Pricing
Per-token pricing, published for every model. One balance covers all of them.
Cost calculator
Estimate your monthly spend for a given token volume on a given model.
Model prices
3 input : 1 output token mix| Model | Input / MTok | Output / MTok | Blended 3:1 |
|---|---|---|---|
meta/llama-prompt-guard-2 | $0.02 | $0.02 | $0.02 |
google/gemma-3n-e4b | $0.03 | $0.10 | $0.048 |
meta/llama-guard-4-12b | $0.05 | $0.10 | $0.063 |
microsoft/phi-4-multimodal | $0.05 | $0.10 | $0.063 |
microsoft/phi-4-mini | $0.04 | $0.14 | $0.065 |
microsoft/phi-4-mini-reasoning | $0.04 | $0.14 | $0.065 |
arcee/afm-4.5b | $0.04 | $0.16 | $0.07 |
nvidia/nemotron-nano-9b-v2 | $0.04 | $0.16 | $0.07 |
google/gemma-4-12b | $0.05 | $0.20 | $0.088 |
microsoft/phi-4-reasoning-plus | $0.07 | $0.14 | $0.088 |
liquid/lfm2-8b | $0.05 | $0.20 | $0.088 |
google/gemma-3-12b-it | $0.05 | $0.20 | $0.088 |
qwen/qwq-32b | $0.06 | $0.20 | $0.095 |
amazon/nova-2-lite | $0.06 | $0.24 | $0.11 |
qwen/qwen3-30b-a3b | $0.07 | $0.22 | $0.11 |
qwen/qwen3-32b | $0.08 | $0.25 | $0.12 |
openai/gpt-5-nano | $0.05 | $0.40 | $0.14 |
qwen/qwen3-coder-30b | $0.09 | $0.30 | $0.14 |
mistralai/mistral-small-3.2 | $0.10 | $0.30 | $0.15 |
mistralai/voxtral-small | $0.10 | $0.30 | $0.15 |
deepseek/deepseek-r1-distill-llama-70b | $0.10 | $0.30 | $0.15 |
mistralai/devstral-small-1.1 | $0.10 | $0.30 | $0.15 |
google/gemma-4-27b | $0.09 | $0.35 | $0.16 |
google/gemma-3-27b-it | $0.09 | $0.35 | $0.16 |
google/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.18 |
google/gemini-2.0-flash | $0.10 | $0.40 | $0.18 |
nvidia/llama-3.3-nemotron-super-49b | $0.10 | $0.40 | $0.18 |
openai/gpt-4.1-nano | $0.10 | $0.40 | $0.18 |
qwen/qwen3-omni-flash | $0.10 | $0.40 | $0.18 |
nousresearch/hermes-4-70b | $0.13 | $0.40 | $0.20 |
qwen/qwen3-vl-30b | $0.12 | $0.50 | $0.22 |
moonshotai/kimi-linear-48b | $0.12 | $0.50 | $0.22 |
moonshotai/kimi-linear-2-80b | $0.12 | $0.50 | $0.22 |
qwen/qwen3-coder-next | $0.14 | $0.50 | $0.23 |
ai21/jamba-mini-1.7 | $0.20 | $0.40 | $0.25 |
meta/llama-4-scout | $0.15 | $0.60 | $0.26 |
x-ai/grok-code-fast-1 | $0.15 | $0.60 | $0.26 |
moonshotai/kimi-dev-72b | $0.15 | $0.60 | $0.26 |
deepseek/deepseek-v4-flash | $0.15 | $0.60 | $0.26 |
qwen/qwen3.8-flash-next | $0.12 | $0.70 | $0.27 |
x-ai/grok-4.1-fast | $0.20 | $0.50 | $0.28 |
x-ai/grok-4.1-fast-non-reasoning | $0.20 | $0.50 | $0.28 |
x-ai/grok-4-fast | $0.20 | $0.50 | $0.28 |
x-ai/grok-4.2-fast | $0.20 | $0.50 | $0.28 |
thedrummer/anubis-24b | $0.20 | $0.55 | $0.29 |
thedrummer/cydonia-24b | $0.20 | $0.55 | $0.29 |
thedrummer/valkyrie-12b | $0.20 | $0.55 | $0.29 |
meta/llama-4.1-scout-109b | $0.18 | $0.65 | $0.30 |
qwen/qwen3-235b-a22b | $0.20 | $0.60 | $0.30 |
qwen/qwen3.5-flash | $0.15 | $0.90 | $0.34 |
x-ai/grok-3-mini | $0.30 | $0.50 | $0.35 |
meta/llama-4-maverick | $0.22 | $0.85 | $0.38 |
zhipu/glm-5.3-flash | $0.20 | $1.00 | $0.40 |
