gpt·basedElo-ranked, value-sorted
Sign in

Stay updated

Get an email when a cheaper, stronger model than yours appears on the leaderboard. No spam.

gpt·based

The LLM leaderboard that tells you when to switch. Arena rankings joined with OpenRouter pricing, refreshed daily.

Use cases

  • Best for coding
  • Best for multilingual
  • Cheapest worth using
  • Compare two models

Browse

  • Text models
  • WebDev models
  • Vision models
  • Image generation
  • Image edit

Data sources

  • LMArena
  • Providers

Developers

  • API on RapidAPI
  • OpenAPI spec

Contact

  • Contact page
  • [email protected]
© 2026 gptbasedDaily refresh, never paid placement.
    gpt·basedElo-ranked, value-sorted
    Sign in
    Use case

    Cheapest LLMs Worth Using (Under $1 per Million Tokens, Blended)

    These are the LLMs worth your time when budget matters. The list filters to models that cost under $1 per million tokens (blended at a 4:1 input:output ratio, which roughly matches typical chat use), then sorts by value score: Elo rating with a logarithmic price penalty, so you see the best quality per dollar at a glance. The arena rank shown is each model's rank in the overall text category, not a re-rank of this list.

    Top Pick
    Xiaomi: MiMo-V2.5-Pro

    Sorted by value score, filtered to under $1/M blended

    #29Elo 1466
    Input / 1M
    $0.435
    Output / 1M
    $0.870
    Blended (4:1 in:out): $0.522/1M
    Try it on:
    OOpenRouter
    Set alert
    Best Value
    DeepSeek: DeepSeek V4 Flash (thinking)

    Pareto knee, $0.108/1M blended

    #63Elo 1436
    Input / 1M
    $0.090
    Output / 1M
    $0.180
    Blended (4:1 in:out): $0.108/1M
    variant: thinking
    Try it on:
    OOpenRouter
    Set alert
    Recommended
    Qwen: Qwen3 235B A22B Thinking 2507

    Frontier middle pick, $0.100/1M blended

    #119Elo 1399
    Input / 1M
    $0.100
    Output / 1M
    $0.100
    Blended (4:1 in:out): $0.100/1M
    Try it on:
    OOpenRouter
    Set alert

    All matching models (71)

    Click any model for the full deep-dive.

