Cost per task vs price per token
A model's list price is per token, but your bill depends on how many tokens it spends on each job. Wordy answers and long hidden reasoning can make a cheap-looking model expensive, and a terse model cheaper than its price suggests. Cost per task is the average spend on one task of the Artificial Analysis Intelligence Index, counting the tokens each model actually used, as of Nov 16, 2026. 52 models have both figures.
Biggest surprises
Pricier than they look
Rank much worse per task than by list price: they spend more tokens per job.
- Gemini 3.8 Flash#21 by price → #50 per task · $6.26
- Gemini 4 Carbon#32 by price → #46 per task · $4.68
- Gemini 4 Argon#31 by price → #44 per task · $4.31
- GLM 5.3 Flash#7 by price → #19 per task · $0.58
- Nemotron 3.5 Super VL#8 by price → #18 per task · $0.56
Cheaper than they look
Rank much better per task than by list price: they finish jobs in fewer tokens.
- Claude Sonnet 5.5#44 by price → #21 per task · $0.78
- GPT-6.1 Sol#34 by price → #14 per task · $0.36
- Mistral Medium 3.5#42 by price → #24 per task · $1.04
- GPT-6.1 Terra#23 by price → #6 per task · $0.17
- Claude Haiku 4.5#30 by price → #17 per task · $0.53
All models, cheapest per task first
| Model | $/task | Blended $/M tokens | Rank by price → per task | Analyzer Index |
|---|---|---|---|---|
| Mistral Small 4 Mistral | $0.04 | $0.26 | #12 → #1 | — |
| GPT-6 Luna OpenAI | $0.04 | $0.10 | #1 → #2 | 63.7 |
| Claude Haiku 5.5 Anthropic | $0.09 | $0.20 | #4 → #3 | 61.9 |
| Muse Ember Meta | $0.12 | $0.20 | #5 → #4 | — |
| MiMo-V2.6-Flash Xiaomi (MiMo) | $0.13 | $0.18 | #3 → #5 | — |
| GPT-6.1 Terra OpenAI | $0.17 | $1.00 | #23 → #6 | — |
| Muse Glimmer 30B Meta | $0.18 | $0.52 | #17 → #7 | — |
| Gemini 3.1 Flash Lite Google | $0.19 | $0.28 | #13 → #8 | 50.1 |
| Inkling Small Thinking Machines | $0.20 | $0.64 | #20 → #9 | 59.4 |
| MiMo-V2.6-Pro Xiaomi (MiMo) | $0.26 | $0.54 | #18 → #10 | — |
| Nemotron 3.5 Lightning NVIDIA | $0.31 | $0.10 | #2 → #11 | — |
| GPT-5.6 Luna OpenAI | $0.33 | $0.23 | #6 → #12 | 67.5 |
| gpt-oss-120b OpenAI | $0.35 | $0.26 | #10 → #13 | 44.3 |
| GPT-6.1 Sol OpenAI | $0.36 | $2.00 | #34 → #14 | 88.7 |
| DeepSeek V4.1 Flash 1017 DeepSeek | $0.46 | $0.26 | #9 → #15 | — |
| MiniMax M3.1 Flash MiniMax | $0.49 | $0.26 | #11 → #16 | — |
| Claude Haiku 4.5 Anthropic | $0.53 | $2.00 | #30 → #17 | 45.5 |
| Nemotron 3.5 Super VL NVIDIA | $0.56 | $0.24 | #8 → #18 | — |
| GLM 5.3 Flash Zhipu AI (GLM) | $0.58 | $0.24 | #7 → #19 | 69.8 |
| Gemini 3.5 Flash Lite Google | $0.69 | $0.43 | #14 → #20 | 44.4 |
| Claude Sonnet 5.5 Anthropic | $0.78 | $4.00 | #44 → #21 | 81.5 |
| Gemini 4 Hydrogen Google | $0.80 | $1.50 | #28 → #22 | — |
| Hy4 Tencent (Hunyuan) | $1.03 | $0.63 | #19 → #23 | — |
| Mistral Medium 3.5 Mistral | $1.04 | $3.00 | #42 → #24 | — |
| Inkling 2 Small Thinking Machines | $1.18 | $0.48 | #15 → #25 | — |
| MiniMax M3 MiniMax | $1.29 | $0.52 | #16 → #26 | 53.5 |
| Inkling Thinking Machines | $1.35 | $1.76 | #29 → #27 | 59.2 |
| Mistral Large 4 Mistral | $1.41 | $1.05 | #24 → #28 | 61.9 |
| GLM 5.3 Zhipu AI (GLM) | $1.57 | $2.15 | #37 → #29 | 72.4 |
| DeepSeek V4 Pro 0423 DeepSeek | $1.77 | $1.05 | #26 → #30 | 64.3 |
| Muse Spark Open Meta | $2.02 | $2.00 | #36 → #31 | — |
| Qwen3.8 27B Alibaba (Qwen) | $2.16 | $0.96 | #22 → #32 | — |
| Nemotron 3 Ultra NVIDIA | $2.21 | $1.05 | #25 → #33 | 57.9 |
| Step 5 Preview StepFun | $2.35 | $1.43 | #27 → #34 | — |
| Kimi K3 Moonshot (Kimi) | $2.37 | $6.00 | #46 → #35 | 77.3 |
| Muse Spark 1.3 Meta | $2.39 | $2.00 | #35 → #36 | 87.0 |
| Claude Opus 5.5 Anthropic | $2.45 | $8.00 | #47 → #37 | 93.8 |
| GPT-6 Sol OpenAI | $2.47 | $2.00 | #33 → #38 | 79.8 |
| GPT-6 Astra OpenAI | $2.73 | $10.00 | #50 → #39 | 91.3 |
| Qwen4 Max Alibaba (Qwen) | $3.27 | $2.25 | #39 → #40 | — |
| Kimi K3.1 Pro Moonshot (Kimi) | $3.68 | $4.00 | #45 → #41 | 81.5 |
| GPT-5.6 Terra OpenAI | $3.73 | $2.25 | #38 → #42 | 77.5 |
| Claude Fable 5.2 Anthropic | $3.80 | $16.00 | #51 → #43 | — |
| Gemini 4 Argon Google | $4.31 | $2.00 | #31 → #44 | 92.8 |
| Muse Wonder Meta | $4.56 | $8.00 | #48 → #45 | 89.0 |
| Gemini 4 Carbon Google | $4.68 | $2.00 | #32 → #46 | 95.7 |
| Grok 4.6 xAI | $4.68 | $3.00 | #40 → #47 | 74.3 |
| Claude Fable 5.1 Anthropic | $5.56 | $20.00 | #52 → #48 | 91.3 |
| Grok 4.7 xAI | $6.18 | $3.00 | #41 → #49 | 71.3 |
| Gemini 3.8 Flash Google | $6.26 | $0.75 | #21 → #50 | 81.0 |
| Qwen3.8 Max (0902) Alibaba (Qwen) | $10.02 | $3.00 | #43 → #51 | — |
| Claude Opus 5 Anthropic | $11.82 | $10.00 | #49 → #52 | 86.9 |
Reading these figures
Blended price assumes three input tokens per output token. Cost per task reflects one task mix (Artificial Analysis's evaluation suite); your prompts may use more or fewer tokens. Effort variants of the same model are listed separately because higher reasoning effort uses more tokens per task. For your own workload, use the cost calculator, or sort the leaderboard by $/task.