KI‑Modell‑Intelligenz

Anbieter · 2026-06-29

fireworks-ai

2 kanonische Modelle13 Einträge insgesamt (inkl. Derivate)
ModellEingabe / 1MAusgabe / 1MKontextHosterTags
GPT OSS 20B$0.070$0.300131K1tools · reasoning · open-weights
GPT OSS 120B$0.150$0.600131K1tools · reasoning · open-weights
MiniMax-M2.7Derivat$0.300$1.20197K1tools · reasoning · open-weights
Qwen 3.7 PlusDerivat$0.400$1.60262K1tools · reasoning · vision
Kimi K2.6Derivat$0.950$4.00262K1tools · reasoning · vision · open-weights
Kimi K2.7 CodeDerivat$0.950$4.00262K1tools · reasoning · vision · open-weights
GLM 5.1Derivat$1.40$4.40203K1tools · reasoning · open-weights
GLM 5.2Derivat$1.40$4.401.05M1tools · reasoning · open-weights
GLM 5.2 FastDerivat$2.10$6.601.05M1tools · reasoning · open-weights
Kimi K2.7 Code FastDerivat$1.90$8.00262K1tools · reasoning · vision · open-weights
Kimi K2.6 TurboDerivat$2.00$8.00262K1tools · reasoning · vision · open-weights
Kimi K2.6 FastDerivat$2.00$8.00262K1tools · reasoning · vision · open-weights
GLM 5.1 FastDerivat$2.80$8.80203K1tools · reasoning · open-weights

Frequently asked questions

How many AI models does fireworks-ai offer?

We track 2 canonical fireworks-ai models plus 11 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.

Which fireworks-ai model is the cheapest?

GPT OSS 20B is currently the lowest-priced fireworks-ai model, at $0.070 per 1M input tokens and $0.300 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which fireworks-ai model has the largest context window?

GPT OSS 20B leads at 131K tokens. This is the total of prompt + completion.

Which fireworks-ai models support tool calling?

Multiple fireworks-ai models support tool calling, with GPT OSS 20B being a popular pick. The capability column in the table above marks every model with fireworks-ai tool-calling support.

What are the best alternatives to fireworks-ai?

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

How fresh is this fireworks-ai pricing data?

Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

Zuletzt aktualisiert:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.