Models and pricing
Live per-token prices for every model, including cache and long-context tiers.
ORYNX serves 34 models. The tables below come from the live catalog, so they show the prices you are charged. The Models page has the same data with filters and live status, latency and throughput.
How a request is priced
You pay for tokens at the model's published rate, in US dollars per 1M tokens:
- Input tokens you send, not counting cache reads and cache writes.
- Cache read tokens, when the provider serves part of your prompt from its cache. The price is in the Cache read column, often 10% of the input price.
- Cache write tokens, when part of your prompt is written to the provider's cache. Claude lets you choose a 5-minute or 1-hour lifetime. The tables show the 5-minute price, and model pages also list the 1-hour price where there is one.
- Output tokens the model generates, including reasoning tokens.
For example, a Claude Opus 5 call ($5.00 / $25.00) with 12,000 input tokens and 800 output tokens costs 12,000 × input price + 800 × output price, divided by one million.
Dynamic pricing
Some models cost more for long prompts (for example over 272K tokens) or during peak hours. The tiers are listed under each table, with peak hours in UTC and Myanmar time (UTC+06:30).
Claude
| Model | Input | Output | Cache read | Cache write 5m | Context |
|---|---|---|---|---|---|
| claude-opus-5 | $5.00 | $25.00 | $0.50 | $6.25 | 1M |
| claude-fable-5-1 | $10.00 | $50.00 | $0.25 | $12.50 | 1M |
| claude-fable-5 | $10.00 | $50.00 | $1.00 | $12.50 | 1M |
| claude-sonnet-5 | $2.00 | $10.00 | $0.20 | $2.50 | 1M |
| claude-opus-4-8 | $5.00 | $25.00 | $0.50 | $6.25 | 1M |
| claude-opus-4-7 | $5.00 | $25.00 | $0.50 | $6.25 | 1M |
| claude-opus-4-6 | $5.00 | $25.00 | $0.50 | $6.25 | 1M |
| claude-sonnet-4-6 | $3.00 | $15.00 | $0.30 | $3.75 | 1M |
| claude-sonnet-4-5 | $0.60 | $3.00 | $0.06 | $0.75 | 1M |
| claude-haiku-4-5 | $1.00 | $5.00 | $0.10 | $1.25 | 200K |
per 1M tokens · USD
GPT
| Model | Input | Output | Cache read | Cache write 5m | Context |
|---|---|---|---|---|---|
| gpt-6-astraDynamic pricing | $3.00 | $15.00 | $0.30 | $3.75 | 1.05M |
| gpt-5.6-solDynamic pricing | $1.20 | $6.00 | $0.12 | $1.50 | 1.05M |
| gpt-5.6-terraDynamic pricing | $0.60 | $3.60 | $0.06 | $0.75 | 1.05M |
| gpt-5.6-lunaDynamic pricing | $0.40 | $2.40 | $0.04 | $0.50 | 1.05M |
| gpt-5.5Dynamic pricing | $1.50 | $9.00 | $0.15 | — | 1.05M |
| codex-auto-review | $1.50 | $9.00 | $0.15 | — | 1.05M |
| gpt-5.5-codex-auto-review | $1.50 | $9.00 | $0.15 | — | 1.05M |
| gpt-5.5-openai-compact | $1.25 | $7.50 | $0.125 | — | 1.05M |
per 1M tokens · USD
gpt-6-astra · Dynamic pricing
- Prompts up to 272K tokensInput $3.00 · Output $15.00
- Prompts over 272K tokensInput $6.00 · Output $22.50
gpt-5.6-sol · Dynamic pricing
- Prompts up to 272K tokensInput $1.20 · Output $6.00
- Prompts over 272K tokensInput $2.40 · Output $9.00
gpt-5.6-terra · Dynamic pricing
- Prompts up to 272K tokensInput $0.60 · Output $3.60
- Prompts over 272K tokensInput $1.20 · Output $5.40
gpt-5.6-luna · Dynamic pricing
- Prompts up to 272K tokensInput $0.40 · Output $2.40
- Prompts over 272K tokensInput $0.80 · Output $3.60
gpt-5.5 · Dynamic pricing
- Prompts up to 272K tokensInput $1.50 · Output $9.00
- Prompts over 272K tokensInput $3.00 · Output $13.50
Gemini
| Model | Input | Output | Cache read | Cache write 5m | Context |
|---|---|---|---|---|---|
| gemini-3.8-flash | $0.225 | $1.125 | $0.0225 | — | 1M |
| gemini-3.7-flash | $0.225 | $1.125 | $0.0225 | — | 1M |
| gemini-3.6-flash | $0.225 | $1.125 | $0.0225 | — | 1M |
| gemini-3.6-flash-tiered | $0.45 | $2.25 | $0.045 | — | 1M |
| gemini-3-flash | $0.15 | $0.90 | $0.015 | — | 1M |
per 1M tokens · USD
Grok
| Model | Input | Output | Cache read | Cache write 5m | Context |
|---|---|---|---|---|---|
| grok-4.6Dynamic pricing | $0.50 | $1.50 | $0.125 | — | 500K |
| grok-4.5Dynamic pricing | $0.50 | $1.50 | $0.075 | — | 500K |
per 1M tokens · USD
grok-4.6 · Dynamic pricing
- Prompts up to 200K tokensInput $0.50 · Output $1.50
- Prompts over 200K tokensInput $1.00 · Output $3.00
grok-4.5 · Dynamic pricing
- Prompts up to 200K tokensInput $0.50 · Output $1.50
- Prompts over 200K tokensInput $1.00 · Output $3.00
DeepSeek
| Model | Input | Output | Cache read | Cache write 5m | Context |
|---|---|---|---|---|---|
| deepseek-v4.1-flash | $0.40 | $1.60 | $0.008 | — | 1M |
| deepseek-v4-pro-0813 | $0.105 | $0.24 | $0.003 | — | 1M |
| deepseek-v4-flash-0731 | $0.024 | $0.03 | $0.0009 | — | 1M |
| deepseek-v4-flash-vision-expDynamic pricing | $0.045 | $0.18 | $0.0009 | — | 1M |
per 1M tokens · USD
deepseek-v4-flash-vision-exp · Dynamic pricing
- Off-peak (all other times)Input $0.045 · Output $0.18
- Peak hoursMon–Fri 01:00–04:00 UTCMon–Fri 07:30–10:30 Myanmar timeMon–Fri 06:00–10:00 UTCMon–Fri 12:30–16:30 Myanmar timeInput $0.09 · Output $0.36
Kimi
| Model | Input | Output | Cache read | Cache write 5m | Context |
|---|---|---|---|---|---|
| kimi-k3 | $0.90 | $4.50 | $0.09 | — | 1M |
per 1M tokens · USD
GLM
| Model | Input | Output | Cache read | Cache write 5m | Context |
|---|---|---|---|---|---|
| glm-5.3 | $0.42 | $1.32 | $0.078 | $0 | 1M |
| glm-5.3-flash | $0.0225 | $0.075 | $0.0045 | $0 | 1M |
| glm-5.2 | $0.42 | $1.32 | $0.078 | $0 | 1M |
| glm-5.1 | $0.42 | $1.32 | $0.078 | $0 | 200K |
per 1M tokens · USD