sao10k/l3.3-euryale-70b | $0.30 | $0.75 | $0.41 |
zhipu/glm-4.5-air | $0.20 | $1.10 | $0.43 |
zhipu/glm-5-air | $0.20 | $1.10 | $0.43 |
inception/mercury-2 | $0.25 | $1.00 | $0.44 |
inception/mercury-2-coder | $0.25 | $1.00 | $0.44 |
meta/llama-4.1-maverick-405b | $0.28 | $0.95 | $0.45 |
mistralai/codestral-25.08 | $0.30 | $0.90 | $0.45 |
deepseek/deepseek-v3.2 | $0.27 | $1.10 | $0.48 |
qwen/qwen3-coder-480b | $0.29 | $1.20 | $0.52 |
qwen/qwen3-vl-235b | $0.30 | $1.20 | $0.52 |
minimax/minimax-m2 | $0.30 | $1.20 | $0.52 |
deepseek/deepseek-math-v2 | $0.30 | $1.20 | $0.52 |
openai/gpt-5.6-luna | $0.30 | $1.20 | $0.52 |
deepseek/deepseek-v4 | $0.35 | $1.40 | $0.61 |
minimax/minimax-m2.5 | $0.35 | $1.40 | $0.61 |
qwen/qwen3.5-397b-a17b | $0.40 | $1.40 | $0.65 |
openai/gpt-5.1-codex-mini | $0.25 | $2.00 | $0.69 |
openai/gpt-5-mini | $0.25 | $2.00 | $0.69 |
openai/gpt-4.1-mini | $0.40 | $1.60 | $0.70 |
qwen/qwen3.5-vl-plus | $0.40 | $1.60 | $0.70 |
zhipu/glm-4.6 | $0.40 | $1.75 | $0.74 |
mistralai/voxtral-large | $0.50 | $1.50 | $0.75 |
mistralai/magistral-small-1.2 | $0.50 | $1.50 | $0.75 |
qwen/qwen3-coder-plus | $0.45 | $1.80 | $0.79 |
mistralai/mistral-medium-3.1 | $0.40 | $2.00 | $0.80 |
mistralai/devstral-2 | $0.40 | $2.00 | $0.80 |
moonshotai/kimi-k2-0905 | $0.40 | $2.00 | $0.80 |
mistralai/mistral-medium-3.2 | $0.40 | $2.00 | $0.80 |
meta/llama-4.1-behemoth-2t | $0.75 | $1.00 | $0.81 |
minimax/minimax-m1 | $0.40 | $2.10 | $0.83 |
deepseek/deepseek-v3.1-terminus | $0.55 | $1.68 | $0.83 |
google/gemini-2.5-flash | $0.30 | $2.50 | $0.85 |
google/gemini-2.5-flash-image | $0.30 | $2.50 | $0.85 |
google/gemini-3-flash-image | $0.30 | $2.50 | $0.85 |
deepseek/deepseek-r1-0528 | $0.45 | $2.15 | $0.88 |
zhipu/glm-5 | $0.50 | $2.00 | $0.88 |
qwen/qwen3.5-coder | $0.50 | $2.00 | $0.88 |
zhipu/glm-5.3 | $0.50 | $2.00 | $0.88 |
zhipu/glm-4.5v | $0.60 | $1.80 | $0.90 |
nvidia/nemotron-ultra-253b | $0.60 | $1.80 | $0.90 |
google/gemini-3.6-flash | $0.40 | $2.40 | $0.90 |
deepseek/deepseek-r2 | $0.55 | $2.20 | $0.96 |
perplexity/sonar | $1.00 | $1.00 | $1.00 |
google/gemini-3-flash | $0.50 | $3.00 | $1.13 |
google/gemini-3.8-flashpopular | $0.50 | $3.00 | $1.13 |
moonshotai/kimi-k2.5 | $0.60 | $2.80 | $1.15 |
moonshotai/kimi-k2-thinking | $0.60 | $2.80 | $1.15 |
moonshotai/kimi-k3 | $0.70 | $3.00 | $1.28 |
amazon/nova-2-omni | $0.80 | $3.20 | $1.40 |
nousresearch/hermes-4.5-405b | $1.00 | $3.00 | $1.50 |
nousresearch/hermes-4-405b | $1.00 | $3.00 | $1.50 |
amazon/nova-2-pro | $0.90 | $3.60 | $1.58 |
google/gemini-2.5-flash-native-audio | $1.00 | $3.50 | $1.63 |
qwen/qwen3.5-plus | $0.90 | $4.50 | $1.80 |
openai/o4-mini | $1.10 | $4.40 | $1.93 |
anthropic/claude-haiku-4.5 | $1.00 | $5.00 | $2.00 |
anthropic/claude-haiku-4.6 | $1.00 | $5.00 | $2.00 |
qwen/qwen3.8-max | $1.10 | $5.50 | $2.20 |
qwen/qwen3-max | $1.20 | $6.00 | $2.40 |
microsoft/mai-2 | $1.50 | $6.00 | $2.63 |
