CheapTokens
AI inference provider · 70 models listed · wins best price on 70.
Models listed
70
across our index
Best price wins
70
100% of models
Avg input
$0.769
USD / 1M tokens
Avg output
$3.99
USD / 1M tokens
All models at CheapTokens
Model
IQ
In/1M
Out/1M
Status
Qwen 3.5 9B
—
$0.020
$0.060
best
GPT OSS 20B
—
$0.020
$0.070
best
Qwen 2.5 7B
—
$0.020
$0.050
best
NVIDIA Nemotron 3 Nano 30B
—
$0.030
$0.110
best
OpenAI GPT OSS 120B
—
$0.030
$0.110
best
Google Gemma 3 27B Instruct
—
$0.040
$0.070
best
Mistral Small 3.2 24B Instruct
—
$0.040
$0.090
best
GLM 4.7 Flash Heretic
—
$0.050
$0.300
best
Nvidia Nemotron Cascade 2 30b A3b
—
$0.050
$0.300
best
Gemma 3 27B
—
$0.050
$0.190
best
GLM 4.7 Flash
—
$0.050
$0.210
best
GPT OSS 120B
—
$0.050
$0.240
best
GLM 4.7 Flash
—
$0.050
$0.190
best
Google Gemma 4 26b A4b It
—
$0.060
$0.190
best
Qwen 3 235B A22B Instruct 2507
—
$0.060
$0.280
best
Llama 3.2 3B
—
$0.060
$0.220
best
Venice Uncensored 1.1
—
$0.070
$0.340
best
Venice Uncensored 1 2
—
$0.070
$0.340
best
Qwen3 30B A3B
—
$0.070
$0.260
best
Mistral Small 2603
—
$0.070
$0.280
best
GPT-4o Mini
—
$0.070
$0.280
best
Google Gemma 4 31b It
—
$0.070
$0.190
best
Qwen3 VL 235B
—
$0.090
$0.560
best
Venice Uncensored 1.1
—
$0.090
$0.430
best
Qwen3 VL 30B A3B
—
$0.090
$0.340
best
Grok 4.1 Fast
38.6
$0.090
$0.210
best
DeepSeek V3.2
41.7
$0.120
$0.180
best
Qwen 3.5 35B A3B
—
$0.120
$0.470
best
Arcee Trinity Large Thinking
—
$0.120
$0.420
best
Mercury 2
—
$0.120
$0.350
best
Qwen 3 Next 80b
—
$0.130
$0.710
best
Qwen 3 Coder 480B Turbo
—
$0.130
$0.560
best
MiniMax M2.5
41.9
$0.130
$0.450
best
MiniMax M2.7
49.6
$0.140
$0.560
best
Qwen 3 235B A22B Thinking 2507
—
$0.170
$1.31
best
Venice Role Play Uncensored
—
$0.190
$0.750
best
Qwen3.5 122B A10B
—
$0.190
$1.50
best
Kimi K2.5
46.8
$0.210
$1.31
best
GLM 4.7
—
$0.210
$0.990
best
Qwen 3 6 Plus
50.0
$0.230
$1.41
best
Gemini 3 Flash Preview
46.4
$0.260
$1.41
best
Llama 3.3 70B
36.0
$0.260
$1.05
best
Qwen3 5 397b A17b
—
$0.280
$1.69
best
Qwen 3 Coder 480b
24.8
$0.280
$1.12
best
Kimi K2 Thinking
46.8
$0.280
$1.20
best
GLM 4.6
—
$0.320
$1.03
best
Openai Gpt 54 Mini
—
$0.350
$2.11
best
GLM 5
40.6
$0.370
$1.20
best
Aion Labs Aion 2 0
—
$0.370
$0.750
best
Hermes 3 Llama 3.1 405b
—
$0.410
$1.12
best
GLM 4.7
—
$0.410
$1.56
best
GLM 5
—
$0.410
$1.56
best
Z Ai Glm 5 Turbo
—
$0.450
$1.50
best
Z Ai Glm 5v Turbo
—
$0.560
$1.87
best
Zai Org Glm 5 1
51.4
$0.660
$2.06
best
GPT-5.2
44.6
$0.820
$6.56
best
GPT-5.2 Codex
44.6
$0.820
$6.56
best
GPT-5.3 Codex
53.6
$0.820
$6.56
best
Grok 4 20
38.6
$0.850
$2.55
best
Grok 4 20 Multi Agent
—
$0.850
$2.55
best
Gemini 3.1 Pro Preview
57.2
$0.940
$5.62
best
GPT-5.4
56.8
$1.17
$7.04
best
GPT-4o
—
$1.17
$4.68
best
Claude Sonnet 4.6
51.7
$1.35
$6.74
best
Claude Sonnet 4.5
—
$1.41
$7.03
best
Claude Opus 4 7
—
$2.25
$11.24
best
Claude Opus 4.6
53.0
$2.25
$11.24
best
Claude Opus 4.5
—
$2.25
$11.24
best
Claude Opus 4.6 Fast
—
$13.49
$67.45
best
GPT-5.4 Pro
—
$14.05
$84.31
best
Cite: CheapTokens pricing data
Citation
CheapTokens — AI inference pricing (70 models). Inference Index, 2026-04-16. https://inferenceindex.ai/providers/cheaptokensAPI
curl https://inferenceindex.ai/api/prices