Cheapest models

Models in the current catalog priced at or below $0.35 per million input tokens.

Author
Input
Providers
Limits

Context

Input price

Only

Sort

92 models

  • LongCat 2.5 PreviewNew
    Context
    1M
    Input / 1M
    $0.315
    Output / 1M
    $1.26
    Max output
    131K
    Accepts
    • Text
  • GPT-6 LunaNew
    Context
    1.1M
    Input / 1M
    $0.105
    Output / 1M
    $0.525
    Max output
    128K
    Accepts
    • Text
    • Image
  • GPT-6 Luna (Fast)New
    Context
    1.1M
    Input / 1M
    $0.21
    Output / 1M
    $1.05
    Max output
    128K
    Accepts
    • Text
    • Image
  • MiMo V2.6 FlashNew
    Context
    1M
    Input / 1M
    $0.147
    Output / 1M
    $0.294
    Max output
    131K
    Accepts
    • Text
    • Image
  • Qwen 3.8 Omni FlashNew
    Context
    1M
    Input / 1M
    $0.158
    Output / 1M
    $0.494
    Max output
    131K
    Accepts
    • Text
    • Image
  • Bonsai 2 27B
    Context
    262K
    Input / 1M
    $0.0788
    Output / 1M
    $0.525
    Max output
    33K
    Accepts
    • Text
  • JevEvaluation
    Context
    32K
    Input / 1M
    $0.0462
    Output / 1M
    Free
    Max output
    —
    Accepts
    • Text
  • DeepSeek V4.1 Flash
    Context
    1M
    Input / 1M
    $0.315Off-peak · 2× at peak
    Output / 1M
    $1.26Off-peak · 2× at peak
    Max output
    33K
    Accepts
    • Text
  • Mercury 2.5
    Context
    260K
    Input / 1M
    $0.042
    Output / 1M
    $0.158
    Max output
    66K
    Accepts
    • Text
  • Ling 3.0 Flash Sante (Free)Free
    Context
    256K
    Input / 1M
    Free
    Output / 1M
    Free
    Max output
    32K
    Accepts
    • Text
  • Muse Spark 1.3 Contributor
    Context
    1M
    Input / 1M
    $0.105
    Output / 1M
    $0.21
    Max output
    1M
    Accepts
    • Text
  • Ling 3.0 Flash Fin
    Context
    256K
    Input / 1M
    $0.0788
    Output / 1M
    $0.231
    Max output
    32K
    Accepts
    • Text
  • Qwen 3.8 Flash
    Context
    991K
    Input / 1M
    $0.158
    Output / 1M
    $0.494
    Max output
    128K
    Accepts
    • Text
  • GLM 5.3 Flash
    Context
    1M
    Input / 1M
    $0.158
    Output / 1M
    $0.525
    Max output
    131K
    Accepts
    • Text
    • Image
  • DeepSeek V4 Flash Vision Exp
    Context
    1M
    Input / 1M
    $0.226Off-peak · 2× at peak
    Output / 1M
    $0.679Off-peak · 2× at peak
    Max output
    1M
    Accepts
    • Text
  • Nemotron 3.5 Lightning 30B
    Context
    262K
    Input / 1M
    $0.0525
    Output / 1M
    $0.21
    Max output
    131K
    Accepts
    • Text
  • Ling 3.0 Flash
    Context
    256K
    Input / 1M
    $0.0221
    Output / 1M
    $0.0661
    Max output
    32K
    Accepts
    • Text
  • Muse Spark 1.2 Contributor
    Context
    1M
    Input / 1M
    $0.105
    Output / 1M
    $0.21
    Max output
    1M
    Accepts
    • Text
    • Image
    • PDF
  • Qwen 3.7 Flash
    Context
    991K
    Input / 1M
    $0.0315
    Output / 1M
    $0.137
    Max output
    64K
    Accepts
    • Text
    • Image
    • PDF
  • Gemini 3.5 Flash Lite
    Context
    1M
    Input / 1M
    $0.315
    Output / 1M
    $2.625
    Max output
    65K
    Accepts
    • Text
    • Image
    • PDF
    • Video
  • Laguna S 2.1 FreeFree
    Context
    256K
    Input / 1M
    Free
    Output / 1M
    Free
    Max output
    33K
    Accepts
    • Text
  • Laguna S 2.1
    Context
    1M
    Input / 1M
    $0.105
    Output / 1M
    $0.21
    Max output
    131K
    Accepts
    • Text
  • GPT 5.6 Luna
    Context
    1.1M
    Input / 1M
    $0.21
    Output / 1M
    $1.26
    Max output
    128K
    Accepts
    • Text
    • Image
    • PDF
  • Hy3
    Context
    262K
    Input / 1M
    $0.147
    Output / 1M
    $0.609
    Max output
    262K
    Accepts
    • Text
  • MiniMax M3
    Context
    512K
