Model availability
284 models, 0 of them checked in the last 24 hours with a real request through the Rust gateway.
—up
of 0 checked models
- up
- 0
- degraded
- 0
- down
- 0
- not checked
- 284
Every model by health
- Anthropic
- DeepSeek
- Meta
- Microsoft
- Mistral AI
- Moonshot AI
- OpenAI
- Other
- Qwen
- TypeSafe AI
- xAI
- Z-AI
By model
| Trend | Last 5 | ||||||
|---|---|---|---|---|---|---|---|
| claude-opus-5 Claude Opus 5 is a multimodal foundation model supporting text and image inputs with a 1,000,000-token context window and 128,000 max output tokens. It has a May 2026 knowledge cutoff for multi-stage software engineering. | Anthropic | Not checked yet | — | — | $5.00 / $25.00 | — | — |
| claude-sonnet-5 Claude Sonnet 5 is a multimodal foundation model offering a 1,000,000-token context window and 128,000 max output tokens. It supports text and image inputs with a January 2026 knowledge cutoff for production workflows. | Anthropic | Not checked yet | — | — | $2.00 / $10.00 | — | — |
| claude-fable-5 Claude Fable 5 is a multimodal foundation model supporting text and image inputs with a 1,000,000-token context window and 128,000 max output tokens. It features a January 2026 knowledge cutoff for agentic workflows. | Anthropic | Not checked yet | — | — | $10.00 / $50.00 | — | — |
| claude-opus-4-8 Claude Opus 4.8 is an enterprise-grade model built for sustained collaboration, dynamic workflow execution, and large-scale architectural problem solving. | Anthropic | Not checked yet | — | — | $5.00 / $25.00 | — | — |
| claude-opus-4-7 Claude Opus 4.7 is a deep reasoning model with an upgraded tokenizer and high-resolution vision, engineered for long-horizon software engineering and interface design. | Anthropic | Not checked yet | — | — | $5.00 / $25.00 | — | — |
| claude-sonnet-4-6 Claude Sonnet 4.6 provides balanced speed and intelligence with a 1M token context window, designed for enterprise software engineering and agentic planning. | Anthropic | Not checked yet | — | — | $3.00 / $15.00 | — | — |
| claude-opus-4-6 Claude Opus 4.6 is a multimodal coding and reasoning model with a 1,000,000-token context window and a 128,000 max output token limit. It processes text and image inputs for large codebases and complex agent operations. | Anthropic | Not checked yet | — | — | $5.00 / $25.00 | — | — |
| claude-opus-4-5-20251101 Claude Opus 4.5 from Anthropic — 200K-token context, multimodal vision, function calling. | Anthropic | Not checked yet | — | — | $5.00 / $25.00 | — | — |
| claude-haiku-4-5-20251001 Claude Haiku 4.5 from Anthropic — 200K-token context, multimodal vision, function calling. | Anthropic | Not checked yet | — | — | $1.00 / $5.00 | — | — |
| claude-sonnet-4-5-20250929 Claude Sonnet 4.5 from Anthropic — 200K-token context, multimodal vision, function calling. | Anthropic | Not checked yet | — | — | $3.00 / $15.00 | — | — |
| claude-fable-5-1 | Anthropic | Not checked yet | — | — | $10.00 / $50.00 | — | — |
| claude-opus-5-5 | Anthropic | Not checked yet | — | — | $5.00 / $25.00 | — | — |
| claude-sonnet-5-5 | Anthropic | Not checked yet | — | — | $2.00 / $10.00 | — | — |
| deepseek-v4-pro-0813 DeepSeek-V4-Pro-0813 is the production release of the DeepSeek-V4-Pro architecture, pairing 1.6T MoE parameters with a DSpark speculative decoding engine for accelerated agentic execution, full-stack software engineering, and deep logical reasoning. | DeepSeek | Not checked yet | — | — | $1.60 / $6.40 | — | — |
| deepseek-v4-flash-0731 DeepSeek-V4-Flash-0731 is the production release of DeepSeek-V4-Flash, incorporating an integrated speculative decoding module. It delivers enhanced agentic performance, tool execution, and code synthesis across a 1M-token context window. | DeepSeek | Not checked yet | — | — | $0.20 / $0.40 | — | — |
