AI API Cost Calculator
Estimate what a workload costs on 101 AI models, side by side. Pick a preset or enter your own token counts.
Provider list prices from EVA's model catalog, checked November 9, 2026. Estimates only.
Don't know your token count? Paste a sample prompt
≈ 0 tokens (about 4 characters each)
101 models, cheapest first, for 500 in + 500 out tokens
| Model | Input $/1M | Output $/1M | Per request | Per month |
|---|---|---|---|---|
 Qwen3.7 FlashQwen | $0.03 | $0.13 | $0.00008 | $0.08 |
 NVIDIA Nemotron 3.5 LightningNVIDIA | $0.07 | $0.2 | $0.00014 | $0.14 |
| Qwen3.5 FlashQwen | $0.065 | $0.26 | $0.00016 | $0.16 |
 Llama 4 ScoutMeta | $0.08 | $0.3 | $0.00019 | $0.19 |
 Ministral 3Mistral | $0.2 | $0.2 | $0.0002 | $0.2 |
 DeepSeek V4 FlashDeepSeek | $0.14 | $0.28 | $0.00021 | $0.21 |
| DeepSeek V4 Flash 0731DeepSeek | $0.14 | $0.3 | $0.00022 | $0.22 |
 GPT-5 nanoOpenAI | $0.05 | $0.4 | $0.00022 | $0.23 |
 Inception Mercury 3Inception | $0.1 | $0.35 | $0.00022 | $0.23 |
 Gemini 2.5 Flash-LiteGoogle | $0.1 | $0.4 | $0.00025 | $0.25 |
 Claude Haiku 5.5Anthropic | $0.1 | $0.5 | $0.0003 | $0.3 |
| GPT-6 LunaOpenAI | $0.1 | $0.5 | $0.0003 | $0.3 |
| Qwen3.8 FlashQwen | $0.15 | $0.47 | $0.00031 | $0.31 |
| Qwen3.8 Omni FlashQwen | $0.15 | $0.47 | $0.00031 | $0.31 |
 GLM-5.3 FlashGLM (z.ai) | $0.15 | $0.5 | $0.00032 | $0.33 |
| Llama 4 MaverickMeta | $0.15 | $0.6 | $0.00038 | $0.38 |
 MiniMax M3.1 FlashMiniMax | $0.15 | $0.6 | $0.00038 | $0.38 |
| Mistral Small 4Mistral | $0.15 | $0.6 | $0.00038 | $0.38 |
| DeepSeek V4.1 Flash 1017DeepSeek | $0.17 | $0.68 | $0.00042 | $0.42 |
| MiniMax M2.5MiniMax | $0.27 | $0.95 | $0.00061 | $0.61 |
 Reflection Beam 1.0Reflection | $0.25 | $1.00 | $0.00063 | $0.63 |
| GPT-5.4 nanoOpenAI | $0.2 | $1.25 | $0.00072 | $0.72 |
| Meta Muse Glimmer 30BMeta | $0.3 | $1.20 | $0.00075 | $0.75 |
| MiniMax M2.7MiniMax | $0.3 | $1.20 | $0.00075 | $0.75 |
| MiniMax M3MiniMax | $0.3 | $1.20 | $0.00075 | $0.75 |
| Qwen3.7 PlusQwen | $0.32 | $1.28 | $0.0008 | $0.8 |
| GLM-5.3 FlashXGLM (z.ai) | $0.37 | $1.25 | $0.00081 | $0.81 |
 Cohere Command A+Cohere | $0.3 | $1.50 | $0.0009 | $0.9 |
| Qwen3.5 PlusQwen | $0.26 | $1.56 | $0.00091 | $0.91 |
| GPT-4.1 miniOpenAI | $0.4 | $1.60 | $0.001 | $1.00 |
| Mistral Large 3Mistral | $0.5 | $1.50 | $0.001 | $1.00 |
| GPT-5 miniOpenAI | $0.25 | $2.00 | $0.0011 | $1.13 |
| Qwen3.6 PlusQwen | $0.33 | $1.95 | $0.0011 | $1.14 |
| Mistral Medium 3.1Mistral | $0.4 | $2.00 | $0.0012 | $1.20 |
| Qwen3.8 27BQwen | $0.18 | $2.30 | $0.0012 | $1.24 |
 SonarPerplexity | $0.25 | $2.50 | $0.0014 | $1.38 |
