← All plans and pricing

AI pricing

Every model call is metered in the tokens the provider reports: input, output, cached input and cache writes. Each model has its own price, so you can choose the model that fits the task and see exactly what it costs.

  • Agent conversations and tool use
  • Pipeline and plan authoring
  • Predictions and forecasting
  • Audio transcription

Allowances and rates

Monthly allowances apply before your plan's usage credit. Access is determined by your plan.

ResourceStarterProEnterprise
AI input tokens
$0 to $50.00 / 1M tokens
$0 to $50.00 / 1M tokens
Custom
AI output tokens
$0 to $300.00 / 1M tokens
$0 to $300.00 / 1M tokens
Custom
AI cached input tokens
$0 to $12.50 / 1M tokens
$0 to $12.50 / 1M tokens
Custom
AI cache write tokens
$0 to $31.25 / 1M tokens
$0 to $31.25 / 1M tokens
Custom
AI requests
No charge
No charge
Custom
Audio transcription
$0.01 / minute
$0.01 / minute
Custom

Detailed resource rates

The same on Starter and Pro. Prices are in US dollars, excluding tax.

ModelAI input tokensper 1M tokensAI output tokensper 1M tokensAI cached input tokensper 1M tokensAI cache write tokensper 1M tokens
alibaba/qwen-3-14b$0.20$0.40——
alibaba/qwen-3-235b$0.3667$1.47——
alibaba/qwen-3-30b$0.20$0.8333——
alibaba/qwen-3-32b$0.2667$1.07——
alibaba/qwen-3.6-max-preview$2.17$13.00$0.2167$2.71
alibaba/qwen3-235b-a22b-thinking$0.6667$6.67——
alibaba/qwen3-coder$2.50$12.50$0.50—
alibaba/qwen3-coder-30b-a3b$0.25$1.00——
alibaba/qwen3-coder-next$0.8333$2.00——
alibaba/qwen3-coder-plus$1.67$8.33$0.3333—
alibaba/qwen3-max$2.00$10.00$0.40—
alibaba/qwen3-max-preview$2.00$10.00$0.40—
alibaba/qwen3-max-thinking$2.00$10.00$0.40—
alibaba/qwen3-next-80b-a3b-instruct$0.25$2.00——
alibaba/qwen3-next-80b-a3b-thinking$0.25$2.00——
alibaba/qwen3-vl-235b-a22b-instruct$0.6667$2.67——
alibaba/qwen3-vl-instruct$0.6667$2.67——
alibaba/qwen3-vl-thinking$0.6667$6.67——
alibaba/qwen3.5-flash$0.1667$0.6667$0.01667$0.2083
alibaba/qwen3.5-plus$0.6667$4.00$0.06667$0.8333
alibaba/qwen3.6-27b$1.00$6.00——
alibaba/qwen3.6-plus$0.8333$5.00$0.08333$1.04
alibaba/qwen3.7-flash$0.05$0.2167$0.01$0.06333
alibaba/qwen3.7-max$4.17$12.50$0.8333$5.21
alibaba/qwen3.7-plus$0.6667$2.67$0.1333$0.8333
alibaba/qwen3.8-2.4t-a95b$3.33$10.00$0.4167—
alibaba/qwen3.8-27b$0.8333$5.00$0.1667$1.04
alibaba/qwen3.8-flash$0.25$0.7833$0.02667$0.3333
alibaba/qwen3.8-max$3.33$10.00$0.4167—
alibaba/qwen3.8-max-0902$3.33$10.00$0.4167$4.17
alibaba/qwen3.8-max-prime$6.67$20.00$0.8333$8.33
alibaba/qwen3.8-omni-flash$0.25$0.7833$0.02667—
