Available Models
Browse the full catalogue of supported LLM models with live pricing per million tokens.
JBridge proxies to leading LLM providers. Pricing is shown per million input/output tokens and updates automatically.
| Model | Input / 1M tokens | Output / 1M tokens |
|---|---|---|
| claude-haiku-4-5 | $1.00 | $5.00 |
| claude-haiku-4-5-20251001 | $1.00 | $5.00 |
| claude-opus-4-6 | $5.00 | $25.00 |
| claude-opus-4-7 | $5.00 | $25.00 |
| claude-opus-4-8 | $5.00 | $25.00 |
| claude-sonnet-4-6 | $3.00 | $15.00 |
| deepseek-v3.2 | $0.58 | $1.68 |
| deepseek-v4-flash | $0.19 | $0.51 |
| deepseek-v4-pro | $1.74 | $3.48 |
| gpt-5.2 | $1.75 | $14.00 |
| gpt-5.2-chat | $1.75 | $14.00 |
| gpt-5.3-chat | $1.75 | $14.00 |
| gpt-5.3-codex | $1.75 | $14.00 |
| gpt-5.4 | $2.50 | $15.00 |
| gpt-5.4-mini | $0.75 | $4.50 |
| gpt-5.4-nano | $0.20 | $1.25 |
| gpt-5.5 | $5.00 | $30.00 |
| grok-4-1-fast-non-reasoning | $0.20 | $0.50 |
| grok-4-1-fast-reasoning | $0.20 | $0.50 |
| kimi-k2.5 | $0.60 | $3.00 |
| kimi-k2.6 | $0.95 | $4.00 |
Choosing a model
- General-purpose tasks (chat, coding assistance) — start with the latest GPT or Claude tier; they balance latency, quality, and cost.
- Long-context retrieval / RAG — Claude models offer extended context windows; verify the model card on the provider's site for the latest limits.
- Cost-sensitive workloads — DeepSeek and Kimi tiers are typically the cheapest; useful for high-volume background tasks.
Pricing notes
- All prices are USD per million tokens.
- Input and output tokens are billed separately at the rates above.
- JBridge bills you exactly what the upstream provider charges — no markup on tokens; revenue comes from a flat platform fee shown on your invoice.
- Sub-cent precision is preserved in the ledger; per-request charges may round only at display time.
Need a model that isn't listed?
Drop a request in support — we add models within days when there's demand.