GLM 5.3
Flagship GLM model for long-horizon coding, agents, and complex project delivery
- Context
- 1.0M
- Released
- 2mo ago
- Parameters
- 753B
- Input / 1M tokens
- $0.08
- Output / 1M tokens
- $4.80
- Cached input / 1M tokens
- $0.08
Sources:models.devOpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
DeepSWE 1.1
Primary coding-agent benchmark · 113 tasks · Data generated 2026-09-22
- pass@4
- 87.6%
- Average cost / attempt
- $3.99
- Benchmark runs
- 4
pass@1 is the success rate across scored attempts; pass@4 is the share of tasks solved in at least one of four attempts. Costs are reported by DeepSWE for each configuration. These results are not directly comparable to evaluations using different harnesses. Official source JSON.
Other published benchmarks
| Evaluation | Reported score and source |
|---|---|
| FrontierMath-Tier-4-v2-Private | |
| FrontierMath-Tiers-1-3-v2-Private | |
| GPQA diamond | |
| OTIS Mock AIME 2024-2025 | |
| SimpleQA Verified |
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
Specifications
- Developer
- Z.ai
- Model family
- GLM
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- August 14, 2026
- Model ID
z-ai/glm-5.3- Openness
- Open weights
- License
- —
- Parameters
- 753B
- Architecture
- glm_dsa_moe
- Families
- glm_dsa_moe
- Input modalities
- text
- Output modalities
- text
- Modality
- text->text
- Native context
- 1.0M
- Tokenizer
- Other
- Max output tokens
- 944K
- Hugging Face
- zai-org/GLM-5.3
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- zhipuai/glm-5.3
- Source family
- glm
- Last updated
- 2026-08-14
- Model context
- 1M
- Model output limit
- 131K
- Open weights
- Yes
- File attachments
- No
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Temperature control
- Yes
Published benchmarks
| Benchmark | Score | Evaluation details | Evidence |
|---|---|---|---|
| Terminal-Bench | 88.2 · pass@1 | Claude Code 2.1.207 · max effort · 2.1 | Source |
| Terminal-Bench | 28.3 · avg@3 | Claude Code 2.1.207 · max effort · 3.0 | Source |
| DeepSWE | 66.9 · resolved | mini-swe-agent · max effort; 6h timeout; 400K context · 1.1 | Source |
| NL2Repo | 58 · score | max effort | Source |
| ProgramBench | 19 · almost solved | max effort | Source |
| FrontierSWE | 78.1 · dominance score | max effort · 2026-08-14 | Source |
| SWE-Marathon | 42.5 · score | Claude Code 2.1.207 · max effort; modified anti-cheat checks · 1.1 | Source |
| PostTrainBench | 39.8 · weighted average | Claude Code 2.1.207 · max effort; 3 runs; modified external-API checks | Source |
| CyberGym | 84.5 · pass@1 | Claude Code 2.1.207 · max effort | Source |
| ExploitGym | 105 · tasks solved | Claude Code 2.1.207 · 869 tasks · max effort; 2h rescaled timeout | Source |
| ExploitGym | 130 · tasks solved | Claude Code 2.1.207 · 869 tasks · max effort; 6h rescaled timeout | Source |
| ExploitBench | 54.4 · average coverage | Claude Code 2.1.207 · max effort; union over 3 revisions | Source |
| Toolathlon-Verified | 73 · pass@1 | max effort | Source |
| AutomationBench | 48.2 · pass@1 | max effort · 1.0.6 | Source |
| Agents' Last Exam | 28.5 · score | Claude Code 2.1.207 · max effort; CLI | Source |
| Humanity's Last Exam | 62.5 · accuracy | max effort; with tools | Source |
| GDPval-AA | 1769 · Elo | max effort · 2 | Source |
Complete source record (JSON)
{
"id": "zhipuai/glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"family": "glm",
"last_updated": "2026-08-14",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"temperature": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"benchmarks": [
{
"name": "Terminal-Bench",
"score": 88.2,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "pass@1",
"harness": "Claude Code 2.1.207",
"variant": "max effort",
"version": "2.1"
},
{
"name": "Terminal-Bench",
"score": 28.3,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "avg@3",
"harness": "Claude Code 2.1.207",
"variant": "max effort",
"version": "3.0"
},
{
"name": "DeepSWE",
"score": 66.9,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "resolved",
"harness": "mini-swe-agent",
"variant": "max effort; 6h timeout; 400K context",
"version": "1.1"
},
{
"name": "NL2Repo",
"score": 58,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "score",
"variant": "max effort"
},
{
"name": "ProgramBench",
"score": 19,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "almost solved",
"variant": "max effort"
},
{
"name": "FrontierSWE",
"score": 78.1,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "dominance score",
"variant": "max effort",
"date": "2026-08-14"
},
{
"name": "SWE-Marathon",
"score": 42.5,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "score",
"harness": "Claude Code 2.1.207",
"variant": "max effort; modified anti-cheat checks",
"version": "1.1"
},
{
"name": "PostTrainBench",
"score": 39.8,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "weighted average",
"harness": "Claude Code 2.1.207",
"variant": "max effort; 3 runs; modified external-API checks"
},
{
"name": "CyberGym",
"score": 84.5,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "pass@1",
"harness": "Claude Code 2.1.207",
"variant": "max effort"
},
{
"name": "ExploitGym",