| Gemini 2.5 FlashGoogle | $0.3 | $2.50 | $0.0014 | $1.40 |
| Gemini 3.5 Flash-LiteGoogle | $0.3 | $2.50 | $0.0014 | $1.40 |
| Mistral Large 4Mistral | $0.7 | $2.10 | $0.0014 | $1.40 |
| NVIDIA Nemotron 3 UltraNVIDIA | $0.6 | $2.40 | $0.0015 | $1.50 |
| GLM-5GLM (z.ai) | $0.72 | $2.30 | $0.0015 | $1.51 |
 Kimi K2 ThinkingMoonshot | $0.6 | $2.50 | $0.0015 | $1.55 |
 Grok 4.3xAI | $1.25 | $2.50 | $0.0019 | $1.88 |
| GLM-5.1GLM (z.ai) | $1.00 | $3.20 | $0.0021 | $2.10 |
| Kimi K2.6Moonshot | $0.75 | $3.50 | $0.0021 | $2.13 |
| Gemini 3.6 FlashGoogle | $0.75 | $3.75 | $0.0022 | $2.25 |
| Gemini 3.8 FlashGoogle | $0.75 | $3.75 | $0.0022 | $2.25 |
| DeepSeek V4 ProDeepSeek | $1.49 | $3.13 | $0.0023 | $2.31 |
| GLM-5.3GLM (z.ai) | $1.01 | $3.85 | $0.0024 | $2.43 |
| GPT-5.4 miniOpenAI | $0.75 | $4.50 | $0.0026 | $2.63 |
| DeepSeek V4 Pro 0813DeepSeek | $1.32 | $3.96 | $0.0026 | $2.64 |
| Meta Muse Spark 1.3Meta | $1.25 | $4.25 | $0.0027 | $2.75 |
| GLM-5.2GLM (z.ai) | $1.40 | $4.40 | $0.0029 | $2.90 |
| Qwen3.7 MaxQwen | $1.48 | $4.42 | $0.0029 | $2.95 |
| Claude Haiku 4.5Anthropic | $1.00 | $5.00 | $0.003 | $3.00 |
| GPT-6.1 TerraOpenAI | $1.00 | $5.00 | $0.003 | $3.00 |
| GPT-5.6 LunaOpenAI | $1.00 | $6.00 | $0.0035 | $3.50 |
| Grok 4.20xAI | $2.00 | $6.00 | $0.004 | $4.00 |
| Grok 4.20 (Non-Reasoning)xAI | $2.00 | $6.00 | $0.004 | $4.00 |
| Grok 4.5xAI | $2.00 | $6.00 | $0.004 | $4.00 |
| Grok 4.6xAI | $2.00 | $6.00 | $0.004 | $4.00 |
| Grok 4.7xAI | $2.00 | $6.00 | $0.004 | $4.00 |
| Qwen3.8 MaxQwen | $2.00 | $6.00 | $0.004 | $4.00 |
| Mistral Medium 3.5Mistral | $1.50 | $7.50 | $0.0045 | $4.50 |
| GPT-4.1OpenAI | $2.00 | $8.00 | $0.005 | $5.00 |
| o3OpenAI | $2.00 | $8.00 | $0.005 | $5.00 |
| Perplexity Deep ResearchPerplexity | $2.00 | $8.00 | $0.005 | $5.00 |
| Perplexity ResearchPerplexity | $2.00 | $8.00 | $0.005 | $5.00 |
| GPT-5OpenAI | $1.25 | $10.00 | $0.0056 | $5.63 |
| GLM-5.3 PrimeGLM (z.ai) | $2.80 | $8.80 | $0.0058 | $5.80 |
| Claude Sonnet 5Anthropic | $2.00 | $10.00 | $0.006 | $6.00 |
| Claude Sonnet 5.5Anthropic | $2.00 | $10.00 | $0.006 | $6.00 |
| Gemini 4 ArgonGoogle | $2.00 | $10.00 | $0.006 | $6.00 |
| GPT-6.1 SolOpenAI | $2.00 | $10.00 | $0.006 | $6.00 |
| Kimi K3.1 ProMoonshot | $2.00 | $10.00 | $0.006 | $6.00 |
| GPT-5.2OpenAI | $1.75 | $14.00 | $0.0079 | $7.88 |
| Qwen3.8 Max PrimeQwen | $4.00 | $12.00 | $0.008 | $8.00 |
| Kimi K3Moonshot | $2.02 | $14.13 | $0.0081 | $8.08 |
| GPT-5.4OpenAI | $2.50 | $15.00 | $0.0088 | $8.75 |
| GPT-5.6 TerraOpenAI | $2.50 | $15.00 | $0.0088 | $8.75 |
| Claude Sonnet 4.5Anthropic | $3.00 | $15.00 | $0.009 | $9.00 |
| Claude Sonnet 4.6Anthropic | $3.00 | $15.00 | $0.009 | $9.00 |
