Simple, transparent pricing
Pay only for what you use. Per-million-token pricing across every model. No monthly plans, no hidden fees, no surprises.
Pay per million tokens
Access every model with one API key. Prices are per 1 million tokens. Cached input is billed at 10% of the input rate (cache hits); cache writes at 1.25x.
Chat & Reasoning
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Chat Pico | $0.15 | $0.015 | $0.19 | $0.55 |
| Chat Mini | $0.15 | $0.015 | $0.19 | $0.55 |
| Chat v6 | $0.15 | $0.015 | $0.19 | $0.55 |
| Chat Mini 2 | $0.15 | $0.015 | $0.19 | $0.55 |
| Chat Nano | $0.15 | $0.015 | $0.19 | $0.55 |
| Chat v15 (Compact) | $0.15 | $0.015 | $0.19 | $0.55 |
| Chat Mini 3 (Lightweight) | $0.15 | $0.015 | $0.19 | $0.55 |
| Chat v17 (Lite) | $0.15 | $0.015 | $0.19 | $0.55 |
| Chat v12 (Balanced) | $0.40 | $0.040 | $0.50 | $3.25 |
| Chat v14 (Efficient) | $0.40 | $0.040 | $0.50 | $3.25 |
| Chat IN (Indic) | $0.40 | $0.040 | $0.50 | $3.25 |
| Chat JA (Japanese) | $0.40 | $0.040 | $0.50 | $3.25 |
| Chat v10 (Multilingual) | $0.60 | $0.060 | $0.75 | $3.25 |
| Chat v11 (Long Context) | $0.60 | $0.060 | $0.75 | $3.25 |
| Chat v19 (Sparse MoE) | $0.80 | $0.080 | $1.00 | $3.25 |
| Chat Medium | $0.85 | $0.085 | $1.06 | $3.25 |
| Chat v13 (Flagship) | $1.75 | $0.17 | $2.19 | $13.00 |
| Chat v7 (Ultra) | $1.75 | $0.17 | $2.19 | $13.00 |
| Chat v5 | $2.00 | $0.20 | $2.50 | $6.00 |
| Chat Turbo | $2.00 | $0.20 | $2.50 | $6.00 |
| Chat v1 | $2.00 | $0.20 | $2.50 | $6.00 |
| Chat v2 | $2.00 | $0.20 | $2.50 | $6.00 |
| Chat v16 (Flash) | $2.00 | $0.20 | $2.50 | $6.00 |
| Chat v4 | $2.00 | $0.20 | $2.50 | $6.00 |
| MoE | $2.00 | $0.20 | $2.50 | $6.00 |
| Chat v18 (Pro) | $2.00 | $0.20 | $2.50 | $13.00 |
| Chat v8 (Flash) | $4.00 | $0.40 | $5.00 | $6.00 |
| Chat v9 (Pro) | $4.00 | $0.40 | $5.00 | $13.00 |
| Chat v3 | $4.00 | $0.40 | $5.00 | $6.00 |
Classification
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Detect Speaker | $0.20 | — | — | $0.00 |
| Detect AV | $0.20 | — | — | $0.00 |
Code
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Code v2 | $0.95 | $0.095 | $1.19 | $3.25 |
| Code Fast | $0.95 | $0.095 | $1.19 | $3.25 |
| Code v4 | $0.95 | $0.095 | $1.19 | $3.25 |
| Code v1 | $1.00 | $0.10 | $1.25 | $5.00 |
| Coder | $1.00 | $0.10 | $1.25 | $5.00 |
| Code v3 | $1.00 | $0.10 | $1.25 | $5.00 |
Embedding
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Embeddings v2 | $0.15 | — | — | $0.00 |
| Embeddings v1 | $0.20 | — | — | $0.00 |
| Embeddings v4 | $0.30 | — | — | $0.00 |
| Code Embeddings | $0.30 | — | — | $0.00 |
Image Generation
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Image Gen | $0.00 | — | — | $0.00 |
Safety
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Guard v4 (Content Safety) | $0.20 | — | — | $0.00 |
| Guard Topic | $0.30 | — | — | $0.00 |
| Moderation v1 | $0.30 | — | — | $0.00 |
| Moderation v2 | $0.30 | — | — | $0.00 |
| Guard v1 | $0.30 | — | — | $0.00 |
| Guard PII | $0.30 | — | — | $0.00 |
| Guard Content | $0.30 | — | — | $0.00 |
Reasoning
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Reason Nano | $0.15 | $0.015 | $0.19 | $0.55 |
| Reason v7 (Fast) | $0.40 | $0.040 | $0.50 | $3.25 |