    Input / 1M
    $0.315
    Output / 1M
    $1.26
    Max output
    512K
    Accepts
    • Text
    • Image
    • PDF
  • Step 3.7 Flash
    Context
    256K
    Input / 1M
    $0.21
    Output / 1M
    $1.208
    Max output
    256K
    Accepts
    • Text
    • Image
  • Gemini 3.1 Flash Lite
    Context
    1M
    Input / 1M
    $0.262
    Output / 1M
    $1.575
    Max output
    65K
    Accepts
    • Text
    • Image
    • PDF
  • DeepSeek V4 Flash
    Context
    1M
    Input / 1M
    $0.137
    Output / 1M
    $0.273
    Max output
    384K
    Accepts
    • Text
  • DeepSeek V4 Flash 0731
    Context
    1M
    Input / 1M
    $0.0798
    Output / 1M
    $0.161
    Max output
    384K
    Accepts
    • Text
  • MiMo M2.5
    Context
    1.1M
    Input / 1M
    $0.147
    Output / 1M
    $0.294
    Max output
    131K
    Accepts
    • Text
    • Image
  • Qwen 3.6 35B A3B
    Context
    262K
    Input / 1M
    $0.0525
    Output / 1M
    $0.735
    Max output
    16K
    Accepts
    • Text
    • Image
  • Google Gemma 4 26B A4B
    Context
    262K
    Input / 1M
    $0.158
    Output / 1M
    $0.63
    Max output
    131K
    Accepts
    • Text
    • Image
    • PDF
  • Gemma 4 31B IT
    Context
    262K
    Input / 1M
    $0.147
    Output / 1M
    $0.42
    Max output
    131K
    Accepts
    • Text
    • Image
    • PDF
  • Trinity Large Thinking
    Context
    262K
    Input / 1M
    $0.262
    Output / 1M
    $0.945
    Max output
    80K
    Accepts
    • Text
  • MiniMax M2.7
    Context
    205K
    Input / 1M
    $0.315
    Output / 1M
    $1.26
    Max output
    131K
    Accepts
    • Text
  • GPT 5.4 Nano
    Context
    400K
    Input / 1M
    $0.21
    Output / 1M
    $1.313
    Max output
    128K
    Accepts
    • Text
    • Image
    • PDF
  • NVIDIA Nemotron 3 Super 120B A12B
    Context
    256K
    Input / 1M
    $0.158
    Output / 1M
    $0.683
    Max output
    32K
    Accepts
    • Text
  • Qwen 3.5 9B
    Context
    262K
    Input / 1M
    $0.084
    Output / 1M
    $0.137
    Max output
    16K
    Accepts
    • Text
    • Image
  • Qwen 3.5 Flash
    Context
    1M
    Input / 1M
    $0.105
    Output / 1M
    $0.42
    Max output
    64K
    Accepts
    • Text
    • Image
    • PDF
  • Mercury 2
    Context
    128K
    Input / 1M
    $0.262
    Output / 1M
    $0.788
    Max output
    128K
    Accepts
    • Text
  • MiniMax M2.5
    Context
    205K
    Input / 1M
    $0.315
    Output / 1M
    $1.26
    Max output
    131K
    Accepts
    • Text
  • StepFun 3.5 Flash
    Context
    262K
    Input / 1M
    $0.0945
    Output / 1M
    $0.315
    Max output
    262K
    Accepts
    • Text
    • Image
  • GLM 4.7 Flash
    Context
    200K
    Input / 1M
    $0.0735
    Output / 1M
    $0.42
    Max output
    131K
    Accepts
    • Text
  • GLM 4.7 FlashX
    Context
    200K
    Input / 1M
    $0.063
    Output / 1M
    $0.42
    Max output
    128K
    Accepts
    • Text
  • MiniMax M2.1
    Context
    205K
    Input / 1M
    $0.315
    Output / 1M
    $1.26
    Max output
    131K
    Accepts
    • Text
  • MiniMax M2.1 Lightning
    Context
    205K
    Input / 1M
    $0.315
    Output / 1M
    $2.52
    Max output
    131K
    Accepts
    • Text
  • Nemotron 3 Nano 30B A3B
    Context
    262K
    Input / 1M
    $0.0525
    Output / 1M
    $0.21
    Max output
    262K
    Accepts
    • Text
  • Nova 2 Lite
    Context
    1M
    Input / 1M
    $0.315
    Output / 1M
    $2.625
    Max output
    1M
    Accepts
    • Text
    • Image
    • PDF
  • Ministral 14B
    Context
    262K
    Input / 1M
    $0.21
    Output / 1M
    $0.21
    Max output
    256K
    Accepts
    • Text
    • Image
    • PDF
  • GPT OSS Safeguard 120B
    Context
    128K
    Input / 1M
    $0.158
    Output / 1M
    $0.63
    Max output
    16K
    Accepts
    • Text