Updated 1 h ago · first seen 11 Sept 2026
provider_01M293SPBQ2F29E7H96DNK8Y77
Specification
- Batch discount
- 50% of serverless pricing
Source:Fireworks AI — pricingT1observed 1 h agohigh
- Pricing page
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 1 h agomedium
- Website
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 1 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
3
Source tiers
T1T21 / 2
Freshest observation
1 h ago
Conflicts
None
Current prices
| Model | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| NVIDIA Nemotron 3.5 Lightning 30B A3Bfireworks/nemotron-lightning-3p5-30b-a3bNVIDIA | $0.05 | $0.20 | $0.01 | — | — | 1 h ago | app.fireworks.aiT1 |
| GLM 5.3 Flashfireworks/glm-5p3-flashZ.ai (Zhipu AI) | $0.15 | $0.50 | $0.03 | — | — | 1 h ago | app.fireworks.aiT1 |
| gpt-oss-120bfireworks/gpt-oss-120bOpenAI | $0.15 | $0.60 | $0.015 | — | — | 1 h ago | app.fireworks.aiT1 |
| DeepSeek V4 Flash (0731)fireworks/deepseek-v4-flash-0731DeepSeek | $0.22 | $0.66 | $0.007 | — | — | 1 h ago | app.fireworks.aiT1 |
| DeepSeek V4 Flash Vision Expfireworks/deepseek-v4-flash-vision-expDeepSeek | $0.22 | $0.66 | $0.007 | — | — | 1 h ago | app.fireworks.aiT1 |
| DeepSeek-V4.1-Flashfireworks/deepseek-v4p1-flashDeepSeek | $0.22 | $0.66 | $0.007 | — | — | 1 h ago | app.fireworks.aiT1 |
| MiniMax M3fireworks/minimax-m3MiniMax | $0.30 | $1.2 | $0.06 | — | — | 1 h ago | app.fireworks.aiT1 |
| Muse Glimmer 30Bfireworks/muse-glimmer-30bMeta AI | $0.35 | $1.5 | $0.04 | — | — | 1 h ago | app.fireworks.aiT1 |
| Qwen 3.7 Plusfireworks/qwen3p7-plusQwen | $0.40 | $1.6 | $0.08 | — | — | 1 h ago | app.fireworks.aiT1 |
| NVIDIA Nemotron 3 Ultra (Preview)fireworks/nemotron-3-ultra-nvfp4NVIDIA | $0.60 | $2.4 | $0.12 | — | — | 1 h ago | app.fireworks.aiT1 |
| Kimi K2.6fireworks/kimi-k2p6Moonshot AI | $0.95 | $4 | $0.16 | — | — | 1 h ago | app.fireworks.aiT1 |
| Kimi K2.7 Codefireworks/kimi-k2p7-codeMoonshot AI | $0.95 | $4 | $0.19 | — | — | 1 h ago | app.fireworks.aiT1 |
| DeepSeek-V4-Pro-0813fireworks/deepseek-v4-pro-0813DeepSeek | $1.32 | $3.96 | $0.044 | — | — | 1 h ago | app.fireworks.aiT1 |
| GLM 5.2fireworks/glm-5p2 | $1.4 | $4.4 | $0.14 | — | — | 1 h ago | app.fireworks.aiT1 |
| GLM 5.3fireworks/glm-5p3Z.ai (Zhipu AI) | $1.4 | $4.4 | $0.26 | — | — | 1 h ago | app.fireworks.aiT1 |
| Qwen 3.8 Maxfireworks/qwen3p8-maxQwen | $2 | $6 | $0.25 | — | — | 1 h ago | app.fireworks.aiT1 |
| GLM 5.2fireworks/glm-5p2:fast-us | $2.1 | $6.6 | $0.21 | — | — | 1 h ago | app.fireworks.aiT1 |
| GLM 5.2fireworks/glm-5p2:fast | $2.1 | $6.6 | $0.21 | — | — | 1 h ago | app.fireworks.aiT1 |
| Kimi K3fireworks/kimi-k3Moonshot AI | $3 | $15 | $0.30 | — | — | 1 h ago | app.fireworks.aiT1 |
| Kimi K3fireworks/kimi-k3:usMoonshot AI | $3.3 | $16.5 | $0.33 | — | — | 1 h ago | app.fireworks.aiT1 |
| Kimi K3fireworks/kimi-k3:fastMoonshot AI | $4.5 | $22.5 | $0.45 | — | — | 1 h ago | app.fireworks.aiT1 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- DeepSeek V4 Flash (0731)
- DeepSeek V4 Flash Vision Exp
- DeepSeek-V4-Pro-0813
- DeepSeek-V4.1-Flash
- GLM 5.2
- GLM 5.3
- GLM 5.3 Flash
- gpt-oss-120b
- Serves
- NVIDIA Nemotron 3 Ultra (Preview), Kimi K3, Kimi K2.7 Code, Kimi K2.6, DeepSeek-V4.1-Flash, DeepSeek-V4-Pro-0813, DeepSeek V4 Flash (0731), DeepSeek V4 Flash Vision Exp +9(17 total)
- Operated by
- Fireworks AI
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Website
Websitewebsite1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://fireworks.ai | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Fireworks AI — pricing | docs.fireworks.ai/serverless/pricing.md | pricing | T1· Official | 1 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.