amazon/nova-2-lite$0.50$4.17$0.125—
amazon/nova-lite$0.10$0.40——
amazon/nova-micro$0.05833$0.2333——
amazon/nova-pro$1.33$5.33——
anthropic/claude-3-haiku$0.4167$2.08$0.05$0.50
anthropic/claude-fable-5$16.67$83.33$1.67$20.83
anthropic/claude-fable-5.1$16.67$83.33$0.4167$20.83
anthropic/claude-haiku-4.5$1.67$8.33$0.1667$2.08
anthropic/claude-haiku-5.5$0.1667$0.8333$0.01667$0.2083
anthropic/claude-opus-4$25.00$125.00$2.50$31.25
anthropic/claude-opus-4.5$8.33$41.67$0.8333$10.42
anthropic/claude-opus-4.6$8.33$41.67$0.8333$10.42
anthropic/claude-opus-4.7$8.33$41.67$0.8333$10.42
anthropic/claude-opus-4.8$8.33$41.67$0.8333$10.42
anthropic/claude-opus-5$8.33$41.67$0.8333$10.42
anthropic/claude-opus-5.5$6.67$33.33$0.3333$8.33
anthropic/claude-sonnet-4$5.00$25.00$0.50$6.25
anthropic/claude-sonnet-4.5$5.00$25.00$0.50$6.25
anthropic/claude-sonnet-4.6$5.00$25.00$0.50$6.25
anthropic/claude-sonnet-5$3.33$16.67$0.3333$4.17
anthropic/claude-sonnet-5.5$3.33$16.67$0.1667$4.17
arcee-ai/trinity-large-thinking$0.4167$1.33——
bytedance/seed-1.6$0.4167$3.33$0.08333—
bytedance/seed-1.8$0.4167$3.33$0.08333—
bytedance/seed-2.1-turbo$0.8333$4.17$0.1667—
cohere/command-a$4.17$16.67——
deepseek/deepseek-r1$2.25$9.00——
deepseek/deepseek-v3.1$0.4167$1.58$0.2167—
deepseek/deepseek-v3.2$1.03$3.08——
deepseek/deepseek-v3.2-thinking$1.03$3.08——
deepseek/deepseek-v4-flash$0.3667$1.10$0.03667—
deepseek/deepseek-v4-flash-0731$0.3667$1.10$0.03667—
deepseek/deepseek-v4-flash-vision-exp$0.3593$1.08$0.01133—
deepseek/deepseek-v4-pro$1.10$3.30$0.03667—
deepseek/deepseek-v4-pro-0813$1.10$3.30$0.11—
deepseek/deepseek-v4.1-flash$0.50$2.00$0.01167—
deepseek/deepseek-v4.1-flash-fast$0.50$2.00$0.01—
fireworks/ember-1$5.00$25.00$0.50—
google/gemini-2.5-flash$0.50$4.17$0.05—
google/gemini-2.5-flash-image$0.50$4.17$0.05—
google/gemini-2.5-flash-lite$0.1667$0.6667$0.01667—
google/gemini-2.5-pro$2.08$16.67$0.2083—
google/gemini-3-flash$0.8333$5.00$0.08333—
google/gemini-3-pro-image$3.33$20.00$0.3333—
google/gemini-3.1-flash-image$0.8333$5.00$0.08333—
google/gemini-3.1-flash-image-preview$0.8333$5.00$0.08333—
google/gemini-3.1-flash-lite$0.4167$2.50$0.05—
google/gemini-3.1-flash-lite-image$0.4167$2.50$0.05—
google/gemini-3.1-pro-preview$3.33$20.00$0.3333—
google/gemini-3.5-flash$2.50$15.00$0.25—
google/gemini-3.5-flash-lite$0.50$4.17$0.05—
google/gemini-3.6-flash$1.25$6.25$0.125—
google/gemini-3.7-flash$1.25$6.25$0.125—
google/gemini-3.8-flash$1.25$6.25$0.125—
google/gemini-nano-banana-2.1$2.50$12.50$0.25—
