Skip to content
M82 Router
ModelsRankingsDocsSupport
Sign inSign in
M82 Router

An OpenAI-compatible LLM API for developers in Nepal, billed in rupees.

Product

  • How it works
  • Billing
  • Models and prices
  • Rankings
  • Questions

Developers

  • Documentation
  • Code examples
  • Sign in

Help

  • Support
  • System status ↗
  • contact@m82labs.dev

Legal

  • Terms of Service
  • Privacy Policy
  • Refund Policy
  • Acceptable Use
© 2026 M82 Labs · M82 RouterPrices in Nepali rupees (Rs.)Nepal time 08:01 · UTC+05:45

Model catalog

Models

Every model behind one API key, priced live in rupees. Pick by what it can do, how much it reads, or what a request costs; each request keeps the price that was active when its credit was reserved.

42models live, read 08:01 NPT

Sort
Estimate cost for
Filters
Capabilities
Maker
Context window
Access

Frontier models need a verified top-up above the account minimum.

All 42 modelsExample request: 1,200 tokens sent, 350 written

Intelligence: Epoch Capabilities Index by Epoch AI, measured by Epoch AI at its test settings, read 2026-10-11. Licensed CC BY 4.0; matched to M82 model IDs by M82. Models Epoch AI has not scored are shown as not rated.

  1. OpenAI: GPT-6 Astra

    openai/gpt-6-astra

    FrontierTool calls

    • Intelligence166.4
    • Context272K
    • Max output3K
    • InputRs. 1,702.04/1M
    • Cached inputRs. 170.20/1M
    • OutputRs. 8,510.20/1M
    ≈ Rs. 5.02per short reply≈ 19 per Rs. 100

  2. OpenAI: GPT-6.1 Sol

    openai/gpt-6.1-sol

    FrontierTool calls

    • Intelligence166.1
    • Context272K
    • Max output4K
    • InputRs. 340.41/1M
    • Cached inputRs. 17.02/1M
    • OutputRs. 1,702.04/1M
    ≈ Rs. 1.00per short reply≈ 99 per Rs. 100

  3. OpenAI: GPT-6 Sol

    openai/gpt-6-sol

    FrontierTool calls

    • Intelligence162.7
    • Context272K
    • Max output4K
    • InputRs. 340.41/1M
    • Cached inputRs. 34.04/1M
    • OutputRs. 1,702.04/1M
    ≈ Rs. 1.00per short reply≈ 99 per Rs. 100

  4. OpenAI: GPT-5.6 Sol

    openai/gpt-5.6-sol

    FrontierTool calls

    • Intelligence161.7
    • Context272K
    • Max output4K
    • InputRs. 340.41/1M
    • Cached inputRs. 34.04/1M
    • OutputRs. 1,702.04/1M
    ≈ Rs. 1.00per short reply≈ 99 per Rs. 100

  5. OpenAI: GPT-5.6 Terra

    openai/gpt-5.6-terra

    FrontierTool calls

    • Intelligence159.6
    • Context272K
    • Max output4K
    • InputRs. 340.41/1M
    • Cached inputRs. 34.04/1M
    • OutputRs. 2,042.45/1M
    ≈ Rs. 1.12per short reply≈ 89 per Rs. 100

  6. OpenAI: GPT-5.5

    openai/gpt-5.5

    FrontierTool calls

    • Intelligence159.1
    • Context272K
    • Max output4K
    • InputRs. 851.02/1M
    • Cached inputRs. 85.10/1M
    • OutputRs. 5,106.12/1M
    ≈ Rs. 2.81per short reply≈ 35 per Rs. 100

  7. OpenAI: GPT-5.4

    openai/gpt-5.4

    FrontierTool calls

    • Intelligence156.8
    • Context272K
    • Max output4K
    • InputRs. 425.51/1M
    • Cached inputRs. 42.55/1M
    • OutputRs. 2,553.06/1M
    ≈ Rs. 1.40per short reply≈ 71 per Rs. 100

  8. OpenAI: GPT-5.3-Codex

    openai/gpt-5.3-codex

    FrontierTool calls

    • Intelligence156.8
    • Context400K
    • Max output4K
    • InputRs. 297.86/1M
    • Cached inputRs. 29.79/1M
    • OutputRs. 2,382.86/1M
    ≈ Rs. 1.19per short reply≈ 83 per Rs. 100

