Models and pricing
Console pricing is authoritative
Prices below apply the current production group multipliers and are provided for estimation. Check the Sakrylle Console for model availability, balance, and actual charges.
Group overview
One API key binds to exactly one group. Create separate keys in the Console when you need models from different groups.
| Group | Multiplier | Billing | Notes |
|---|---|---|---|
| Claude-AWSQ | 0.4 | token | 6 Claude models, 1M context |
| Claude-Kiro | 0.5 | token | Same 6 Claude models, 1M context |
| Claude-Max | 1.3 | token | 7 Claude models, Claude Code only |
| Claude-Max-C | 1.5 | token | Same as Claude-Max, external API supported |
| GPT-Pro | 0.5 | token | GPT 5.6, 5.5, and 5.4 families |
| GPT-Pro-Special | 0.4 | token | Same as GPT-Pro, separate key channel |
| GPT-Image | 1.0 | per request | gpt-image-2, ￥0.15/call |
| Deepseek-Anthropic | 1.0 | token | Deepseek V4, Anthropic-native protocol |
| Deepseek-OpenAI | 1.0 | token | Deepseek V4, OpenAI-compatible protocol |
| Grok-API | 0.1 | token | 5 Grok models |
Billing rules
Token-billed groups apply the group multiplier to each model's backend base price:
actual = input token cost + output token cost + cache cost
each cost = tokens / 1,000,000 × backend base price × group multiplierThe token tables below already apply each group multiplier and use ￥ / MTok. The image group bills only successful requests; failed requests are not charged.
Claude pricing
Claude-AWSQ and Claude-Kiro offer the six shared models below. Claude-Max and Claude-Max-C additionally offer claude-fable-5. All four groups support a 1M context window.
Claude-AWSQ
| Model | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
claude-opus-4-8 / 4-7 / 4-6 | ￥2 | ￥10 | ￥0.2 | ￥2.5 |
claude-sonnet-5 | ￥0.8 | ￥4 | ￥0.08 | ￥1 |
claude-sonnet-4-6 | ￥1.2 | ￥6 | ￥0.12 | ￥1.5 |
claude-haiku-4-5-20251001 | ￥0.4 | ￥2 | ￥0.04 | ￥0.5 |
Claude-Kiro
| Model | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
claude-opus-4-8 / 4-7 / 4-6 | ￥2.5 | ￥12.5 | ￥0.25 | ￥3.125 |
claude-sonnet-5 | ￥1 | ￥5 | ￥0.1 | ￥1.25 |
claude-sonnet-4-6 | ￥1.5 | ￥7.5 | ￥0.15 | ￥1.875 |
claude-haiku-4-5-20251001 | ￥0.5 | ￥2.5 | ￥0.05 | ￥0.625 |
Claude-Max
Claude-Max is restricted to Claude Code.
| Model | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
claude-opus-4-8 / 4-7 / 4-6 | ￥6.5 | ￥32.5 | ￥0.65 | ￥8.125 |
claude-sonnet-5 | ￥2.6 | ￥13 | ￥0.26 | ￥3.25 |
claude-sonnet-4-6 | ￥3.9 | ￥19.5 | ￥0.39 | ￥4.875 |
claude-haiku-4-5-20251001 | ￥1.3 | ￥6.5 | ￥0.13 | ￥1.625 |
claude-fable-5 | ￥13 | ￥65 | ￥1.3 | ￥16.25 |
Claude-Max-C
Claude-Max-C supports external API clients.
| Model | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
claude-opus-4-8 / 4-7 / 4-6 | ￥7.5 | ￥37.5 | ￥0.75 | ￥9.375 |
claude-sonnet-5 | ￥3 | ￥15 | ￥0.3 | ￥3.75 |
claude-sonnet-4-6 | ￥4.5 | ￥22.5 | ￥0.45 | ￥5.625 |
claude-haiku-4-5-20251001 | ￥1.5 | ￥7.5 | ￥0.15 | ￥1.875 |
claude-fable-5 | ￥15 | ￥75 | ￥1.5 | ￥18.75 |
GPT pricing
GPT-Pro
| Model | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
gpt-5.6-sol, codex-auto-review | ￥2.5 | ￥15 | ￥0.25 | ￥3.125 |
gpt-5.6-terra | ￥1 | ￥6 | ￥0.1 | ￥1.25 |
gpt-5.5 | ￥2.5 | ￥15 | ￥0.25 | Not billed |
gpt-5.4 | ￥1.25 | ￥7.5 | ￥0.125 | Not billed |
GPT-Pro-Special
| Model | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
gpt-5.6-sol, codex-auto-review | ￥2 | ￥12 | ￥0.2 | ￥2.5 |
gpt-5.6-terra | ￥0.8 | ￥4.8 | ￥0.08 | ￥1 |
gpt-5.5 | ￥2 | ￥12 | ￥0.2 | Not billed |
gpt-5.4 | ￥1 | ￥6 | ￥0.1 | Not billed |
GPT 5.6 models bill cache-write tokens at 125% of the corresponding input price. GPT 5.5 and 5.4 models currently do not bill cache writes. Cache reads cost 10% of the corresponding input price for all GPT models.
Compact mappings
Compact names use the same price as their mapped standard model:
| Compact model | Maps to |
|---|---|
gpt-5.6-sol-openai-compact | gpt-5.6-sol |
gpt-5.6-terra-openai-compact | gpt-5.6-terra |
gpt-5.5-openai-compact | gpt-5.5 |
gpt-5.4-openai-compact | gpt-5.4 |
codex-auto-review rewrites to gpt-5.6-sol and uses the gpt-5.6-sol price.
Image pricing
| Group | Model | Price |
|---|---|---|
| GPT-Image | gpt-image-2 | ￥0.15 / call |
Image generation and editing are billed per successful call. See the Images API for request formats.
Deepseek pricing
The two Deepseek groups have the same models and prices; only the protocol differs.
| Model | Input | Output | Cache read |
|---|---|---|---|
deepseek-v4-flash | ￥1 | ￥2 | ￥0.02 |
deepseek-v4-pro | ￥3 | ￥6 | ￥0.025 |
Choose Deepseek-Anthropic for the Anthropic-native /v1/messages endpoint, or Deepseek-OpenAI for OpenAI-compatible endpoints.
Grok pricing
| Model | Input | Output | Cache read |
|---|---|---|---|
grok-4.20-0309 | ￥0.125 | ￥0.25 | ￥0.02 |
grok-4.20-0309-non-reasoning | ￥0.125 | ￥0.25 | ￥0.02 |
grok-4.20-multi-agent-0309 | ￥0.125 | ￥0.25 | ￥0.02 |
grok-4.3 | ￥0.125 | ￥0.25 | ￥0.02 |
grok-build-0.1 | ￥0.1 | ￥0.2 | ￥0.01 |
Streaming is strongly recommended for Grok. Clients should retry 429 and 503 responses with exponential backoff.
Volume discounts
For volume use or other billing questions, contact support@sakrylle.com.