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.

ModelInput / 1M tokensOutput / 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.