  9. OpenAI: GPT-5.6 Luna

    openai/gpt-5.6-luna

    Tool calls

    • Intelligence156.4
    • Context272K
    • Max output4K
    • InputRs. 34.04/1M
    • Cached inputRs. 3.40/1M
    • OutputRs. 204.24/1M
    ≈ Rs. 0.112per short reply≈ 890 per Rs. 100

  10. OpenAI: GPT-6 Luna

    openai/gpt-6-luna

    Tool calls

    • Intelligence156.3
    • Context272K
    • Max output4K
    • InputRs. 17.02/1M
    • Cached inputRs. 1.70/1M
    • OutputRs. 85.10/1M
    ≈ Rs. 0.0502per short reply≈ 1,900 per Rs. 100

  11. DeepSeek: DeepSeek V4 Pro

    deepseek/deepseek-v4-pro

    Frontier1M contextTool callsReasoning

    • Intelligence155.3
    • Context1M
    • Max output4K
    • InputRs. 213.97/1M
    • Cached inputRs. 7.13/1M
    • OutputRs. 641.91/1M
    ≈ Rs. 0.481per short reply≈ 200 per Rs. 100

  12. DeepSeek: DeepSeek V4.1 Flash

    deepseek/deepseek-flash

    1M contextTool callsReasoning

    • Intelligence154.9
    • Context1M
    • Max output4K
    • InputRs. 48.63/1M
    • Cached inputRs. 0.973/1M
    • OutputRs. 194.52/1M
    ≈ Rs. 0.126per short reply≈ 790 per Rs. 100

  13. OpenAI: GPT-5.2

    openai/gpt-5.2

    FrontierTool calls

    • Intelligence153.4
    • Context400K
    • Max output4K
    • InputRs. 297.86/1M
    • Cached inputRs. 29.79/1M
    • OutputRs. 2,382.86/1M
    ≈ Rs. 1.19per short reply≈ 83 per Rs. 100

  14. OpenAI: GPT-5

    openai/gpt-5

    FrontierTool calls

    • Intelligence150.0
    • Context400K
    • Max output4K
    • InputRs. 212.75/1M
    • Cached inputRs. 21.28/1M
    • OutputRs. 1,702.04/1M
    ≈ Rs. 0.851per short reply≈ 110 per Rs. 100

  15. OpenAI: GPT-5.1

    openai/gpt-5.1

    FrontierTool calls

    • Intelligence149.6
    • Context400K
    • Max output4K
    • InputRs. 212.75/1M
    • Cached inputRs. 21.28/1M
    • OutputRs. 1,702.04/1M
    ≈ Rs. 0.851per short reply≈ 110 per Rs. 100

  16. OpenAI: GPT-5.4 Mini

    openai/gpt-5.4-mini

    Tool calls

    • Intelligence148.8
    • Context400K
    • Max output4K
    • InputRs. 127.65/1M
    • Cached inputRs. 12.77/1M
    • OutputRs. 765.92/1M
    ≈ Rs. 0.421per short reply≈ 230 per Rs. 100

  17. OpenAI: o3

    openai/o3

    FrontierTool calls

    • Intelligence146.9
    • Context200K
    • Max output4K
    • InputRs. 340.41/1M
    • Cached inputRs. 85.10/1M
    • OutputRs. 1,361.63/1M
    ≈ Rs. 0.885per short reply≈ 110 per Rs. 100

  18. OpenAI: GPT-5.4 Nano

    openai/gpt-5.4-nano

    Tool calls

    • Intelligence145.8
    • Context400K
    • Max output4K
    • InputRs. 34.04/1M
    • Cached inputRs. 3.40/1M
    • OutputRs. 212.75/1M
    ≈ Rs. 0.115per short reply≈ 860 per Rs. 100

  19. OpenAI: o4 Mini

    openai/o4-mini

    FrontierTool calls

    • Intelligence145.6
    • Context200K
    • Max output4K
    • InputRs. 187.22/1M
    • Cached inputRs. 46.81/1M
    • OutputRs. 748.90/1M
    ≈ Rs. 0.487per short reply≈ 200 per Rs. 100