"score": 105,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "tasks solved",
"harness": "Claude Code 2.1.207",
"variant": "max effort; 2h rescaled timeout",
"dataset": "869 tasks"
},
{
"name": "ExploitGym",
"score": 130,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "tasks solved",
"harness": "Claude Code 2.1.207",
"variant": "max effort; 6h rescaled timeout",
"dataset": "869 tasks"
},
{
"name": "ExploitBench",
"score": 54.4,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "average coverage",
"harness": "Claude Code 2.1.207",
"variant": "max effort; union over 3 revisions"
},
{
"name": "Toolathlon-Verified",
"score": 73,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "pass@1",
"variant": "max effort"
},
{
"name": "AutomationBench",
"score": 48.2,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "pass@1",
"variant": "max effort",
"version": "1.0.6"
},
{
"name": "Agents' Last Exam",
"score": 28.5,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "score",
"harness": "Claude Code 2.1.207",
"variant": "max effort; CLI"
},
{
"name": "Humanity's Last Exam",
"score": 62.5,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "accuracy",
"variant": "max effort; with tools"
},
{
"name": "GDPval-AA",
"score": 1769,
"source": "https://huggingface.co/zai-org/GLM-5.3",
"metric": "Elo",
"variant": "max effort",
"version": "2"
}
],
"release_date": "2026-08-14",
"open_weights": true
}Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| relace | 1.0M | $0.02 | $4.40 | $0.02 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| wafer | 1.0M | $0.03 | $4.80 | $0.03 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| relaceBatch pricing | 1.0M | $0.06 | $4.40 | $0.06 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| wafer/us | 1.0M | $0.08 | $4.80 | $0.08 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| wafer/usBatch pricing | 1.0M | $0.08 | $4.80 | $0.08 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| inference-net/fp4 | 1.0M | $0.08 | $4.80 | $0.06 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| inference-net/fp4Batch pricing | 1.0M | $0.08 | $4.40 | $0.06 | — | 99.86% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| morph/fp8Batch pricing | 1.0M | $0.08 | $6.00 | $0.08 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| morph/fp8 | 1.0M | $0.09 | $6.00 | $0.09 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| makora/fp4 | 1.0M | $0.14 | $4.40 | $0.10 | — | 95.11% | ZDR: Yes | |
| makora/fp4Batch pricing | 1.0M | $0.14 | $4.40 | $0.10 | — | 92.48% | ZDR: No | |
| reka | 262K | $0.14 | $4.20 | $0.11 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| rekaBatch pricing | 262K | $0.14 | $4.20 | $0.11 | — | 99.72% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| sail-research/us | 1.0M | $0.15 | $3.40 | $0.14 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| sail-research/fp8 | 1.0M | $0.15 | $3.40 | $0.14 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| sail-research/usBatch pricing | 1.0M | $0.15 | $3.40 | $0.14 | — | 99.58% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| sail-research/fp8Batch pricing | 1.0M | $0.15 | $3.40 | $0.14 | — | 99.51% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| waferBatch pricing | 1.0M | $0.17 | $4.80 | $0.17 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| akashml/fp8 | 1.0M | $0.19 | $4.40 | $0.19 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| akashml/fp8Batch pricing | 1.0M | $0.19 | $4.40 | $0.19 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| io-net/fp8 | 262K | $0.49 | $2.90 | $0.19 | — | 99.57% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| io-net/fp8Batch pricing | 262K | $0.49 | $2.90 | $0.19 | — | 99.69% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| inceptron/fp4 | 1.0M | $0.55 | $2.20 | $0.18 | — | 99.79% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| inceptron/fp4Batch pricing | 1.0M | $0.55 | $2.20 | $0.18 | — | 99.64% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| deepinfra/fp4 | 1.0M | $0.56 | $2.50 | $0.13 | — | 98.89% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| deepinfra/fp4Batch pricing | 1.0M | $0.56 | $2.50 | $0.13 | — | 98.01% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| tenstorrent/fp8 | 1.0M | $0.60 | $2.50 | $0.10 | — | 95.99% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| tenstorrent/fp8Batch pricing | 1.0M | $0.60 | $2.50 | $0.10 | — | 97.11% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| novita/fp8 | 1.0M | $0.70 | $2.20 | $0.13 | — | 99.21% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| novita/fp8Batch pricing | 1.0M | $0.70 | $2.20 | $0.13 | — | 99.93% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| siliconflow/fp8 | 1.0M | $0.70 | $2.20 | $0.13 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| siliconflow/fp8Batch pricing | 1.0M | $0.70 | $2.20 | $0.13 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| decart/fp4 | 1.0M | $0.84 | $4.40 | $0.16 | — | 99.93% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| decart/fp4Batch pricing | 1.0M | $0.84 | $2.66 | $0.19 | — | 99.86% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| phala | 1.0M | $0.84 | $2.64 | $0.16 | — | 