o10Last updated 2026-07-26

Cheapest chat models (2026)

As of 2026-06-27, the lowest-priced routable chat model in o10's catalog is Mistral Nemo at $0.02/M input.

As of 2026-06-27, the lowest-priced routable chat model in o10's catalog is Mistral Nemo at $0.02/M input.

Dashboards observe.
o10 enforces.

Every page in this index follows the same structure as the home site — answer-first, passage blocks, operational steps, and expanded FAQs. o10 State of Inference Spend 2026 found up to 638× compliant price spread across venues for identical workloads.

Start hereQuick overview

How to use this index

Cheapest chat models (2026)

As of 2026-06-27, the lowest-priced routable chat model in o10's catalog is Mistral Nemo at $0.02/M input.

Catalog 2026-06-27.

As of 2026-06-27, the lowest-priced routable chat model in o10's catalog is Mistral Nemo at $0.02/M input.

  1. Mistral Nemo — $0.02/M input · C3 pricing
  2. Nova Micro — $0.04/M input · C1 pricing
  3. Arcee Ai Trinity Mini — $0.05/M input · C0 pricing
  4. Gpt 5 Nano — $0.05/M input · C1 pricing
  5. Gpt Oss 20b — $0.05/M input · C2 pricing
  6. Nemotron 3 Nano 30b A3b — $0.05/M input · C2 pricing
  7. Nvidia Nemotron 3 Nano 30b A3b — $0.05/M input · C0 pricing
  8. Gpt 5 Nano — $0.05/M input · C0 pricing
  9. Gpt Oss 20b — $0.05/M input · C1 pricing
  10. Glm 4.7 Flashx — $0.06/M input · C2 pricing
  11. Nemotron Nano 9b V2 — $0.06/M input · C2 pricing
  12. Nova Lite — $0.06/M input · C2 pricing
  13. Nvidia Nemotron Nano 9b V2 — $0.06/M input · C0 pricing
  14. Glm 4.7 Flash — $0.07/M input · C2 pricing
  15. Zai Glm 4 7 Flash — $0.07/M input · C0 pricing
  16. Gpt Oss Safeguard 20b — $0.08/M input · C3 pricing
  17. Gpt Oss Safeguard 20b — $0.08/M input · C1 pricing
  18. Step 3.5 Flash — $0.09/M input · C2 pricing
  19. Stepfun Step 3 5 Flash — $0.09/M input · C0 pricing
  20. Devstral Small — $0.1/M input · C3 pricing
  21. Devstral Small 2 — $0.1/M input · C2 pricing
  22. Gemini 2 5 Flash Lite — $0.1/M input · C0 pricing
  23. Gemini 2.5 Flash Lite — $0.1/M input · C2 pricing
  24. Gemini 2 5 Flash Lite — $0.1/M input · C0 pricing
  25. Gpt 4 1 Nano — $0.1/M input · C2 pricing
  26. Gpt 4.1 Nano — $0.1/M input · C1 pricing
  27. Llama 3.2 1b — $0.1/M input · C1 pricing
  28. Mimo V2 Flash — $0.1/M input · C2 pricing
  29. Ministral 3b — $0.1/M input · C1 pricing
  30. Mistral Mistral Small 2402 V1 0 — $0.1/M input · C0 pricing
  31. Mistral Small — $0.1/M input · C2 pricing
  32. Mistralai Mistral Small 24b Instruct 2501 — $0.1/M input · C0 pricing
  33. Mistralai Mistral Small 2603 — $0.1/M input · C0 pricing
  34. Mistralai Mistral Small 3 1 24b Instruct — $0.1/M input · C0 pricing
  35. Mistralai Mistral Small 3 2 24b Instruct — $0.1/M input · C0 pricing
  36. Mistralai Mistral Small 4 119b 2603 — $0.1/M input · C0 pricing
  37. Gpt 4 1 Nano — $0.1/M input · C2 pricing
  38. Qwen3.5 Flash — $0.1/M input · C2 pricing
  39. Qwen 3 14b — $0.12/M input · C2 pricing
  40. Qwen 3 30b — $0.12/M input · C2 pricing
  41. Deepseek V4 Flash — $0.14/M input · C0 pricing
  42. Deepseek V4 Flash — $0.14/M input · C2 pricing
  43. Gemma 4 31b It — $0.14/M input · C2 pricing
  44. Gemma 4 31b It — $0.14/M input · C0 pricing
  45. Xiaomi Mimo V2 5 — $0.14/M input · C1 pricing
  46. Gemma 4 26b A4b It — $0.15/M input · C2 pricing
  47. Gemma 4 26b A4b It — $0.15/M input · C1 pricing
  48. Gpt 4o Mini — $0.15/M input · C2 pricing
  49. Gpt 4o Mini Search Preview — $0.15/M input · C3 pricing
  50. Llama 3.2 3b — $0.15/M input · C1 pricing
FAQFrequently asked questions

Common questions

How were these models ranked?

Sorted by inputPerM ASC. Snapshot date: 2026-06-27.

Where does pricing data come from?

Gateway catalog snapshot joined with o10 fulfillment catalog.

o10Set the envelope. o10 holds it.

See what you're overpaying.

Paste a week of traffic. Get the number that books the audit.

See what you're overpaying →