  20. OpenAI: GPT-5 Mini

    openai/gpt-5-mini

    Tool calls

    • Intelligence145.5
    • Context400K
    • Max output4K
    • InputRs. 42.55/1M
    • Cached inputRs. 4.26/1M
    • OutputRs. 340.41/1M
    ≈ Rs. 0.17per short reply≈ 580 per Rs. 100

  21. OpenAI: o1

    openai/o1

    FrontierTool calls

    • Intelligence141.9
    • Context200K
    • Max output4K
    • InputRs. 2,553.06/1M
    • Cached inputRs. 1,276.53/1M
    • OutputRs. 10,212.24/1M
    ≈ Rs. 6.64per short reply≈ 15 per Rs. 100

  22. OpenAI: o3 Mini

    openai/o3-mini

    FrontierTool calls

    • Intelligence140.3
    • Context200K
    • Max output4K
    • InputRs. 187.22/1M
    • Cached inputRs. 93.61/1M
    • OutputRs. 748.90/1M
    ≈ Rs. 0.487per short reply≈ 200 per Rs. 100

  23. OpenAI: gpt-oss-120b

    openai/gpt-oss-120b

    Tool calls

    • Intelligence139.9
    • Context128K
    • Max output4K
    • InputRs. 6.30/1M
    • Cached inputRs. 6.30/1M
    • OutputRs. 28.93/1M
    ≈ Rs. 0.0177per short reply≈ 5,600 per Rs. 100

  24. OpenAI: GPT-5 Nano

    openai/gpt-5-nano

    Tool calls

    • Intelligence139.4
    • Context400K
    • Max output4K
    • InputRs. 8.51/1M
    • Cached inputRs. 0.851/1M
    • OutputRs. 68.08/1M
    ≈ Rs. 0.034per short reply≈ 2,900 per Rs. 100

  25. OpenAI: gpt-oss-20b

    openai/gpt-oss-20b

    Lowest priceTool calls

    • Intelligence137.8
    • Context128K
    • Max output4K
    • InputRs. 3.06/1M
    • Cached inputRs. 1.53/1M
    • OutputRs. 15.32/1M
    ≈ Rs. 0.00904per short reply≈ 11,000 per Rs. 100

  26. OpenAI: GPT-4.1

    openai/gpt-4.1

    Frontier1M contextTool calls

    • Intelligence136.8
    • Context10,47,576
    • Max output4K
    • InputRs. 340.41/1M
    • Cached inputRs. 85.10/1M
    • OutputRs. 1,361.63/1M
    ≈ Rs. 0.885per short reply≈ 110 per Rs. 100

  27. OpenAI: GPT-4.1 Mini

    openai/gpt-4.1-mini

    1M contextTool calls

    • Intelligence135.0
    • Context10,47,576
    • Max output4K
    • InputRs. 68.08/1M
    • Cached inputRs. 17.02/1M
    • OutputRs. 272.33/1M
    ≈ Rs. 0.177per short reply≈ 560 per Rs. 100

  28. OpenAI: GPT-4.1 Nano

    openai/gpt-4.1-nano

    1M contextTool calls

    • Intelligence129.6
    • Context10,47,576
    • Max output4K
    • InputRs. 17.02/1M
    • Cached inputRs. 4.26/1M
    • OutputRs. 68.08/1M
    ≈ Rs. 0.0443per short reply≈ 2,200 per Rs. 100

  29. OpenAI: GPT-4o

    openai/gpt-4o

    FrontierTool calls

    • Intelligence128.8
    • Context125K
    • Max output4K
    • InputRs. 425.51/1M
    • Cached inputRs. 212.75/1M
    • OutputRs. 1,702.04/1M
    ≈ Rs. 1.11per short reply≈ 90 per Rs. 100

  30. OpenAI: GPT-4 Turbo

    openai/gpt-4-turbo

    FrontierTool calls

    • Intelligence127.3
    • Context125K
    • Max output3K
    • InputRs. 1,702.04/1M
    • Cached inputRs. 1,702.04/1M
    • OutputRs. 5,106.12/1M
    ≈ Rs. 3.83per short reply≈ 26 per Rs. 100

  31. OpenAI: GPT-4o-mini

    openai/gpt-4o-mini

    Tool calls

    • Intelligence126.6
    • Context125K
    • Max output4K
    • InputRs. 25.53/1M
    • Cached inputRs. 12.77/1M
    • OutputRs. 102.12/1M
    ≈ Rs. 0.0664per short reply≈ 1,500 per Rs. 100