google/gemini-omni-flash-preview$2.50$15.00——
google/gemma-4-26b-a4b-it$0.25$1.00$0.025—
google/gemma-4-31b-it$0.2333$0.6667——
inception/mercury-2$0.4167$1.25$0.04167—
inception/mercury-2.5$0.06667$0.25$0.006667—
inception/mercury-coder-small$0.4167$1.67——
inclusionai/ling-3.0-flash$0.035$0.105$0.007—
inclusionai/ling-3.0-flash-fin$0.125$0.3667$0.025—
inclusionai/ling-3.0-flash-sante$0.125$0.3667$0.025—
inclusionai/ling-3.0-flash-vl$0.125$0.3667$0.025—
inclusionai/ling-3.1-flashNo chargeNo charge——
inference-net/schematron-v2-small$0.08333$0.3833$0.08333—
inference-net/schematron-v2-turbo$0.05$0.25$0.05—
interfaze/interfaze-beta$2.50$5.83——
meituan/longcat-2.5-preview$0.50$2.00$0.01—
meta/llama-3.1-70b$1.20$1.20——
meta/llama-3.1-8b$0.3667$0.3667——
meta/llama-3.3-70b$1.20$1.20——
meta/llama-4-maverick$0.40$1.62——
meta/llama-4-scout$0.2833$1.10——
meta/muse-glimmer-30b$0.5833$2.50$0.06667—
meta/muse-spark-1.1$2.08$7.08$0.25—
meta/muse-spark-1.2$2.08$7.08$0.25—
meta/muse-spark-1.2-contributor$0.1667$0.3333$0.003333—
meta/muse-spark-1.3$2.08$7.08$0.25—
meta/muse-spark-1.3-contributor$0.1667$0.3333$0.003333—
minimax/minimax-m2$0.50$2.00$0.05$0.625
minimax/minimax-m2.1$0.50$2.00$0.05$0.625
minimax/minimax-m2.1-lightning$0.50$4.00$0.05$0.625
minimax/minimax-m2.5$0.50$2.00$0.05$0.625
minimax/minimax-m2.5-highspeed$1.00$4.00$0.05$0.625
minimax/minimax-m2.7$0.50$2.00$0.10$0.625
minimax/minimax-m2.7-highspeed$1.00$4.00$0.10$0.625
minimax/minimax-m3$0.50$2.00$0.10—
mistral/codestral$0.50$1.50$0.05—
mistral/ministral-14b$0.3333$0.3333$0.03333—
mistral/ministral-3b$0.1667$0.1667$0.01667—
mistral/ministral-8b$0.25$0.25$0.025—
mistral/mistral-large-3$0.8333$2.50$0.08333—
mistral/mistral-large-4$1.13$3.48$0.1167—
mistral/mistral-medium-3.5$2.50$12.50$0.25—
mistral/mistral-nemo$0.06667$0.2833——
mistral/mistral-small$0.25$1.00$0.025—
mixedbread/toast-1$0.50$1.20$0.06—
moonshotai/kimi-k2$0.95$3.83——
moonshotai/kimi-k2.5$1.00$5.00——
moonshotai/kimi-k2.6$1.58$6.67$0.2667—
moonshotai/kimi-k2.7-code$1.58$6.67$0.3167—
moonshotai/kimi-k2.7-code-highspeed$3.17$13.33$0.6333—
moonshotai/kimi-k3$5.00$25.00$0.50—
moonshotai/kimi-k3-fast$7.50$37.50$0.75—
morph/morph-v3-fast$1.33$2.00——
morph/morph-v3-large$1.50$3.17——
nvidia/nemotron-3-nano-30b-a3b$0.08333$0.3333$0.04167—
nvidia/nemotron-3-super-120b-a12b$0.25$1.08——
nvidia/nemotron-3-ultra-550b-a55b$1.00$4.00$0.20—
nvidia/nemotron-3.5-lightning$0.08333$0.3333$0.01667—
nvidia/nemotron-nano-12b-v2-vl$0.3333$1.00——
nvidia/nemotron-nano-9b-v2$0.10$0.3833——