| deepseek-v4-pro DeepSeek-V4-Pro is a text model with a 1,048,576-token context window, 393,216 max output tokens, evaluated at 87.5 on MMLU-Pro, 90.1 on GPQA Diamond, and 80.6 on SWE-bench Verified. | DeepSeek | Not checked yet | — | — | $2.40 / $4.80 | — | — |
| deepseek-r1-0528-maas | DeepSeek | Not checked yet | — | — | $1.35 / $5.40 | — | — |
| deepseek-v3.2-maas | DeepSeek | Not checked yet | — | — | $0.56 / $1.68 | — | — |
| deepseek-v4.1-flash | DeepSeek | Not checked yet | — | — | $0.25 / $2.00 | — | — |
| r1 | DeepSeek | Not checked yet | — | — | $1.35 / $5.40 | — | — |
| v3 | DeepSeek | Not checked yet | — | — | $0.58 / $1.68 | — | — |
| v3.2 | DeepSeek | Not checked yet | — | — | $0.62 / $1.85 | — | — |
| gemini-3.1-flash-lite Gemini 3.1 Flash-Lite is Google's lightweight multimodal foundation model for high-throughput tasks. It processes up to 1,048,576 input tokens across text, audio, video, image, and PDF, with 65,536 max output tokens for translation, transcription, and classification. | Not checked yet | — | — | $0.25 / $1.50 | — | — | |
| gemini-3-flash-preview | Not checked yet | — | — | $0.50 / $2.00 | — | — | |
| gemini-3.1-pro-preview | Not checked yet | — | — | $0.50 / $2.00 | — | — | |
| gemini-3.5-flash | Not checked yet | — | — | $1.50 / $9.00 | — | — | |
| gemini-3.5-flash-lite | Not checked yet | — | — | $0.30 / $2.50 | — | — | |
| gemini-3.5-live-translate-preview | Not checked yet | — | — | $0.50 / $2.00 | — | — | |
| gemini-3.6-flash | Not checked yet | — | — | $0.75 / $3.75 | — | — | |
| gemini-3.7-flash | Not checked yet | — | — | $0.75 / $3.75 | — | — | |
| gemini-3.8-flash | Not checked yet | — | — | $0.75 / $3.75 | — | — | |
| gemini-live-2.5-flash-native-audio | Not checked yet | — | — | $0.50 / $2.00 | — | — | |
| gemma-3-12b-it | Not checked yet | — | — | $0.09 / $0.29 | — | — | |
| gemma-3-27b-it | Not checked yet | — | — | $0.23 / $0.38 | — | — | |
| gemma-3-4b-it | Not checked yet | — | — | $0.04 / $0.08 | — | — | |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | Meta | Not checked yet | — | — | $1.41 / $0.35 | — | — |
| Llama-4-Scout-17B-16E-Instruct | Meta | Not checked yet | — | — | $0.20 / $0.78 | — | — |
| llama3-1-70b-instruct | Meta | Not checked yet | — | — | $0.99 / $0.99 | — | — |
| llama3-1-8b-instruct | Meta | Not checked yet | — | — | $0.22 / $0.22 | — | — |
| llama3-3-70b-instruct | Meta | Not checked yet | — | — | $0.72 / $0.72 | — | — |
| llama4-maverick-17b-instruct | Meta | Not checked yet | — | — | $0.24 / $0.97 | — | — |
| llama4-scout-17b-instruct | Meta | Not checked yet | — | — | $0.17 / $0.66 | — | — |
| Phi-4-mini-instruct Phi-4-mini-instruct is Microsoft's 3.8-billion parameter lightweight instruction-tuned model featuring a 128K context window, engineered for high-throughput edge and latency-sensitive server workloads. | Microsoft | Not checked yet | — | — | $0.07 / $0.30 | — | — |
| Phi-4-mini-reasoning Phi-4-mini-reasoning is Microsoft's compact reasoning model delivering chain-of-thought problem solving in mathematics and logic within a 128K token context window. | Microsoft | Not checked yet | — | — | $0.08 / $0.32 | — | — |
| Phi-4-multimodal-instruct Phi-4-multimodal-instruct is Microsoft's 5.6-billion parameter multimodal model accepting text, vision, and audio inputs with a 128K context window for cross-modality comprehension. | Microsoft | Not checked yet | — | — | $0.08 / $0.32 | — | — |
| Phi-4-reasoning Phi-4-reasoning is Microsoft's 14-billion parameter reasoning model specialized in step-by-step logical deduction, STEM proofs, and rigorous code verification. | Microsoft | Not checked yet | — | — | $0.13 / $0.50 | — | — |
| Phi-4 Phi-4 is Microsoft's 14-billion parameter language model engineered for complex reasoning, mathematical problem solving, and code generation, trained on synthetic reasoning datasets and curated web texts. | Microsoft | Not checked yet | — | — | $0.13 / $0.50 | — | — |
| devstral-2-123b | Mistral AI | Not checked yet | — | — | $0.40 / $2.00 | — | — |