  32. OpenAI: GPT-3.5 Turbo

    openai/gpt-3.5-turbo

    Tool calls

    • Intelligence115.7
    • Context16,385
    • Max output4K
    • InputRs. 85.10/1M
    • Cached inputRs. 85.10/1M
    • OutputRs. 255.31/1M
    ≈ Rs. 0.191per short reply≈ 520 per Rs. 100

  33. OpenAI: GPT-5.1-Codex-Mini

    openai/gpt-5.1-codex-mini

    Tool calls

    • IntelligenceNot rated
    • Context400K
    • Max output4K
    • InputRs. 42.55/1M
    • Cached inputRs. 5.11/1M
    • OutputRs. 340.41/1M
    ≈ Rs. 0.17per short reply≈ 580 per Rs. 100

  34. OpenAI: GPT-5.1-Codex

    openai/gpt-5.1-codex

    FrontierTool calls

    • IntelligenceNot rated
    • Context400K
    • Max output4K
    • InputRs. 212.75/1M
    • Cached inputRs. 22.13/1M
    • OutputRs. 1,702.04/1M
    ≈ Rs. 0.851per short reply≈ 110 per Rs. 100

  35. OpenAI: GPT-5.1-Codex-Max

    openai/gpt-5.1-codex-max

    FrontierTool calls

    • IntelligenceNot rated
    • Context400K
    • Max output4K
    • InputRs. 212.75/1M
    • Cached inputRs. 21.28/1M
    • OutputRs. 1,702.04/1M
    ≈ Rs. 0.851per short reply≈ 110 per Rs. 100

  36. OpenAI: GPT-5.2-Codex

    openai/gpt-5.2-codex

    FrontierTool calls

    • IntelligenceNot rated
    • Context400K
    • Max output4K
    • InputRs. 297.86/1M
    • Cached inputRs. 29.79/1M
    • OutputRs. 2,382.86/1M
    ≈ Rs. 1.19per short reply≈ 83 per Rs. 100

  37. Qwen: Qwen3 Coder 30B A3B Instruct

    qwen/qwen3-coder-30b-a3b-instruct

    Tool calls

    • IntelligenceNot rated
    • Context256K
    • Max output4K
    • InputRs. 11.91/1M
    • Cached inputRs. 11.91/1M
    • OutputRs. 47.66/1M
    ≈ Rs. 0.031per short reply≈ 3,200 per Rs. 100

  38. Qwen: Qwen3 Coder Next

    qwen/qwen3-coder-next

    Tool calls

    • IntelligenceNot rated
    • Context256K
    • Max output4K
    • InputRs. 20.42/1M
    • Cached inputRs. 11.91/1M
    • OutputRs. 136.16/1M
    ≈ Rs. 0.0722per short reply≈ 1,300 per Rs. 100

  39. OpenAI: gpt-oss-safeguard-20b

    openai/gpt-oss-safeguard-20b

    Tool calls

    • IntelligenceNot rated
    • Context128K
    • Max output4K
    • InputRs. 12.77/1M
    • Cached inputRs. 6.38/1M
    • OutputRs. 51.06/1M
    ≈ Rs. 0.0332per short reply≈ 3,000 per Rs. 100

  40. Z.ai: GLM 4.7 Flash

    z-ai/glm-4.7-flash

    Tool calls

    • IntelligenceNot rated
    • Context128K
    • Max output4K
    • InputRs. 10.30/1M
    • Cached inputRs. 10.30/1M
    • OutputRs. 68.08/1M
    ≈ Rs. 0.0362per short reply≈ 2,700 per Rs. 100

  41. Anthropic: Claude Haiku 5.5

    anthropic/claude-haiku-5.5

    Tool calls

    • IntelligenceNot rated
    • Context96K
    • Max output8K
    • InputRs. 17.02/1M
    • Cached inputRs. 1.70/1M
    • OutputRs. 85.10/1M
    ≈ Rs. 0.0502per short reply≈ 1,900 per Rs. 100

  42. TypeSafe: Jev 1.13 — decisions

    typesafe/jev-1.13.0

    Decisions API

    • IntelligenceNot rated
    • Context32K
    • Max output1
    • InputRs. 7.15/1M
    • Cached inputRs. 7.15/1M
    • OutputRs. 0/1M
    Priced per decision