    RankModelTrendEloValueIn / 1MOutputVotesLink
    #63
    DeepSeek: DeepSeek V4 Flash (thinking)
    deepseek-v4-flash-thinking
    14361533$0.090$0.18028,215
    #69
    Xiaomi: MiMo-V2.5
    mimo-v2.5
    14331510$0.140$0.28027,111
    #119
    Qwen: Qwen3 235B A22B Thinking 2507
    qwen3-235b-a22b-thinking-2507
    13991499$0.100$0.1008,994
    #141
    Qwen: Qwen3 30B A3B Instruct 2507
    qwen3-30b-a3b-instruct-2507
    13831495$0.048$0.19323,728
    #29
    Xiaomi: MiMo-V2.5-Pro
    mimo-v2.5-pro
    14661494$0.435$0.87026,563
    #36
    DeepSeek: DeepSeek V4 Pro (thinking)
    deepseek-v4-pro-thinking
    14581486$0.435$0.87026,928
    #127
    StepFun: Step 3.5 Flash
    step-3.5-flash
    13951483$0.090$0.30044,826
    #85
    DeepSeek: DeepSeek V3.2
    deepseek-v3.2
    14231483$0.229$0.34311,922
    #49
    MiniMax: MiniMax M3
    minimax-m3
    14481480$0.300$1.2011,264
    #85
    DeepSeek: DeepSeek V3.2 Exp
    deepseek-v3.2
    14231476$0.270$0.41011,922
    #170
    OpenAI: gpt-oss-120b
    gpt-oss-120b
    13531470$0.039$0.18030,635
    #157
    Google: Gemma 3 27B
    gemma-3-27b-it
    13661468$0.080$0.16047,529
    #44
    MoonshotAI: Kimi K2.5 (thinking)
    kimi-k2.5-thinking
    14501465$0.375$2.0247,780
    #37
    Z.ai: GLM 5
    glm-5
    14571464$0.600$1.9223,246
    #55
    Qwen: Qwen3.6 Plus
    qwen3.6-plus
    14441463$0.325$1.9528,997
    #101
    Qwen: Qwen3 VL 235B A22B Instruct
    qwen3-vl-235b-a22b-instruct
    14151463$0.200$0.88011,512
    #70
    Google: Gemini 3.1 Flash Lite
    gemini-3.1-flash-lite-preview
    14321462$0.250$1.5048,525
    #70
    Google: Gemini 3.1 Flash Lite Preview
    gemini-3.1-flash-lite-preview
    14321462$0.250$1.5048,525
    #59
    Z.ai: GLM 4.7
    glm-4.7
    14431460$0.400$1.7512,121
    #187
    Google: Gemma 3 12B
    gemma-3-12b-it
    13421457$0.050$0.1503,829
    #155
    Z.ai: GLM 4.7 Flash
    glm-4.7-flash
    13681457$0.060$0.40011,731
    #91
    DeepSeek: DeepSeek V3.1 Terminus (thinking)
    deepseek-v3.1-terminus-thinking
    14181457$0.270$0.9503,462
    #96
    MiniMax: MiniMax M2.7
    minimax-m2.7
    14171456$0.250$1.0034,620
    #117
    Qwen: Qwen3 Next 80B A3B Instruct
    qwen3-next-80b-a3b-instruct
    14021455$0.090$1.1022,873
    #57
    Qwen: Qwen3.5 397B A17B
    qwen3.5-397b-a17b
    14441454$0.385$2.4543,048
    #220
    OpenAI: gpt-oss-20b
    gpt-oss-20b
    13181447$0.029$0.14010,627
    #124
    Qwen: Qwen3.5-35B-A3B
    qwen3.5-35b-a3b
    13961446$0.140$1.0029,248
    #130
    MiniMax: MiniMax M2.5
    minimax-m2.5
    13911443$0.150$0.90041,271
    #115
    OpenAI: GPT-5.4 Nano (high)
    gpt-5.4-nano-high
    14031442$0.200$1.2538,610
    #111
    Qwen: Qwen3.5-27B
    qwen3.5-27b
    14091442$0.195$1.5627,421
    #79
    Z.ai: GLM 4.6
    glm-4.6
    14251441$0.430$1.7435,640
    #178
    Qwen: Qwen3 32B
    qwen3-32b
    13471439$0.080$0.2803,926
    #94
    Qwen: Qwen3.5-122B-A10B
    qwen3.5-122b-a10b
    14171438$0.260$2.0828,575
    #153
    Qwen: Qwen3 Next 80B A3B Thinking (thinking)
    qwen3-next-80b-a3b-thinking
    13701433$0.098$0.78013,693
    #216
    Google: Gemma 3n 4B
    gemma-3n-e4b-it
    13181432$0.060$0.12022,594
    #87
    DeepSeek: R1 0528
