Z.ai: GLM Latest
z-ai/glm-latestThis model always redirects to the latest GLM model from Z.ai.
Modalities
In / out per 1M$0.06 / $1.20
Context1M
ReleasedAug 19, 2026
Providers
46 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.08 | $1.00 | $0.07 | 1.96s | 66 tps | 100% | |
| $0.08 | $1.40 | $0.08 | 0.50s | 113 tps | 100% | |
| $0.18 | $1.40 | $0.18 | 0.44s | 111 tps | 100% | |
| $0.19 | $4.40 | $0.19 | 1.55s | 71 tps | 100% | |
| $0.50 | $1.50 | $0.12 | 1.57s | 90 tps | 100% | |
| $0.50 | $1.50 | $0.12 | 0.82s | 83 tps | 100% | |
| $0.70 | $2.20 | $0.13 | 2.07s | 56 tps | 100% | |
| $0.84 | $2.64 | $0.16 | 2.57s | 51 tps | 100% | |
| $0.84 | $2.68 | $0.19 | 0.90s | 120 tps | 100% | |
| $1.19 | $3.74 | $0.24 | 1.71s | 64 tps | 100% | |
 Baseten (fp4)us · fp4 | $1.40 | $4.40 | $0.14 | 2.37s | 60 tps | 100% |
| $1.40 | $4.40 | $0.26 | 0.90s | 129 tps | 100% | |
| $1.40 | $4.40 | $0.26 | 0.53s | 155 tps | 100% | |
| Baseten (fp4)fp4 | $1.40 | $4.40 | $0.14 | 1.71s | 70 tps | 100% |
| $1.40 | $4.40 | $0.26 | 2.66s | 30 tps | 100% | |
| $1.40 | $4.40 | $0.26 | 3.04s | 48 tps | 100% | |
 Mistraleu · nvfp4 | $1.54 | $4.84 | $0.15 | 2.51s | 53 tps | 100% |
| Baseten (fp8)us · fp8 | $2.10 | $6.60 | $0.21 | 0.76s | 144 tps | 100% |
| Baseten (fp8)fp8 | $2.10 | $6.60 | $0.21 | 0.67s | 142 tps | 100% |
| $2.80 | $8.80 | $0.56 | 0.96s | 70 tps | 100% | |
| $0.08 | $4.38 | $0.08 | 0.84s | 82 tps | 99.97% | |
| $0.55 | $1.00 | $0.18 | 0.62s | 82 tps | 99.97% | |
| $1.40 | $4.40 | $0.26 | 1.05s | 54 tps | 99.96% | |
| $0.49 | $2.60 | $0.19 | 2.30s | 37 tps | 99.94% | |
| $0.05 | $6.00 | $0.03 | 8.79s | 15 tps | 99.88% | |
 SiliconFlowfp8 | $0.70 | $2.20 | $0.13 | 2.21s | 63 tps | 99.88% |
 Fireworks | $1.40 | $4.40 | $0.26 | 1.51s | 61 tps | 99.86% |
 DigitalOcean | $0.91 | $2.86 | $0.17 | 0.73s | 102 tps | 99.83% |
| $1.40 | $4.40 | $0.26 | 1.43s | 74 tps | 99.82% | |
| $1.40 | $4.40 | $0.26 | 2.27s | 41 tps | 99.75% | |
| Fireworks | $2.10 | $6.60 | $0.39 | 0.91s | 148 tps | 99.74% |
| Mistralnvfp4 | $1.40 | $4.40 | $0.14 | 3.07s | 46 tps | 99.67% |
| $0.14 | $4.20 | $0.10 | 7.56s | 11 tps | 99.59% | |
| $1.40 | $4.40 | $0.26 | 0.63s | 118 tps | 99.56% | |
| $1.26 | $3.96 | $0.23 | 0.77s | 87 tps | 99.46% | |
 DeepInfraus · fp4 | $0.56 | $2.50 | $0.13 | 3.08s | 29 tps | 99.26% |
| $1.40 | $4.40 | $0.26 | 0.76s | 93 tps | 99.18% | |
| Mistralnvfp4 | $1.40 | $4.40 | $0.14 | 3.06s | 48 tps | 99.07% |
| $0.18 | $2.95 | $0.15 | 1.90s | 74 tps | 98.7% | |
 ModelRun [by Modular]fp4 | $2.10 | $6.60 | $0.40 | 0.65s | 140 tps | 98.25% |
| $1.40 | $4.40 | $0.26 | 1.47s | 60 tps | 98.22% | |
| $1.40 | $4.40 | $0.26 | 1.85s | 25 tps | 98.05% | |
| $0.14 | $4.40 | $0.10 | 1.02s | 78 tps | 97.73% | |
| $1.40 | $4.40 | Variable | 1.28s | 103 tps | 94.93% | |
 CoreWeavefp8 | $1.20 | $4.00 | $0.19 | 0.58s | 108 tps | 92.6% |
| $0.60 | $2.50 | $0.10 | 6.15s | 61 tps | 86.61% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves GLM Latest in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what GLM Latest costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.06
per 1M tokens
Output
$1.20
per 1M tokens
Cache read
$0.06
per 1M cached tokens
Included in every pass
GLM Latest 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.
0.0s100.0s200.0s300.0s400.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Prime Intellect Together GMICloud Alibaba Cloud Int. Cloudflare Baseten (fp8) (us) SiliconFlow Baidu Qianfan Makora DeepInfra (us) Sail Research Phala Fireworks AkashML ModelRun [by Modular] Wafer Alibaba Cloud Int. inference.net Mistral NovitaAI Mistral (eu) Tenstorrent AtlasCloud Sail Research (us) Mistral Reka AI Z.ai Baseten (fp8) Relace io.net Friendli Inceptron (eu) Fireworks Wafer (us) Modal Baseten (fp4) (us) Venice Decart Crusoe Parasail Morph DigitalOcean Baseten (fp4) DekaLLM Nebius Token Factory CoreWeave
0 tok/s2000 tok/s4000 tok/s6000 tok/s8000 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Prime Intellect Together GMICloud Alibaba Cloud Int. Cloudflare Baseten (fp8) (us) SiliconFlow Baidu Qianfan Makora DeepInfra (us) Sail Research Phala Fireworks AkashML ModelRun [by Modular] Wafer Alibaba Cloud Int. inference.net Mistral NovitaAI Mistral (eu) Tenstorrent AtlasCloud Sail Research (us) Mistral Reka AI Z.ai Baseten (fp8) Relace io.net Friendli Inceptron (eu) Fireworks Wafer (us) Modal Baseten (fp4) (us) Venice Decart Crusoe Parasail Morph DigitalOcean Baseten (fp4) DekaLLM Nebius Token Factory CoreWeave
Uptime
Share of requests that at least one provider served successfully.
Last 3 days
Oct 16, 11:00 AMNow
Availability over the last 24 hours
100% 98% 97% 95%
Oct 18, 11:00 AMNow
Apps
Tools that most often run GLM Latest, by tokens this week.
No apps published
This measurement has not been published for the model yet. It appears as soon as it is.
Activity
Tokens processed market-wide.
No activity published
This measurement has not been published for the model yet. It appears as soon as it is.
FAQ
Which model id do I use for GLM Latest?
~z-ai/glm-latest. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does GLM Latest 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. Output: text.
What does GLM Latest cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.06 per 1M input tokens and $1.20 per 1M output tokens.
Who built GLM Latest?
Z.ai, in the GLM family.
Explore
Other models your pass can call.
