AI models

Compare up to five models

Select the models once. Every card then uses the same volume.

Full rate table

Models

Two to five. The result has its own link if you want to save it.

Currency AI models Order follows your selection.

Shared workload

Total tokens

Requests per day Tokens per request

Daily requests × tokens per request × 30 days.

Same assumptions

Pick two to five models.

Cost at the same volumes

Same mix on every model you picked. Each row is a larger token count.

List-price estimates, not invoices. Batch, priority, long-context, cache, regional, and negotiated rates can change the result.

ai21 / Jamba Large — $2.00/$8.00
ai21 / Jamba Mini — $0.2/$0.4
anthropic / Claude Fable 5 — $10.00/$50.00
anthropic / Claude Fable 5.1 — $10.00/$50.00
anthropic / Claude Opus 5 — $5.00/$25.00
anthropic / Claude Sonnet 5 — $3.00/$15.00
anthropic / Claude Haiku 4.5 — $1.00/$5.00
anthropic / Claude Opus 4.5 — $5.00/$25.00
anthropic / Claude Opus 4.8 — $5.00/$25.00
anthropic / Claude Sonnet 4.6 — $3.00/$15.00
anthropic / Claude Mythos 5.1 — $10.00/$50.00
azure / GPT-5.4 mini (Azure Global) — $0.75/$4.50
azure / GPT-4o mini (Azure Global) — $0.15/$0.6
azure / GPT-4o (Azure Global) — $2.50/$10.00
azure / GPT-5.4 (Azure Global, short context) — $2.50/$15.00
baseten / Kimi K3 (Baseten) — $3.00/$15.00
baseten / GLM-5.2 (Baseten) — $1.40/$4.40
baseten / GLM-5.2 Fast (Baseten) — $2.10/$6.60
baseten / GPT OSS 120B (Baseten) — $0.1/$0.5
baseten / DeepSeek V4 (Baseten) — $1.74/$3.48
baseten / Kimi K2.6 (Baseten) — $0.95/$4.00
cerebras / GPT OSS 120B (Cerebras) — $0.35/$0.75
cerebras / Gemma 4 31B (Cerebras) — $0.99/$1.49
cerebras / GLM 4.7 (Cerebras) — $2.25/$2.75
cloudflare / Llama 3.3 70B (Workers AI) — $0.293/$2.253
cloudflare / Llama 4 Scout (Workers AI) — $0.27/$0.85
cloudflare / gpt-oss-120b (Workers AI) — $0.35/$0.75
cloudflare / Gemma 4 26B (Workers AI) — $0.1/$0.3
cloudflare / Llama 3.1 8B Instruct FP8 Fast (Workers AI) — $0.045/$0.384
cloudflare / GPT OSS 20B (Workers AI) — $0.2/$0.3
cohere / Command A — $2.50/$10.00
cohere / Command R+ — $2.50/$10.00
cohere / Command R — $0.5/$1.50
cohere / Command Light — $0.3/$0.6
cohere / Aya Expanse — $0.5/$1.50
deepinfra / Llama 3.3 70B Turbo (DeepInfra) — $0.1/$0.32
deepinfra / Llama 3.1 8B Turbo (DeepInfra) — $0.02/$0.04
deepinfra / DeepSeek V4 Flash (DeepInfra) — $0.09/$0.18
deepinfra / DeepSeek V4 Pro (DeepInfra) — $1.30/$2.60
deepinfra / Llama 4 Scout (DeepInfra) — $0.1/$0.3
deepinfra / Llama 4 Maverick (DeepInfra) — $0.2/$0.8
deepinfra / Qwen3 32B (DeepInfra) — $0.08/$0.28
deepinfra / Mistral Nemo (DeepInfra) — $0.019/$0.03
deepinfra / Gemma 4 31B Turbo (DeepInfra) — $0.09/$0.34
deepseek / DeepSeek V4 Flash — $0.15/$0.6
deepseek / DeepSeek V4 Pro — $0.66/$1.98
deepseek / DeepSeek V4.1 Flash — $0.15/$0.6
fireworks / Kimi K3 (Fireworks) — $3.00/$15.00
fireworks / DeepSeek V4 Pro (Fireworks) — $1.74/$3.48
fireworks / DeepSeek V4 Flash (Fireworks) — $0.14/$0.28
fireworks / GLM 5.2 (Fireworks) — $1.40/$4.40
fireworks / MiniMax M3 (Fireworks) — $0.3/$1.20
fireworks / GPT OSS 120B (Fireworks) — $0.15/$0.6
fireworks / GPT OSS 20B (Fireworks) — $0.07/$0.3