99.76% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| phalaBatch pricing | 1.0M | $0.84 | $2.64 | $0.16 | — | 99.78% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| digitalocean | 1.0M | $0.91 | $2.86 | $0.17 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| digitaloceanBatch pricing | 1.0M | $0.91 | $2.86 | $0.17 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| gmicloud/fp8 | 1.0M | $0.98 | $3.08 | $0.18 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| gmicloud/fp8Batch pricing | 1.0M | $0.98 | $3.08 | $0.18 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| alibaba | 1M | $1.19 | $3.74 | $0.24 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| alibabaBatch pricing | 1M | $1.19 | $3.74 | $0.24 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| friendli | 1.0M | $1.26 | $3.96 | $0.23 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| friendliBatch pricing | 1.0M | $1.26 | $3.96 | $0.23 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| atlas-cloud/fp8 | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| atlas-cloud/fp8Batch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baidu/fp8 | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baidu/fp8Batch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baseten/fp4 | 1.0M | $1.40 | $4.40 | $0.14 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baseten/fp4/us | 1.0M | $1.40 | $4.40 | $0.14 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baseten/fp4Batch pricing | 1.0M | $1.40 | $4.40 | $0.14 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baseten/fp4/usBatch pricing | 1.0M | $1.40 | $4.40 | $0.14 | — | 99.91% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| cloudflare | 1.0M | $1.40 | $4.40 | $0.26 | — | 80.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| cloudflareBatch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| crusoe/fp4 | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| crusoe/fp4Batch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 99.58% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| fireworks | 1.0M | $1.40 | $4.40 | $0.26 | — | 96.81% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| fireworksBatch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 96.84% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/zdr | 1.0M | $1.40 | $4.40 | $0.14 | — | 99.72% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/nvfp4 | 1.0M | $1.40 | $4.40 | $0.14 | — | 99.79% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/zdrBatch pricing | 1.0M | $1.40 | $4.40 | $0.14 | — | 99.79% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/nvfp4Batch pricing | 1.0M | $1.40 | $4.40 | $0.14 | — | 99.72% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| modal | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| modalBatch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| parasail/fp8 | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| parasail/fp8Batch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 99.29% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| primeintellect | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: Yes | |
| primeintellectBatch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: No | |
| together | 1.0M | $1.40 | $4.40 | $0.26 | — | 99.65% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| togetherBatch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 99.23% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| venice | 1M | $1.40 | $4.40 | $0.26 | — | 95.99% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| veniceBatch pricing | 1M | $1.40 | $4.40 | $0.26 | — | 97.11% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| z-ai/fp8 | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| z-ai/fp8Batch pricing | 1.0M | $1.40 | $4.40 | $0.26 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/nvfp4/eu | 1.0M | $1.54 | $4.84 | $0.15 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| mistral/nvfp4/euBatch pricing | 1.0M | $1.54 | $4.84 | $0.15 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baseten/fast | 1.0M | $2.10 | $6.60 | $0.21 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baseten/us/fast | 1.0M | $2.10 | $6.60 | $0.21 | — | 99.89% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baseten/fastBatch pricing | 1.0M | $2.10 | $6.60 | $0.21 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| baseten/us/fastBatch pricing | 1.0M | $2.10 | $6.60 | $0.21 | — | 99.89% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| fireworks/fast | 1.0M | $2.10 | $6.60 | $0.39 | — | 97.10% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| fireworks/fastBatch pricing | 1.0M | $2.10 | $6.60 | $0.39 | — | 97.10% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| modelrun/fp4 | 1.0M | $2.10 | $6.60 | $0.40 | — | 76.16% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| modelrun/fp4Batch pricing | 1.0M | $2.10 | $6.60 | $0.40 | — | 79.37% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| alibaba/prime | 1M | $2.80 | $8.80 | $0.56 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| alibaba/primeBatch pricing | 1M | $2.80 | $8.80 | $0.56 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.