Fireworks AI
21 modelsProvider docs
As of Oct 4, 2026, Fireworks AI lists 21 supported models in the Sovyron catalog, including Ember-1, DeepSeek Flash Latest, DeepSeek V4.1 Flash, GLM 5.3 Fast and GLM Flash Latest (GLM 5.3 Flash) — deepseek-flash, glm, glm-flash, qwen, nemotron and kimi-k3 families. Its metered rates span $0.0875–$9 per 1M tokens on a 3:1 input:output blend, and every price in the table is Fireworks AI's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
21 of 21 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| Ember-1 | $3 | $15 | $0.3 | 1.0M | Sep 22, 2026 |
| DeepSeek Flash Latest | $0.3 | $1.2 | $0.006 | 1.0M | Sep 10, 2026 |
| DeepSeek V4.1 Flash | $0.3 | $1.2 | $0.006 | 1.0M | Sep 10, 2026 |
| GLM 5.3 Fast | $2.1 | $6.6 | $0.39 | 1.0M | Aug 28, 2026 |
| GLM Flash Latest (GLM 5.3 Flash) | $0.15 | $0.5 | $0.03 | 1.0M | Aug 26, 2026 |
| GLM-5.3-Flash | $0.15 | $0.5 | $0.03 | 1.0M | Aug 26, 2026 |
| GLM Latest | $1.4 | $4.4 | $0.26 | 1.0M | Aug 14, 2026 |
| GLM-5.3 | $1.4 | $4.4 | $0.26 | 1.0M | Aug 14, 2026 |
| Qwen3.8 2.4T A95B | $2 | $6 | $0.25 | 262k | Aug 12, 2026 |
| Nemotron 3.5 Lightning 30B A3B | $0.05 | $0.2 | $0.01 | 262k | Aug 11, 2026 |
| Qwen Max Latest (Qwen3.8 Max) | $2 | $6 | $0.25 | 262k | Aug 3, 2026 |
| Qwen3.8 Max | $2 | $6 | $0.25 | 262k | Aug 3, 2026 |
| Kimi Fast Latest | $4.5 | $22.5 | $0.45 | 1.0M | Jul 27, 2026 |
| Kimi K3 | $3 | $15 | $0.3 | 1.0M | Jul 27, 2026 |
| Kimi K3 Fast | $4.5 | $22.5 | $0.45 | 1.0M | Jul 27, 2026 |
| Kimi Latest | $3 | $15 | $0.3 | 1.0M | Jul 27, 2026 |
| Inkling | $1 | $4.05 | $0.17 | 1.0M | Jul 15, 2026 |
| MiniMax Latest | $0.3 | $1.2 | $0.06 | 512k | Jun 12, 2026 |
| MiniMax-M3 | $0.3 | $1.2 | $0.06 | 512k | Jun 12, 2026 |
| Nemotron 3 Ultra 550B A55B | $0.6 | $2.4 | $0.12 | 262k | Jun 4, 2026 |
| GPT OSS 120B | $0.15 | $0.6 | $0.015 | 131k | Aug 5, 2025 |