| magistral-small-2509 | Mistral AI | Not checked yet | — | — | $0.50 / $1.50 | — | — |
| ministral-3-14b-instruct | Mistral AI | Not checked yet | — | — | $0.20 / $0.20 | — | — |
| ministral-3-3b-instruct | Mistral AI | Not checked yet | — | — | $0.10 / $0.10 | — | — |
| ministral-3-8b-instruct | Mistral AI | Not checked yet | — | — | $0.15 / $0.15 | — | — |
| mistral-large-3-675b-instruct | Mistral AI | Not checked yet | — | — | $0.50 / $1.50 | — | — |
| mistral-medium-2505 | Mistral AI | Not checked yet | — | — | $0.40 / $2.00 | — | — |
| mistral-small-2503 | Mistral AI | Not checked yet | — | — | $0.10 / $0.30 | — | — |
| pixtral-large-2502 | Mistral AI | Not checked yet | — | — | $2.00 / $6.00 | — | — |
| voxtral-mini-3b-2507 | Mistral AI | Not checked yet | — | — | $0.04 / $0.04 | — | — |
| voxtral-small-24b-2507 | Mistral AI | Not checked yet | — | — | $0.10 / $0.30 | — | — |
| kimi-k2-thinking | Moonshot AI | Not checked yet | — | — | $0.60 / $2.50 | — | — |
| kimi-k2-thinking-maas | Moonshot AI | Not checked yet | — | — | $0.60 / $2.50 | — | — |
| kimi-k2.5 | Moonshot AI | Not checked yet | — | — | $0.60 / $3.00 | — | — |
| kimi-k2.7-code | Moonshot AI | Not checked yet | — | — | $0.95 / $4.00 | — | — |
| kimi-k3 | Moonshot AI | Not checked yet | — | — | $3.00 / $15.00 | — | — |
| kimi/kimi-k3 | Moonshot AI | Not checked yet | — | — | $1.00 / $3.00 | — | — |
| gpt-5.5 GPT-5.5 from OpenAI — 1M-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $5.00 / $30.00 | — | — |
| gpt-5.5-2026-04-23 Fixed snapshot of GPT-5.5 dated April 23, 2026, providing stable reasoning outputs and 1.05 million token context limits for production pipelines. | OpenAI | Not checked yet | — | — | $5.00 / $30.00 | — | — |
| gpt-5.4-mini GPT-5.4 Mini from OpenAI — 1M-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $0.75 / $4.50 | — | — |
| gpt-5.4-mini-2026-03-17 Specific snapshot of GPT-5.4 Mini from March 17, 2026, delivering balanced reasoning performance and 400K context capacity at reduced inference latency. | OpenAI | Not checked yet | — | — | $0.75 / $4.50 | — | — |
| gpt-5.4-nano GPT-5.4 Nano from OpenAI — 1M-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $0.20 / $1.25 | — | — |
| gpt-5.4-nano-2026-03-17 March 17, 2026 snapshot of GPT-5.4 Nano offering rapid response times and 400K context processing for high-volume, budget-conscious production workloads. | OpenAI | Not checked yet | — | — | $0.20 / $1.25 | — | — |
| gpt-5.4 GPT-5.4 from OpenAI — 1M-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $2.50 / $15.00 | — | — |
| gpt-5.4-2026-03-05 Deterministic snapshot of GPT-5.4 from March 5, 2026, featuring a 1,050,000-token context window and 128,000 max output tokens. It processes text and image inputs with an August 2025 knowledge cutoff. | OpenAI | Not checked yet | — | — | $2.50 / $15.00 | — | — |
| gpt-5.3-codex OpenAI's specialized reasoning model fine-tuned for agentic software engineering and long-horizon programming tasks in Codex, featuring a 400,000-token context window and up to 128,000 output tokens. | OpenAI | Not checked yet | — | — | $1.75 / $14.00 | — | — |
| gpt-image-1.5 Enhanced multimodal generation model by OpenAI offering refined prompt adherence, image editing, and text-image generation outputs. | OpenAI | Not checked yet | — | — | $40.00 / $40.00 | — | — |
| gpt-5.2 GPT-5.2 from OpenAI — 272K-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $1.75 / $14.00 | — | — |
| gpt-5.2-2025-12-11 Pinned snapshot of GPT-5.2 released on December 11, 2025, offering deterministic reasoning behavior and 400K token context capacity for production systems. | OpenAI | Not checked yet | — | — | $1.75 / $14.00 | — | — |
| sora-2 Next-generation video synthesis foundation model from OpenAI producing high-definition video clips with synchronized audio from text and images. | OpenAI | Not checked yet | — | — | $2.00 / $8.00 | — | — |
