Claude API pricing
Every Claude model Inferray offers — 16 from Anthropic — at its list price, with no gateway fee on top. One API key calls all of them, alongside every other model in the catalog.
Claude models and prices
| Model | Input / 1M | Cached / 1M | Output / 1M | Context | Token Plans |
|---|---|---|---|---|---|
| Claude Haiku 5.5Anthropic's fastest model, priced for volume. | $0.1 | $0.01 | $0.5 | 1M | Included |
| Claude Sonnet 5.5Anthropic's best balance of speed and intelligence. | $2 | $0.1 | $10 | 1M | Included |
| Claude Opus 5.5Long-running agentic coding at a lower price than Opus 5. | $4 | $0.2 | $20 | 1M | Included |
| Claude Fable 5.1Anthropic's most intelligent model, for the hardest problems. | $10 | $0.25 | $50 | 1M | Pay-as-you-go |
| Claude Opus 5State-of-the-art agentic coding for enterprise work. | $5 | $0.5 | $25 | 1M | Included |
| Claude Sonnet 5Frontier reasoning at a price that scales to production. | $2 | $0.2 | $10 | 1M | Included |
| Claude Fable 5Next-generation intelligence for knowledge work and coding. | $10 | $1 | $50 | 1M | Pay-as-you-go |
| Claude Opus 4.8A proven pick for hard, long-running work. | $5 | $0.5 | $25 | 1M | Included |
| Claude Opus 4.7Anthropic's flagship for coding and agentic workflows. | $5 | $0.5 | $25 | 1M | Included |
| Claude Sonnet 4.6Reasoning and vision at a mid-tier price. | $3 | $0.3 | $15 | 1M | Included |
| Claude Opus 4.6Advanced reasoning for long-running agentic work. | $5 | $0.5 | $25 | 1M | Included |
| Claude Opus 4.5Claude Opus 4.5 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $5 | $0.5 | $25 | 200K | Pay-as-you-go |
| Claude Haiku 4.5Fast and efficient for high-volume, low-latency work. | $1 | $0.1 | $5 | 200K | Included |
| Claude Haiku 4.5 (2025-10-01)Claude Haiku 4.5 (2025-10-01) for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $1 | $0.1 | $5 | 200K | Pay-as-you-go |
| Claude Sonnet 4.5Claude Sonnet 4.5 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $3 | $0.3 | $15 | 200K | Pay-as-you-go |
| Claude Sonnet 4.5 (2025-09-29)Claude Sonnet 4.5 (2025-09-29) for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses. | $3 | $0.3 | $15 | 200K | Pay-as-you-go |
Which Claude model should I use?
- Claude Haiku 5.5 is the newest, released October 7, 2026.
- Claude Haiku 5.5 costs the least per request: $0.1 in / $0.5 out per 1M tokens.
Each model page has worked cost examples, code, and the full spec.
Call the Claude API
Point the OpenAI SDK (or the Anthropic SDK, or plain HTTP) at Inferray and name the model. This calls Claude Haiku 5.5; swap the id for any model above.
from openai import OpenAI
client = OpenAI(base_url="https://api.inferray.com/v1", api_key="inferray_...")
reply = client.chat.completions.create(
model="claude-haiku-5-5",
messages=[{"role": "user", "content": "ship it"}],
)Claude API questions
- How much does the Claude API cost?
- On Inferray, Claude models cost $0.1–$10 per 1M input tokens, the list price per model with no gateway fee on top. The table above has every model's input, cached input, and output price.
- Do I need a Anthropic account to use Claude?
- No. You call Claude with your Inferray API key and pay from one Inferray balance or Token Plan, the same as for every other model in the catalog.
- Are Claude models included in Token Plans?
- All of them except Claude Fable 5.1, Claude Fable 5, Claude Opus 4.5, Claude Haiku 4.5 (2025-10-01), Claude Sonnet 4.5, and Claude Sonnet 4.5 (2025-09-29), which are pay-as-you-go only. Plan credit is spent at list price, so the 20 Solo plan gives you 60 of usage a month.
- Does my credit expire?
- No. Pay-as-you-go credit never expires, and a top-up credits exactly what you pay. Token Plan credit resets each month with the plan.
Other model families
Prices from the catalog as of November 12, 2026.