fireworks / Kimi K2.6 (Fireworks) — $0.95/$4.00
friendli / GLM-5.2 (FriendliAI) — $1.40/$4.40
friendli / DeepSeek V3.2 (FriendliAI) — $0.5/$1.50
friendli / Gemma 4 31B (FriendliAI) — $0.14/$0.4
friendli / MiniMax M2.5 (FriendliAI) — $0.3/$1.20
google / Gemini 3.1 Pro — $2.00/$12.00
google / Gemini 3.6 Flash — $0.75/$3.75
google / Gemini 3.7 Flash — $0.75/$3.75
google / Gemini 3.5 Flash — $1.50/$9.00
google / Gemini 3 Flash Preview — $0.5/$3.00
google / Gemini 3.1 Flash-Lite — $0.25/$1.50
google / Gemini 3.5 Flash-Lite — $0.3/$2.50
google / Gemini 2.5 Pro — $1.25/$10.00
google / Gemini 3.8 Flash — $0.75/$3.75
google / Gemini 2.5 Flash — $0.3/$2.50
google / Gemini 2.5 Flash-Lite — $0.1/$0.4
google / Gemini Embedding 2 — $0.2/$0
google / Gemini Embedding 001 — $0.15/$0
google / Gemini 3.1 Flash TTS Preview — $1.00/$20.00
google / Gemini Robotics ER 2 Preview — $2.00/$10.00
groq / Llama 3.3 70B Versatile (Groq) — $0.59/$0.79
groq / Llama 3.1 8B Instant (Groq) — $0.05/$0.08
groq / GPT OSS 120B (Groq) — $0.15/$0.6
groq / GPT OSS 20B (Groq) — $0.075/$0.3
groq / Qwen 3.6 27B (Groq) — $0.6/$3.00
groq / Llama Prompt Guard 2 22M (Groq) — $0.03/$0.03
groq / Llama Prompt Guard 2 86M (Groq) — $0.04/$0.04
hyperbolic / Llama 3.3 70B (Hyperbolic) — $0.12/$0.3
hyperbolic / Llama 3.1 8B (Hyperbolic) — $0.1/$0.1
hyperbolic / DeepSeek V3 (Hyperbolic) — $0.25/$0.25
ibm / Granite 4H Small (watsonx.ai) — $0.0636/$0.265
ibm / Llama 4 Maverick (watsonx.ai) — $0.371/$1.484
ibm / Llama 3.3 70B (watsonx.ai) — $0.7526/$0.7526
ibm / Mistral Small 3.1 24B (watsonx.ai) — $0.106/$0.318
ibm / Mistral Large (watsonx.ai) — $0.636/$1.908
ibm / GPT OSS 120B (watsonx.ai) — $0.159/$0.636
iflytek / Spark X2.5 — $0.236/$0.886
inception / Mercury 2 — $0.25/$0.75
inception / Mercury Edit 2 — $0.25/$0.75
inclusionai / Ling 3.0 Flash — $0.06/$0.18
jina / jina-embeddings-v3 — $0.05/$0
meta / Muse Spark 1.3 — $1.25/$4.25
meta / Muse Spark 1.3 Contributor — $0.1/$0.2
microsoft / MAI-Thinking-1 — $2.00/$8.00
microsoft / MAI-Code-1.1-Flash — $0.2/$1.20
microsoft / MAI-Code-1-Flash — $0.75/$4.50
minimax / MiniMax M3 — $0.3/$1.20
minimax / MiniMax M2.7 — $0.3/$1.20
mistral / Mistral Large 3 — $0.5/$1.50
mistral / Mistral Small 4 — $0.15/$0.6
mistral / Mistral Medium 3.5 — $1.50/$7.50
mistral / Codestral — $0.3/$0.9
mistral / Ministral 3B — $0.1/$0.1
mistral / Ministral 8B — $0.15/$0.15
mistral / Ministral 14B — $0.2/$0.2
mistral / Mistral Embed — $0.1/$0
moonshot / Kimi K3 — $3.00/$15.00
moonshot / Kimi K2.6 — $0.95/$4.00
moonshot / Kimi K2.5 — $0.6/$3.00
nebius / Gemma 3 27B (Nebius) — $0.1/$0.3
nebius / GLM-5.2 (Nebius) — $1.40/$4.40
nebius / Kimi K3 (Nebius) — $3.00/$15.00
nebius / Llama 3.1 405B (Nebius) — $1.00/$3.00
nex / Nex-N2-Mini — $0.025/$0.1
nex / Nex-N2-Pro — $0.25/$1.00
novita / Llama 3.1 8B Instruct (Novita) — $0.02/$0.05
novita / Llama 3.3 70B Instruct (Novita) — $0.135/$0.4
novita / Llama 4 Scout (Novita) — $0.18/$0.59
novita / Llama 4 Maverick (Novita) — $0.27/$0.85
novita / DeepSeek V3.2 (Novita) — $0.269/$0.4
openai / GPT-6 Astra — $10.00/$50.00
openai / GPT-5.5 — $5.00/$30.00
openai / GPT-5.4 — $2.50/$15.00
openai / GPT-5.4 mini — $0.75/$4.50
