Skip to Content
Pricing

Pricing

Pay per token from prepaid credits. No subscriptions, no seat fees. The table below is rendered from the same catalog the API serves at GET /models — what you see here is what you are billed.

Model pricing

All rates in USD per million tokens. Cached prompt tokens are billed at the discounted cached rate where the model supports prompt caching.

ModelPrompt / MtokCompletion / MtokCached prompt / MtokContextMax outputFeaturesDatacenters
DeepSeek V4 Flash
deepseek/deepseek-v4-flash
$0.15$0.3$0.081.049M32.768Ktools, json_mode, reasoning, streaming, prompt_cachingeu-west, us-east, uae
DeepSeek V4 Pro
deepseek/deepseek-v4-pro
$1.83$3.66$0.351.049M32.768Ktools, json_mode, reasoning, streaming, prompt_cachingeu-west, us-east, uae
DeepSeek V3.2
deepseek/deepseek-v3.2
$0.59$1.77$0.27163.84K65.536Ktools, json_mode, reasoning, streaming, prompt_cachingeu-west, us-east, uae
Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b
$0.79$4.73$0.58262.144K65.536Ktools, vision, json_mode, reasoning, streaming, prompt_cachingeu-west, us-east, uae
Qwen3 Coder 480B A35B
qwen/qwen3-coder
$1.05$5.12$1.051.049M65.536Ktools, json_mode, streaming, prompt_cachingeu-west, us-east, uae
GLM 5.2
z-ai/glm-5.2
$1.47$4.62$0.281.049M131.072Ktools, json_mode, reasoning, streaming, prompt_cachingeu-west, us-east, uae
GLM 5.1
z-ai/glm-5.1
$1.62$5.09$0.31202.752K131.072Ktools, json_mode, reasoning, streaming, prompt_cachingeu-west, us-east, uae
Gemma 4 31B
google/gemma-4-31b-it
$0.41$1.02262.144K16.384Ktools, vision, json_mode, reasoning, streamingeu-west, us-east, uae
Gemma 4 26B A4B
google/gemma-4-26b-a4b-it
$0.16$0.63262.144K16.384Ktools, vision, json_mode, reasoning, streamingeu-west, us-east, uae
Llama 4 Maverick
meta-llama/llama-4-maverick
$0.37$1.21$0.181.049M16.384Ktools, vision, json_mode, streamingeu-west, us-east, uae
Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instruct
$1.1$1.1$0.31131.072K16.384Ktools, json_mode, streamingeu-west, us-east, uae
Llama 4 Scout
meta-llama/llama-4-scout
$0.27$0.74$0.061.311M16.384Ktools, vision, json_mode, streamingeu-west, us-east, uae
Mistral Small 3.2 24B
mistralai/mistral-small-3.2-24b-instruct
$0.11$0.32$0.06131.072K32.768Ktools, vision, json_mode, streaming, prompt_cachingeu-west, us-east, uae
Mistral Large 3
mistralai/mistral-large-2512
$0.53$1.58$0.06262.144K32.768Ktools, vision, json_mode, streaming, prompt_cachingeu-west, us-east, uae
Kimi K2.6
moonshotai/kimi-k2.6
$1.26$4.83$0.39262.144K32.768Ktools, vision, json_mode, reasoning, streaming, prompt_cachingeu-west, us-east, uae
Kimi K2.7 Code
moonshotai/kimi-k2.7-code
$2$8.4$0.4262.144K32.768Ktools, vision, json_mode, reasoning, streaming, prompt_cachingeu-west, us-east, uae

Credits & top-up fees

Credits are workspace-scoped, denominated in USD, and never expire. Top-ups carry a service fee, shown transparently before you confirm:

Payment methodService feeExample: $1,000 in creditsMinimum top-up
Card5.5%$55.00 fee → $1055.00 charged$5.00
Crypto (USDC)5%$50.00 fee → $1050.00 charged$5.00

Buying $1,000 in credits by card charges $1,055.00; by crypto (USDC) $1,050.00 — you receive the full $1,000 in credits either way. Depending on your billing country and status, tax (e.g. UAE VAT, EU consumer VAT) may apply on top and is itemized at checkout.

Server tools

Server-tool executions (web search, web fetch, PDF parsing) are billed per use against workspace credits as separate, itemized ledger lines tied to the request that triggered them. Per-tool rates are published here before general availability of each tool.

Credits calculator

Estimate in both directions — tokens to dollars, and what a budget buys:

Estimated cost: $0.021 in credits


$10 buys ≈ 66.67M prompt tokens or ≈ 33.33M completion tokens on DeepSeek V4 Flash.

Estimates use uncached prompt rates from the catalog above. Actual billing is exact per-token math on the measured usage of each request — see Usage & Credits.