openai/gpt-3.5-turbo$0.8333$2.50——
openai/gpt-4-turbo$16.67$50.00——
openai/gpt-4.1$3.33$13.33$0.8333No charge
openai/gpt-4.1-mini$0.6667$2.67$0.1667No charge
openai/gpt-4.1-nano$0.1667$0.6667$0.04167No charge
openai/gpt-4o$4.17$16.67$2.08No charge
openai/gpt-4o-mini$0.25$1.00$0.125No charge
openai/gpt-5$2.08$16.67$0.2083No charge
openai/gpt-5-codex$2.08$16.67$0.2167No charge
openai/gpt-5-mini$0.4167$3.33$0.04167No charge
openai/gpt-5-nano$0.08333$0.6667$0.008333No charge
openai/gpt-5-pro$25.00$200.00——
openai/gpt-5.1-codex$2.08$16.67$0.2167—
openai/gpt-5.1-codex-max$2.08$16.67$0.2083—
openai/gpt-5.1-codex-mini$0.4167$3.33$0.05—
openai/gpt-5.1-thinking$2.08$16.67$0.2083—
openai/gpt-5.2$2.92$23.33$0.2917—
openai/gpt-5.2-codex$2.92$23.33$0.2917—
openai/gpt-5.2-pro$35.00$280.00——
openai/gpt-5.3-codex$2.92$23.33$0.2917—
openai/gpt-5.4$4.17$25.00$0.4167—
openai/gpt-5.4-mini$1.25$7.50$0.125—
openai/gpt-5.4-nano$0.3333$2.08$0.03333—
openai/gpt-5.4-pro$50.00$300.00——
openai/gpt-5.5$8.33$50.00$0.8333—
openai/gpt-5.5-pro$50.00$300.00——
openai/gpt-5.6-luna$0.3333$2.00$0.03333$0.4167
openai/gpt-5.6-sol$6.67$33.33$0.6667$8.33
openai/gpt-5.6-terra$3.33$20.00$0.3333$4.17
openai/gpt-6-astra$16.67$83.33$1.67$20.83
openai/gpt-6-luna$0.1667$0.8333$0.01667$0.2083
openai/gpt-6-sol$3.33$16.67$0.3333$4.17
openai/gpt-6.1-sol$3.33$16.67$0.1667$4.17
openai/gpt-oss-120b$0.1667$0.8333$0.1667—
openai/gpt-oss-20b$0.05$0.2333——
openai/gpt-oss-safeguard-120b$0.25$1.00——
openai/gpt-oss-safeguard-20b$0.1167$0.3333——
openai/o1$25.00$100.00$12.50No charge
openai/o3$3.33$13.33$0.8333No charge
openai/o3-mini$1.83$7.33$0.9167No charge
openai/o3-pro$33.33$133.33——
openai/o4-mini$1.83$7.33$0.4583No charge
perplexity/sonar$0.4167$4.17—$0.1042
poolside/laguna-s-2.1$0.15$0.30$0.015—
poolside/laguna-s-2.1-freeNo chargeNo chargeNo charge—
quiverai/arrow-2$6.67$33.33$0.6667$8.33
quiverai/arrow-2-telos$10.00$50.00$1.00$12.50
sakana/fugu-max$3.33$10.00$0.4167—
sakana/fugu-ultra$8.33$50.00$0.8333—
sakana/fugu-ultra-v2$8.33$50.00$0.8333—
sakana/namazu$1.58$6.67$0.25—
spacexai/grok-4.1-fast-non-reasoning$0.3333$0.8333$0.08333—
spacexai/grok-4.1-fast-reasoning$0.3333$0.8333$0.08333—
spacexai/grok-4.20-multi-agent$2.08$4.17$0.3333—
spacexai/grok-4.20-multi-agent-beta$2.08$4.17$0.3333—
spacexai/grok-4.20-non-reasoning$2.08$4.17$0.3333—
spacexai/grok-4.20-non-reasoning-beta$2.08$4.17$0.3333—
spacexai/grok-4.20-reasoning$2.08$4.17$0.3333—
spacexai/grok-4.20-reasoning-beta$2.08$4.17$0.3333—
spacexai/grok-4.3$2.08$4.17$0.3333—