openai / GPT-5.4 nano — $0.2/$1.25
openai / GPT-5.6 Terra — $2.00/$12.00
openai / GPT-5.6 Sol — $5.00/$30.00
openai / GPT-5.6 Luna — $0.2/$1.20
openai / GPT-5 mini — $0.25/$2.00
openai / GPT-5 nano — $0.05/$0.4
openai / o4-mini — $1.10/$4.40
openai / o3 — $2.00/$8.00
openai / GPT-4.1 — $2.00/$8.00
openai / GPT-4o — $2.50/$10.00
openai / GPT-4o mini — $0.15/$0.6
openai / GPT-5.5 Pro — $30.00/$180.00
openai / GPT-5.4 Pro — $30.00/$180.00
openai / GPT-5.2 — $1.75/$14.00
openai / GPT-5.3 Codex — $1.75/$14.00
openai / GPT-4.1 mini — $0.4/$1.60
openai / GPT-4.1 nano — $0.1/$0.4
openai / text-embedding-3-small — $0.02/$0
openai / text-embedding-3-large — $0.13/$0
openrouter / GPT-5.4 Mini (OpenRouter) — $0.75/$4.50
openrouter / Claude Sonnet 4.6 (OpenRouter) — $3.00/$15.00
openrouter / Gemini 3.6 Flash (OpenRouter) — $0.75/$3.75
openrouter / Mistral Small 4 (OpenRouter) — $0.15/$0.6
openrouter / DeepSeek V3.2 (OpenRouter) — $0.269/$0.4
openrouter / Llama 4 Scout (OpenRouter) — $0.1/$0.3
parasail / DeepSeek V4 Flash (Parasail) — $0.14/$0.28
parasail / GLM-5.2 (Parasail) — $1.40/$4.40
parasail / DeepSeek V4 Pro (Parasail) — $1.74/$3.48
parasail / MiniMax M3 (Parasail) — $0.3/$1.20
parasail / Mistral Small 3.2 24B (Parasail) — $0.09/$0.3
parasail / gpt-oss-120b (Parasail) — $0.1/$0.75
parasail / Gemma 4 31B (Parasail) — $0.15/$0.4
parasail / Kimi K2.6 (Parasail) — $0.75/$3.50
perplexity / Sonar — $1.00/$1.00
perplexity / Sonar Pro — $3.00/$15.00
perplexity / Sonar Reasoning Pro — $2.00/$8.00
perplexity / Sonar Deep Research — $2.00/$8.00
qwen / Qwen3.7 Max — $2.50/$7.50
qwen / Qwen3.8 Max — $2.00/$6.00
qwen / Qwen3.5 Plus — $0.4/$2.40
qwen / Qwen3.5 Flash — $0.1/$0.4
sambanova / GPT OSS 120B (SambaNova) — $0.22/$0.59
sambanova / Gemma 4 31B (SambaNova) — $0.38/$1.15
sambanova / Llama 3.3 70B (SambaNova) — $0.6/$1.20
sambanova / MiniMax M2.7 (SambaNova) — $0.6/$2.40
siliconflow / DeepSeek V4 Flash (SiliconFlow) — $0.13/$0.28
siliconflow / DeepSeek V3.2 (SiliconFlow) — $0.27/$0.42
siliconflow / Qwen3.5 9B (SiliconFlow) — $0.1/$0.15
siliconflow / GLM-5.2 (SiliconFlow) — $1.302/$4.092
siliconflow / Kimi K3 (SiliconFlow) — $3.00/$15.00
siliconflow / gpt-oss-120b (SiliconFlow) — $0.05/$0.45
siliconflow / MiniMax M3 (SiliconFlow) — $0.3/$1.20
together / DeepSeek V4 Pro (Together) — $1.74/$3.48
together / MiniMax M3 (Together) — $0.3/$1.20
together / Kimi K3 (Together) — $3.00/$15.00
together / GLM 5.2 (Together) — $1.40/$4.40
together / Llama 3.3 70B (Together) — $1.04/$1.04
together / GPT OSS 120B (Together) — $0.15/$0.6
together / GPT OSS 20B (Together) — $0.05/$0.2
together / Gemma 3n E4B Instruct (Together) — $0.06/$0.12
together / Kimi K2.6 (Together) — $1.20/$4.50
together / Qwen3.5 9B (Together) — $0.17/$0.25
voyage / voyage-4-large — $0.12/$0
voyage / voyage-4 — $0.06/$0
voyage / voyage-4-lite — $0.02/$0
voyage / voyage-code-3 — $0.18/$0
voyage / rerank-2.5 — $0.05/$0
xai / Grok 4.6 — $2.00/$6.00
xai / Grok 4.5 — $2.00/$6.00
xai / Grok 4.3 — $1.25/$2.50
xai / Grok Build 0.1 — $1.00/$2.00
xai / Grok 4.20 Reasoning — $1.25/$2.50
zai / GLM-5 — $1.00/$3.20
zai / GLM-5-Turbo — $1.20/$4.00
zai / GLM-5.2 — $1.40/$4.40
zai / GLM-5.3 — $1.40/$4.40