Z.ai: GLM 5.3 Flash (batch)
z-ai/glm-5-3-flash-batchGLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.
Modalities
In / out per 1M$0.05 / $0.18
Context1M
ReleasedAug 26, 2026
Providers
40 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.04 | $0.20 | $0.04 | 0.52s | 70 tps | 100% | |
 Particle AInvfp4 | $0.10 | $0.50 | $0.03 | 0.69s | 126 tps | 100% |
| $0.15 | $0.50 | $0.03 | 0.39s | 168 tps | 100% | |
| $0.12 | $0.30 | $0.03 | 0.51s | 94 tps | 100% | |
 Cohere | $0.15 | $0.50 | $0.03 | 0.79s | 112 tps | 100% |
| $0.11 | $0.35 | $0.03 | 0.40s | 75 tps | 100% | |
| $0.11 | $0.35 | $0.03 | 0.51s | 82 tps | 100% | |
 Fireworks | $0.15 | $0.50 | $0.03 | 0.81s | 113 tps | 100% |
 DigitalOcean | $0.11 | $0.38 | $0.03 | 0.88s | 98 tps | 100% |
| $0.15 | $0.50 | $0.03 | 0.82s | 99 tps | 100% | |
 DeepInfraus · fp4 | $0.15 | $0.50 | $0.03 | 0.95s | 85 tps | 100% |
| $0.04 | $0.30 | $0.02 | 0.89s | 57 tps | 100% | |
| $0.15 | $0.50 | $0.03 | 2.41s | 43 tps | 100% | |
| $0.15 | $0.50 | $0.03 | 1.95s | 22 tps | 100% | |
 NEAR AIfp8 | $0.08 | $0.50 | $0.01 | 1.15s | 29 tps | 100% |
| $0.15 | $0.50 | $0.03 | 0.75s | 54 tps | 100% | |
| $0.03 | $0.09 | $0.03 | 1.78s | 31 tps | 99.97% | |
 CoreWeavenvfp4 | $0.12 | $0.38 | $0.02 | 0.62s | 127 tps | 99.95% |
| $0.23 | $0.75 | $0.04 | 1.18s | 48 tps | 99.95% | |
| $0.09 | $0.29 | $0.02 | 2.16s | 35 tps | 99.95% | |
| $0.14 | $0.47 | $0.02 | 0.74s | 67 tps | 99.92% | |
| $0.19 | $0.60 | $0.06 | 0.78s | 89 tps | 99.92% | |
| $0.03 | $0.16 | $0.02 | 1.98s | 55 tps | 99.87% | |
| $0.15 | $0.50 | $0.03 | 1.11s | 110 tps | 99.84% | |
| $0.05 | $0.20 | $0.05 | 0.45s | 53 tps | 99.77% | |
 Basetenfp8 | $0.15 | $0.50 | $0.03 | 0.69s | 84 tps | 99.7% |
| $0.08 | $0.28 | $0.02 | 2.55s | 48 tps | 99.7% | |
| $0.11 | $0.38 | $0.02 | 2.61s | 41 tps | 99.68% | |
| $0.07 | $0.25 | $0.01 | 1.66s | 90 tps | 99.65% | |
| Fireworksus | $0.23 | $0.75 | $0.04 | 0.42s | 156 tps | 99.47% |
| $0.15 | $0.50 | $0.03 | 1.22s | 103 tps | 99.42% | |
 SiliconFlowfp8 | $0.15 | $0.50 | $0.03 | 2.08s | 33 tps | 99.34% |
| $0.15 | $0.50 | $0.03 | 1.82s | 68 tps | 99.32% | |
| $0.11 | $0.45 | $0.03 | 0.94s | 62 tps | 99.1% | |
| $0.35 | $1.25 | $0.04 | 0.57s | 44 tps | 99.09% | |
 Mistral | $0.15 | $0.50 | $0.03 | 1.35s | 64 tps | 98.91% |
| $0.15 | $0.50 | $0.03 | 1.19s | 92 tps | 98.39% | |
| $0.15 | $0.50 | $0.03 | 3.92s | 41 tps | 93.97% | |
 Darkbloomfp4 | $0.07 | $0.18 | $0.01 | 4.23s | 21 tps | 87.7% |
| Basetenus · fp8 | $0.15 | $0.50 | $0.03 | 0.51s | 104 tps | — |
Market-wide measurements, refreshed every 15 minutes. They describe who serves GLM 5.3 Flash (batch) in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what GLM 5.3 Flash (batch) costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.05
per 1M tokens
Output
$0.18
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
GLM 5.3 Flash (batch) is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s50.0s100.0s150.0s200.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
Wafer (us) Friendli NextBit Cohere Parasail Baseten DeepInfra (us) Mistral Darkbloom AtlasCloud Phala Modal inference.net (us) DigitalOcean GMICloud Inceptron (eu) Fireworks (us) NEAR AI Relace Makora Morph (us) Nebius Token Factory Venice Reka AI Sail Research Z.ai Particle AI Baseten (us) inference.net Open Inference StreamLake Prime Intellect Crusoe NovitaAI Fireworks Together Sail Research (us) CoreWeave Wafer SiliconFlow
0 tok/s2000 tok/s4000 tok/s6000 tok/s8000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AMNov 1, 4 PM
Wafer (us) Friendli NextBit Cohere Parasail Baseten DeepInfra (us) Mistral Darkbloom AtlasCloud Phala Modal inference.net (us) DigitalOcean GMICloud Inceptron (eu) Fireworks (us) NEAR AI Relace Makora Morph (us) Nebius Token Factory Venice Reka AI Sail Research Z.ai Particle AI Baseten (us) inference.net Open Inference StreamLake Prime Intellect Crusoe NovitaAI Fireworks Together Sail Research (us) CoreWeave Wafer SiliconFlow
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.82%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.82%
100% 98% 97% 95%
Oct 31, 6:10 PMNow
Apps
Tools that most often run GLM 5.3 Flash (batch), by tokens this week.
Activity
56367.5B tokens processed market-wide in the last month.
01000.0B2000.0B3000.0B4000.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens
FAQ
Which model id do I use for GLM 5.3 Flash (batch)?
z-ai/glm-5.3-flash:batch. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does GLM 5.3 Flash (batch) hold?
1,048,576 tokens per request, of which up to 131,072 can be the response.
What can it accept and return?
Input: text, image, video. Output: text.
What does GLM 5.3 Flash (batch) cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.05 per 1M input tokens and $0.18 per 1M output tokens.
Who built GLM 5.3 Flash (batch)?
Z.ai, in the GLM family.
Explore
Other models your pass can call.