spacexai/grok-4.5$3.33$10.00$0.50—
spacexai/grok-4.6$3.33$10.00$0.8333—
spacexai/grok-4.7$3.33$10.00$0.8333—
spacexai/grok-build-0.1$1.67$3.33$0.3333—
stealth/glyph-clusterNo chargeNo chargeNo charge—
stepfun/step-3.7-flash$0.3333$1.92$0.06667—
stepfun/step-5-preview$1.67$4.50$0.08333—
tencent/hy-mt2-lite$0.07333$0.295——
tencent/hy-mt2-plus$0.1233$0.4917——
tencent/hy-mt2-pro$0.1233$0.4917——
tencent/hy3$0.2333$0.9667$0.05833—
tencent/hy4-preview$1.39$4.17$0.07—
thinkingmachines/inkling$1.67$6.75$0.2833—
thinkingmachines/inkling-small$0.75$2.00$0.1667—
xiaomi/mimo-v2.5$0.2333$0.4667$0.004667—
xiaomi/mimo-v2.5-pro$0.725$1.45$0.006—
xiaomi/mimo-v2.6-flash$0.06667$2.13$0.06667—
xiaomi/mimo-v2.6-pro$0.725$1.45$0.006—
xiaomi/mimo-v2.6-pro-ultraspeed$7.25$14.50$0.06—
zai/glm-4.5$1.00$3.67$0.1833—
zai/glm-4.5-air$0.3333$1.83$0.05—
zai/glm-4.5v$1.00$3.00$0.1833—
zai/glm-4.6$1.00$3.67$0.1833—
zai/glm-4.7$1.00$3.67——
zai/glm-4.7-flash$0.1167$0.6667——
zai/glm-4.7-flashx$0.10$0.6667$0.01667—
zai/glm-5$1.67$5.33——
zai/glm-5-turbo$2.00$6.67$0.40—
zai/glm-5.1$2.33$7.33$0.4333—
zai/glm-5.2$2.33$7.33$0.4667—
zai/glm-5.2-fast$4.67$14.67$0.9333—
zai/glm-5.3$2.33$7.33$0.2333—
zai/glm-5.3-fast$3.50$11.00$0.35—
zai/glm-5.3-flash$0.25$0.8333$0.05—
zai/glm-5.3-flashx$0.6167$2.08$0.125—
zai/glm-5v-turbo$2.00$6.67$0.40—

Enterprise prices are negotiated per agreement.

How it's measured

AI input tokensbilled per 1M tokens
Prompt tokens sent to the model, not served from cache, as the provider reports them.
AI output tokensbilled per 1M tokens
Tokens the model generates, including reasoning tokens.
AI cached input tokensbilled per 1M tokens
Prompt tokens served from the provider's cache, usually far cheaper than fresh input.
AI cache write tokensbilled per 1M tokens
Prompt tokens written to the provider's cache so later calls can reuse them.
AI requestsbilled per 1K requests
Charged per call only for models priced as a whole call rather than per token.
Audio transcriptionbilled per minute
Audio transcribed to text, measured by the length of the audio.

Worked cost examples

Before your plan's included usage, which is applied first each month.

An agent turn

20,000 input tokens of context, 15,000 of them from cache, and a 1,000-token answer. Priced with google/gemini-3.6-flash. At Pro prices.

ResourceQuantityUnit priceAmount
AI input tokens0.005 × 1M tokens$1.25$0.00625
AI cached input tokens0.015 × 1M tokens$0.125$0.001875
AI output tokens0.001 × 1M tokens$6.25$0.00625
Total$0.01438