    deepseek-r1-0528
    14221430$0.500$2.1518,463
    #150
    Z.ai: GLM 4.5 Air
    glm-4.5-air
    13731429$0.130$0.85031,077
    #190
    OpenAI: GPT-5 Nano (high)
    gpt-5-nano-high
    13371429$0.050$0.4008,266
    #231
    IBM: Granite 4.1 8B
    granite-4.1-8b
    13071429$0.050$0.1004,065
    #238
    Google: Gemma 3 4B
    gemma-3-4b-it
    13031425$0.050$0.1004,171
    #108
    Google: Gemini 2.5 Flash
    gemini-2.5-flash
    14101423$0.300$2.50124,544
    #145
    Arcee AI: Trinity Large Thinking
    trinity-large-preview
    13791423$0.250$0.80030,145
    #140
    MiniMax: MiniMax M2.1
    minimax-m2.1-preview
    13841422$0.290$0.95017,128
    #90
    MoonshotAI: Kimi K2 0905
    kimi-k2-0905-preview
    14181419$0.600$2.5011,780
    #146
    Z.ai: GLM 4.6V
    glm-4.6v
    13771415$0.300$0.9002,805
    #107
    Z.ai: GLM 4.5
    glm-4.5
    14111415$0.600$2.2024,310
    #131
    OpenAI: GPT-5 Mini (high)
    gpt-5-mini-high
    13901412$0.250$2.0027,021
    #125
    Qwen: Qwen3 VL 235B A22B Thinking (thinking)
    qwen3-vl-235b-a22b-thinking
    13961410$0.260$2.607,944
    #217
    Meta: Llama 3.3 70B Instruct
    llama-3.3-70b-instruct
    13181402$0.100$0.32054,734
    #142
    OpenAI: GPT-4.1 Mini
    gpt-4.1-mini-2025-04-14
    13831402$0.400$1.6039,329
    #211
    OpenAI: GPT-4.1 Nano
    gpt-4.1-nano-2025-04-14
    13221402$0.100$0.4006,103
    #259
    Mistral: Mistral Small 3
    mistral-small-24b-instruct-2501
    12741399$0.050$0.08014,681
    #166
    Prime Intellect: INTELLECT-3
    intellect-3
    13571399$0.200$1.105,331
    #203
    Qwen: Qwen3 30B A3B
    qwen3-30b-a3b
    13271398$0.120$0.50026,486
    #179
    Inception: Mercury 2
    mercury-2
    13461392$0.250$0.7503,124
    #147
    Qwen: Qwen3 235B A22B
    qwen3-235b-a22b
    13751389$0.455$1.8226,267
    #182
    MiniMax: MiniMax M2
    minimax-m2
    13461385$0.255$1.006,868
    #219
    OpenAI: GPT-4o-mini
    gpt-4o-mini-2024-07-18
    13181380$0.150$0.60068,709
    #219
    OpenAI: GPT-4o-mini (2024-07-18)
    gpt-4o-mini-2024-07-18
    13181380$0.150$0.60068,709
    #294
    Meta: Llama 3.1 8B Instruct
    llama-3.1-8b-instruct
    12111377$0.020$0.03049,605
    #158
    MiniMax: MiniMax M1
    minimax-m1
    13641376$0.400$2.2035,208
    #234
    AllenAI: Olmo 3 32B Think
    olmo-3-32b-think
    13051371$0.150$0.5005,946
    #271
    Microsoft: Phi 4
    phi-4
    12561366$0.065$0.14024,126
    #169
    Z.ai: GLM 4.5V
    glm-4.5v
    13531361$0.600$1.804,959
    #242
    Meta: Llama 3.1 70B Instruct
    llama-3.1-70b-instruct
    12931333$0.400$0.40055,240
    #273
    Cohere: Command R (08-2024)
    command-r-08-2024
    12501312$0.150$0.60010,140
    #287
    Meta: Llama 3 8B Instruct
    llama-3-8b-instruct
    12231308$0.140$0.140104,642
    #245
    Google: Gemma 2 27B
    gemma-2-27b-it
    12891307$0.650$0.65075,754
    #268
    Anthropic: Claude 3 Haiku
    claude-3-haiku-20240307
    12611295$0.250$1.25117,701
    #320
    Meta: Llama 3.2 3B Instruct
    llama-3.2-3b-instruct
    11661263$0.051$0.3357,936
    #349
    Meta: Llama 3.2 1B Instruct
    llama-3.2-1b-instruct
    11101231$0.027$0.2018,045

    Other use cases

    Best for codingBest for multilingualFull leaderboard