mistralai/magistral-2 | $2.00 | $5.00 | $2.75 |
mistralai/mistral-large-3 | $2.00 | $6.00 | $3.00 |
openai/gpt-5.6-terra | $1.50 | $7.50 | $3.00 |
openai/gpt-5.1 | $1.25 | $10.00 | $3.44 |
openai/gpt-5.1-codex-max | $1.25 | $10.00 | $3.44 |
openai/gpt-5.1-chat | $1.25 | $10.00 | $3.44 |
google/gemini-2.5-pro | $1.25 | $10.00 | $3.44 |
openai/gpt-4.1 | $2.00 | $8.00 | $3.50 |
perplexity/sonar-reasoning-pro | $2.00 | $8.00 | $3.50 |
perplexity/sonar-deep-research | $2.00 | $8.00 | $3.50 |
ai21/jamba-large-1.7 | $2.00 | $8.00 | $3.50 |
openai/o3 | $2.00 | $8.00 | $3.50 |
google/gemini-3-pro-image | $1.20 | $12.00 | $3.90 |
openai/gpt-5.6-sol | $2.00 | $10.00 | $4.00 |
openai/gpt-5.2-codex | $1.50 | $12.00 | $4.13 |
openai/gpt-image-1-mini | $1.50 | $12.00 | $4.13 |
cohere/command-a | $2.50 | $10.00 | $4.38 |
cohere/command-a-translate | $2.50 | $10.00 | $4.38 |
cohere/command-a-reasoning | $2.50 | $10.00 | $4.38 |
google/gemini-3-propopular | $2.00 | $12.00 | $4.50 |
google/gemini-3-deep-research | $2.00 | $12.00 | $4.50 |
openai/gpt-5.2popular | $1.75 | $14.00 | $4.81 |
openai/gpt-5.2-chat | $1.75 | $14.00 | $4.81 |
amazon/nova-premier | $2.50 | $12.50 | $5.00 |
openai/gpt-realtime-mini | $3.20 | $12.00 | $5.40 |
anthropic/claude-sonnet-4.6popular | $3.00 | $15.00 | $6.00 |
anthropic/claude-sonnet-4.5 | $3.00 | $15.00 | $6.00 |
anthropic/claude-3.7-sonnet | $3.00 | $15.00 | $6.00 |
x-ai/grok-4.2 | $3.00 | $15.00 | $6.00 |
x-ai/grok-4.1 | $3.00 | $15.00 | $6.00 |
perplexity/sonar-pro | $3.00 | $15.00 | $6.00 |
anthropic/claude-sonnet-4.0 | $3.00 | $15.00 | $6.00 |
x-ai/grok-4 | $3.00 | $15.00 | $6.00 |
anthropic/claude-fable-5 | $3.00 | $15.00 | $6.00 |
anthropic/claude-fable-5.1 | $3.00 | $15.00 | $6.00 |
x-ai/grok-4.6 | $3.00 | $15.00 | $6.00 |
amazon/nova-sonic | $3.50 | $14.00 | $6.13 |
openai/gpt-6-astrapopular | $4.00 | $20.00 | $8.00 |
anthropic/claude-mythos-5 | $4.00 | $20.00 | $8.00 |
anthropic/claude-mythos-5.1 | $4.00 | $20.00 | $8.00 |
anthropic/claude-opus-4.6popular | $5.00 | $25.00 | $10.00 |
anthropic/claude-opus-4.5 | $5.00 | $25.00 | $10.00 |
anthropic/claude-opus-5popular | $6.00 | $30.00 | $12.00 |
openai/gpt-image-1.5 | $5.00 | $40.00 | $13.75 |
openai/gpt-image-1 | $5.00 | $40.00 | $13.75 |
anthropic/claude-opus-4.1 | $15.00 | $75.00 | $30.00 |
google/veo-3-fast | $20.00 | $60.00 | $30.00 |
anthropic/claude-opus-4.0 | $15.00 | $75.00 | $30.00 |
openai/o3-pro | $20.00 | $80.00 | $35.00 |
openai/gpt-realtime | $32.00 | $64.00 | $40.00 |
openai/gpt-5.2-pro | $15.00 | $120.00 | $41.25 |
openai/gpt-5-pro | $15.00 | $120.00 | $41.25 |
openai/sora-2 | $40.00 | $120.00 | $60.00 |
google/veo-3.1 | $50.00 | $130.00 | $70.00 |
google/veo-3 | $50.00 | $130.00 | $70.00 |
Prices in USD per million tokens. Shown for the cheapest hosting provider; see the models page for per-provider detail. Sample data for demonstration.