Fireworks
Hybrid22 models hosted(6 own)ZDR
Avg Price
$3.71/M
Range
$0.420-$15.30
Reasoning
21
With AA Score
19
Hosting
10 self-hosted
Provider Quality
Avg TTFT
487ms
357-7334ms
Avg Throughput
42.3 tok/s
Uptime
100%
Probes (7d)
168
168 ok
Probe model:
accounts/fireworks/models/gpt-oss-120bLast probe: 2026-09-29 08:05 UTCTier Breakdown
Frontier
$10.20/M
1 models
$10.20 - $10.20
Standard
$5.08/M
5 models
$0.540 - $10.20
Budget
$2.03/M
12 models
$0.484 - $3.20
Micro
$5.39/M
4 models
$0.420 - $15.30
ZDR: ZDR by default for open models; opt-in logging for FireOptimizer. Response API exception store=True.
Hosted Models (click column to sort)
| Model | Owner | Tier | Host | Quant | Input $/M | Output $/M | Blended $/M▲ | Cost / IQ | SIT Score |
|---|---|---|---|---|---|---|---|---|---|
| OpenAI: gpt-oss-120bREASONING | OpenAI | Micro | Self | - | $0.150 | $0.600 | $0.420 | $1.45 | N/A |
| DeepSeek: DeepSeek V4 Flash 0731REASONING | DeepSeek | Budget | Self | - | $0.220 | $0.660 | $0.484 | $0.302 | N/A |
| DeepSeek: DeepSeek V4 Flash 0731REASONING | DeepSeek | Budget | - | unknown | $0.220 | $0.660 | $0.484 | $0.302 | N/A |
| DeepSeek: DeepSeek V4 Flash Vision ExpREASONING | DeepSeek | Budget | - | unknown | $0.220 | $0.660 | $0.484 | $1.11 | N/A |
| Z.ai: GLM 5.3 FlashREASONING | Z.ai | Standard | - | unknown | $0.225 | $0.750 | $0.540 | $0.344 | N/A |
| MiniMax: MiniMax M3REASONING | MiniMax | Budget | Self | - | $0.300 | $1.20 | $0.840 | $1.15 | N/A |
| Meta: Muse Glimmer 30BREASONING | Meta | Micro | - | unknown | $0.350 | $1.50 | $1.04 | $1.92 | N/A |
| DeepSeek: DeepSeek V4.1 FlashREASONING | DeepSeek | Standard | - | unknown | $0.450 | $1.80 | $1.26 | $0.798 | N/A |
| NVIDIA: Nemotron 3 UltraREASONING | NVIDIA | Budget | Self | - | $0.600 | $2.40 | $1.68 | $2.93 | N/A |
| MoonshotAI: Kimi K2.6REASONING | Moonshot AI | Budget | Self | - | $0.950 | $4.00 | $2.78 | $3.56 | N/A |
| MoonshotAI: Kimi K2.6REASONING | Moonshot AI | Budget | - | unknown | $0.950 | $4.00 | $2.78 | $3.56 | N/A |
| MoonshotAI: Kimi K2.7 CodeREASONING | Moonshot AI | Budget | Self | - | $0.950 | $4.00 | $2.78 | $4.31 | N/A |
| MoonshotAI: Kimi K2.7 CodeREASONING | Moonshot AI | Budget | - | unknown | $0.950 | $4.00 | $2.78 | $4.31 | N/A |
| DeepSeek: DeepSeek V4 Pro 0813REASONING | DeepSeek | Budget | - | unknown | $1.32 | $3.96 | $2.90 | $3.23 | N/A |
| Z.ai: GLM 5.2REASONING | Z.ai | Budget | Self | - | $1.40 | $4.40 | $3.20 | $3.69 | N/A |
| Z.ai: GLM 5.2REASONING | Z.ai | Budget | - | unknown | $1.40 | $4.40 | $3.20 | $3.69 | N/A |
| Z.ai: GLM 5.3REASONING | Z.ai | Standard | - | unknown | $1.40 | $4.40 | $3.20 | $2.50 | N/A |
| GLM 5.2 Fast | Z Ai | Micro | Self | - | $2.10 | $6.60 | $4.80 | N/A | N/A |
| Fireworks: Ember-1REASONING | Fireworks | Frontier | - | unknown | $3.00 | $15.00 | $10.20 | N/A | N/A |
| MoonshotAI: Kimi K3REASONING | Moonshot AI | Standard | Self | - | $3.00 | $15.00 | $10.20 | $9.36 | N/A |
| MoonshotAI: Kimi K3REASONING | Moonshot AI | Standard | - | unknown | $3.00 | $15.00 | $10.20 | $9.36 | N/A |
| Kimi K3 FastREASONING | Moonshotai | Micro | Self | - | $4.50 | $22.50 | $15.30 | N/A | N/A |