiting on.
Everything about Claude Opus 5.5
LKR 666LKR 3,3301MEveryday coding and documentsGlobal
Cached inputLKR 66.60LKR 833 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 333LKR 1,665Results within 24 hours, for work nobody is waiting on.
Everything about Claude Sonnet 5.5
LKR 333LKR 1,665200KLive chat and support agentsGlobal
Cached inputLKR 33.30LKR 416 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 167LKR 833Results within 24 hours, for work nobody is waiting on.
Everything about Claude Haiku 4.5
ModelInput / 1MOutput / 1MContextBest forProcessed in
LKR 3,330LKR 16,6501.05MHard maths, science and agent tasksGlobal
Cached inputLKR 333LKR 4,163 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 1,665LKR 8,325Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 6,660LKR 24,975Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6 Astra
LKR 2,664LKR 13,3201.05MHard science and mathsGlobal
Cached inputLKR 133LKR 3,330 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 1,332LKR 6,660Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 5,328LKR 19,980Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6.2 Astra
LKR 1,332LKR 6,6601.05MLong coding tasksGlobal
Cached inputLKR 133LKR 1,665 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 666LKR 3,330Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 2,664LKR 9,990Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-5.6 Sol
LKR 666LKR 3,3301.05MEveryday work and agentsGlobal
Cached inputLKR 33.30LKR 833 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 333LKR 1,665Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 1,332LKR 4,995Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6.2 Sol
LKR 666LKR 3,3301.05MProduction coding agentsGlobal
Cached inputLKR 33.30LKR 833 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 333LKR 1,665Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 1,332LKR 4,995Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6.1 Sol
LKR 666LKR 3,3301.05MProducts already built on GPT-6 SolGlobal
Cached inputLKR 66.60LKR 833 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 333LKR 1,665Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 1,332LKR 4,995Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6 Sol
LKR 583LKR 4,662400KTerminal coding agentsGlobal
Cached inputLKR 58.28—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about GPT-5.3-Codex
LKR 66.60LKR 4001.05MHigh-volume extractionGlobal
Cached inputLKR 6.66LKR 83.25 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 33.30LKR 200Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 133LKR 599Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-5.6 Luna
LKR 66.60LKR 416400KClassification and tagging at scaleGlobal
Cached inputLKR 6.66—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 33.30LKR 208Results within 24 hours, for work nobody is waiting on.
Everything about GPT-5.4 nano
LKR 64.94LKR 260131KMaths, science and logicGlobal
Cached inputLKR 32.47—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about gpt-oss-120b
LKR 33.30LKR 1671.05MHigh-volume extraction and routingGlobal
Cached inputLKR 3.33LKR 41.63 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 16.65LKR 83.25Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 66.60LKR 250Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6 Luna
LKR 30.30LKR 108131KQuick reasoning stepsGlobal
Standard rates only. Everything about gpt-oss-20b
LKR 4,995
characters
——Real-time voice repliesGlobal
Standard rates only. Everything about TTS-1
LKR 4,810
audio seconds
——Transcripts and captionsGlobal
Standard rates only. Everything about Whisper large-v3-turbo
LKR 43.29—8KMultilingual search and retrievalGlobal
BatchLKR 21.65FreeResults within 24 hours, for work nobody is waiting on.
Everything about text-embedding-3-large
LKR 6.66—8KLow-cost search and retrievalGlobal
BatchLKR 3.33FreeResults within 24 hours, for work nobody is waiting on.
Everything about text-embedding-3-small
ModelInput / 1MOutput / 1MContextBest forProcessed in
LKR 999LKR 4,9951.05MFinance, legal and long documentsGlobal
Cached inputLKR 49.95—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 500LKR 2,498Results within 24 hours, for work nobody is waiting on.
PriorityLKR 1,798LKR 8,991Faster service, for something a person is sitting in front of.
Everything about Gemini 4 Neon
LKR 666LKR 3,3301.05MFinance, legal and research workGlobal
Cached inputLKR 33.30—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 333LKR 1,665Results within 24 hours, for work nobody is waiting on.
PriorityLKR 1,199LKR 5,994Faster service, for something a person is sitting in front of.
Everything about Gemini 4 Argon
LKR 666LKR 3,9961.05MVideo, audio and long PDFsGlobal
Cached inputLKR 66.60—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 333LKR 1,998Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 1,332LKR 5,994Above 200,000 input tokens, the whole request is billed at these rates.
Everything about Gemini 3.1 Pro
LKR 250LKR 1,2491.05MCoding agents at a mid-range priceGlobal
Cached inputLKR 24.98—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 125LKR 624Results within 24 hours, for work nobody is waiting on.
Everything about Gemini 3.8 Flash
LKR 60.61LKR 173256KDocuments, forms and imagesGlobal
BatchLKR 30.30LKR 86.58Results within 24 hours, for work nobody is waiting on.
Everything about Gemma 4 31B