| Reason v5 (Multimodal) | $0.40 | $0.040 | $0.50 | $3.25 |
| Reason Fast | $0.95 | $0.095 | $1.19 | $3.25 |
| Reason v3 | $0.95 | $0.095 | $1.19 | $3.25 |
| Reason v6 (Deep) | $1.75 | $0.17 | $2.19 | $13.00 |
| Reason v2 | $2.00 | $0.20 | $2.50 | $6.00 |
| Reason v1 | $2.00 | $0.20 | $2.50 | $6.00 |
Reranking
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Rerank v1 | $0.30 | — | — | $0.00 |
| Rerank v2 | $0.30 | — | — | $0.00 |
Science
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Science v2 (Protein Folding) | $0.20 | — | — | $0.00 |
| Science v1 | $0.20 | — | — | $0.00 |
Speech & Audio
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Speech-to-Text v1 | $0.10 | — | — | $0.00 |
Translation
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Translate v1 | $2.00 | $0.20 | $2.50 | $6.00 |
Speech & Audio
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| TTS v1 | $0.40 | — | — | $0.00 |
| TTS v2 | $0.40 | — | — | $0.00 |
Video
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Video v2 | $1.00 | $0.10 | $1.25 | $3.00 |
| Video v1 | $1.00 | $0.10 | $1.25 | $3.00 |
Vision
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Vision v5 (Efficient) | $0.40 | $0.040 | $0.50 | $3.25 |
| Vision v6 (Compact) | $0.40 | $0.040 | $0.50 | $3.25 |
| Vision v1 | $0.90 | $0.090 | $1.13 | $3.25 |
| Vision v4 | $0.90 | $0.090 | $1.13 | $3.25 |
| Vision v2 | $0.90 | $0.090 | $1.13 | $3.25 |
| Vision v3 | $0.90 | $0.090 | $1.13 | $3.25 |
Voice
| Model | Input / 1M | Cached input / 1M | Cache write / 1M | Output / 1M |
|---|---|---|---|---|
| Voice Chat | $0.30 | — | — | $0.00 |
| Voice Enhance | $0.30 | — | — | $0.00 |
Frequently asked questions
Have more questions? Contact us
What counts as a token?
Tokens are pieces of words. On average, 1 token is about 4 characters or 0.75 words. Input and output tokens are priced separately, per million tokens.
How does billing work?
There are no monthly plans. You pay only for what you use — per million input tokens and per million output tokens, at the per-model rates above. Costs are deducted from your wallet balance as you make API calls.
How are cached tokens priced?
Prompt-cache tokens are billed separately from regular input. Cache reads (cache hits, where the model reuses a previously seen prompt prefix) are charged at 10% of the input rate — a 90% discount. Cache writes (creating a cache entry) are charged at 1.25x the input rate. The cached_tokens / cache_write_tokens counts are reported back in each response's usage.prompt_tokens_details so you can see exactly what was cached.
Where do I add funds?
Your wallet is shared across all Assisters products. Top up from your dashboard wallet, and the balance is usable on both assisters.io and assisters.dev.
Are there any minimums or commitments?
No. There are no monthly fees, no token caps, and no commitments — you're only charged for the tokens you actually use.
What payment methods do you accept?
We accept all major credit cards (Visa, Mastercard, American Express) and can arrange invoicing for Enterprise customers.
Ready to get started?
Pay only for the tokens you use — no monthly plans, no commitments.
Looking for consumer AI assistant pricing? View assisters.io plans