| Perplexity Pro SearchPerplexity | $3.00 | $15.00 | $0.009 | $9.00 |
| Gemini 3.1 ProGoogle | $4.00 | $18.00 | $0.011 | $11.00 |
| Claude Opus 5.5Anthropic | $4.00 | $20.00 | $0.012 | $12.00 |
| Meta Muse WonderMeta | $4.00 | $20.00 | $0.012 | $12.00 |
| Claude Opus 4.5Anthropic | $5.00 | $25.00 | $0.015 | $15.00 |
| Claude Opus 4.6Anthropic | $5.00 | $25.00 | $0.015 | $15.00 |
| Claude Opus 4.7Anthropic | $5.00 | $25.00 | $0.015 | $15.00 |
| Claude Opus 4.8Anthropic | $5.00 | $25.00 | $0.015 | $15.00 |
| Claude Opus 5Anthropic | $5.00 | $25.00 | $0.015 | $15.00 |
| GPT-5.5OpenAI | $5.00 | $30.00 | $0.018 | $17.50 |
| GPT-5.6 SolOpenAI | $5.00 | $30.00 | $0.018 | $17.50 |
| Claude Fable 5Anthropic | $10.00 | $50.00 | $0.03 | $30.00 |
| Claude Fable 5.1Anthropic | $10.00 | $50.00 | $0.03 | $30.00 |
| GPT-6 AstraOpenAI | $10.00 | $50.00 | $0.03 | $30.00 |
| o3-proOpenAI | $20.00 | $80.00 | $0.05 | $50.00 |
| GPT-5 proOpenAI | $15.00 | $120 | $0.068 | $67.50 |
| GPT-5.2 proOpenAI | $21.00 | $168 | $0.095 | $94.50 |
| GPT-5.4 ProOpenAI | $30.00 | $180 | $0.1 | $105 |
| GPT-5.5 ProOpenAI | $30.00 | $180 | $0.1 | $105 |
Price is half the answer.
The cheapest model isn't always good enough for the job. In EVA you can send one prompt to up to four models and compare the answers side by side.
Try EVA FreeFrequently asked questions
- How is the cost calculated?
- Cost per request = input tokens × the model's input price per 1M tokens + output tokens × its output price per 1M tokens, divided by one million. The monthly figure multiplies that by your number of requests.
- Where do the prices come from?
- From EVA's model catalog: each provider's standard list price per 1M tokens for the way EVA calls that model. For models EVA reaches through OpenRouter, a typical (median) listed price is used. Prices are refreshed from the catalog every hour.
- What is a token?
- A token is a chunk of text a model reads or writes. For English, one token is roughly 4 characters or three-quarters of a word. Each model has its own tokenizer, so the same text can be a different number of tokens on different models.
- Why might my real bill differ?
- This is an estimate. Real costs also depend on long-context price tiers, cached input discounts, batch pricing, reasoning tokens that some models bill as output, images and files, and taxes. Check the provider's own pricing page before committing to a budget.
- Is this what EVA charges?
- No. These are the providers' API list prices. EVA plans use monthly credits that work across every model; see the pricing page for plan details. EVA pricing