Meta Llama

ModelInput / 1MOutput / 1MContextBest forProcessed in
LKR 127LKR 975128KDrafting and document Q&AGlobal
Standard rates only. Everything about Llama 3.3 70B
LKR 23.79LKR 38.06128KVery low-cost tagging and routingGlobal
Standard rates only. Everything about Llama 3.1 8B

DeepSeek

ModelInput / 1MOutput / 1MContextBest forProcessed in
LKR 519LKR 1,0391MCoding across large repositoriesSingapore
Cached inputLKR 77.92—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about DeepSeek-V4-Pro
LKR 64.94LKR 2601.05MLow-cost coding and tool useSingapore
Cached inputLKR 6.49—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about DeepSeek-V4.1-Flash

Alibaba Qwen

ModelInput / 1MOutput / 1MContextBest forProcessed in
LKR 736LKR 2,2081MFrontier-level coding agentsSingapore
Cached inputLKR 97.40LKR 1,082 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about Qwen 3.8 Max
LKR 152LKR 909262KLow-cost coding agentsSingapore
Cached inputLKR 38.96LKR 271 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about Qwen 3.8 27B
LKR 133LKR 833131KData that must stay in Sri LankaColombo, Sri Lanka
BatchLKR 133LKR 833Results within 24 hours, for work nobody is waiting on.
Everything about Qwen 3.8 27B LK
LKR 64.94LKR 2031MTranscribing and understanding audioSingapore
Cached inputLKR 6.93—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about Qwen 3.8 Omni Flash
LKR 55.19LKR 1731MHigh-volume coding helpSingapore
Cached inputLKR 6.23LKR 86.58 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about Qwen 3.8 Flash

More models

ModelInput / 1MOutput / 1MContextBest forProcessed in
LKR 1,332LKR 3,996500KScience and technical questionsGlobal
Cached inputLKR 167—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about Grok 4.6
Kimi K3
Moonshot AI
LKR 1,234LKR 6,1691.05MWeb research agentsSingapore
Cached inputLKR 117—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about Kimi K3
GLM-5.3
Zhipu AI
LKR 424LKR 1,3331MCoding agents and security workSingapore
Cached inputLKR 109—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about GLM-5.3
MiMo-V2.5
Xiaomi
LKR 173LKR 8661MAudio, video and image analysisGlobal
Cached inputLKR 34.63—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about MiMo-V2.5
MiniMax-M3
MiniMax
LKR 130LKR 5191.05MCoding with screenshots and videoGlobal
Cached inputLKR 25.97—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about MiniMax-M3
LKR 64.94LKR 2161MCheap, high-volume coding agentsGlobal
Cached inputLKR 12.99—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about GLM-5.3-Flash
LKR 64.94LKR 260524KLong documents, without guessingGlobal
Cached inputLKR 12.99—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about Solar Pro 4
LKR 45.45LKR 188256KCoding and office assistantsGlobal
Cached inputLKR 14.29—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about Hunyuan Hy3
Jev
TypeSafe AI
LKR 13.99Free64KGrading and guardrail checksGlobal
Standard rates only. Everything about Jev

Rupee prices are our published US dollar rates converted at LKR 333 to the dollar, our rate for November 2026 — the same rate your invoice uses.

Frontier and locally hosted models

Access leading international models alongside an open-source model hosted in Sri Lanka: Qwen 3.8 27B LK, on our own server in Colombo. Workloads can be matched to the appropriate model based on performance, cost and data requirements.

The table above says where each model is processed. Claude, GPT, Gemini and the other models not marked Colombo are processed outside Sri Lanka. When data has to stay in the country.

Questions

Can I access Claude, GPT and Gemini APIs from Sri Lanka?

Yes. Roar AI provides access to supported models from Anthropic, OpenAI, Google and other providers through a single API.

Can I pay for AI API usage in Sri Lankan rupees?

Yes. Roar AI supports LKR billing, so Sri Lankan businesses and developers can pay for supported AI model usage in rupees.

Are AI models hosted in Sri Lanka?

One is: Qwen 3.8 27B LK runs on our own server in Colombo, and prompts sent to it are processed in Sri Lanka. Frontier models from providers such as Anthropic, OpenAI and Google are processed outside Sri Lanka. Each model page states where processing occurs.

Do I need a different API integration for each model?

No. Supported models can be accessed through the Roar AI gateway, allowing teams to use multiple models without maintaining separate integrations with every provider.

Every model,
billed in rupees

One API key for every model, on one monthly invoice in LKR.