| gpt-5.1 GPT-5.1 from OpenAI — 272K-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $1.25 / $10.00 | — | — |
| gpt-5.1-2025-11-13 Snapshot of GPT-5.1 featuring 400K context input and 128K output limits for reliable production agent deployment. | OpenAI | Not checked yet | — | — | $1.25 / $10.00 | — | — |
| sora-2-pro Professional-tier OpenAI video generation model delivering high-resolution video clips with synchronized audio and fine-grained camera control. | OpenAI | Not checked yet | — | — | $2.00 / $8.00 | — | — |
| gpt-5 GPT-5 from OpenAI — 272K-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $1.25 / $10.00 | — | — |
| gpt-5-2025-08-07 OpenAI's August 7, 2025 production snapshot of GPT-5, providing deep reasoning capabilities across a 400,000-token context window with configurable reasoning effort for complex coding, math, and agentic workflows. | OpenAI | Not checked yet | — | — | $1.25 / $10.00 | — | — |
| gpt-5-mini GPT-5 Mini from OpenAI — 272K-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $0.25 / $2.00 | — | — |
| gpt-5-mini-2025-08-07 Initial snapshot of GPT-5 Mini featuring 400K context capacity and up to 128K generation tokens for cost-efficient reasoning. | OpenAI | Not checked yet | — | — | $0.25 / $2.00 | — | — |
| gpt-5-nano GPT-5 Nano from OpenAI — 272K-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $0.05 / $0.40 | — | — |
| gpt-5-nano-2025-08-07 Snapshot of GPT-5 Nano offering 400K context input support and fast inference for cost-sensitive automation pipelines. | OpenAI | Not checked yet | — | — | $0.05 / $0.40 | — | — |
| o3 o3 from OpenAI — 200K-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $2.00 / $8.00 | — | — |
| o3-2025-04-16 April 16, 2025 checkpoint of OpenAI o3, setting high benchmarks on mathematics, code generation, and visual reasoning across a 200,000-token context window with up to 100,000 generation tokens. | OpenAI | Not checked yet | — | — | $2.00 / $8.00 | — | — |
| o4-mini o4-mini from OpenAI — 200K-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $1.10 / $4.40 | — | — |
| o4-mini-2025-04-16 April 16, 2025 snapshot of o4-mini featuring multimodal perception and 100K token output generation, ranked 160 on the LM Arena text leaderboard. | OpenAI | Not checked yet | — | — | $1.10 / $4.40 | — | — |
| gpt-4.1 GPT-4.1 from OpenAI — 1M-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $2.00 / $8.00 | — | — |
| gpt-4.1-2025-04-14 Primary snapshot of GPT-4.1 offering million-token context processing, multimodal inputs, and high-volume reasoning support. | OpenAI | Not checked yet | — | — | $2.00 / $8.00 | — | — |
| gpt-4.1-mini GPT-4.1 Mini from OpenAI — 1M-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $0.40 / $1.60 | — | — |
| gpt-4.1-mini-2025-04-14 Snapshot of GPT-4.1 Mini providing 1,047,576 context tokens and high-speed execution for lightweight reasoning and data parsing. | OpenAI | Not checked yet | — | — | $0.40 / $1.60 | — | — |
| gpt-4.1-nano GPT-4.1 Nano from OpenAI — 1M-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $0.10 / $0.40 | — | — |
| gpt-4.1-nano-2025-04-14 Dated release of GPT-4.1 Nano combining sub-dollar token economics with large-context ingestion and rapid classification capability. | OpenAI | Not checked yet | — | — | $0.10 / $0.40 | — | — |
| gpt-4o-mini-transcribe Speech-to-text transcription model powered by GPT-4o Mini for fast and accurate audio transcription with language hints. | OpenAI | Not checked yet | — | — | $1.25 / $5.00 | — | — |
| o1-pro-2025-03-19 Compute-intensive version of o1 dated March 19, 2025, using additional reasoning compute for high-difficulty analytical and mathematical queries. | OpenAI | Not checked yet | — | — | $150.00 / $600.00 | — | — |
| o3-mini o3-mini from OpenAI — 200K-token context, multimodal vision, function calling. | OpenAI | Not checked yet | — | — | $1.10 / $4.40 | — | — |
| o3-mini-2025-01-31 January 31, 2025 snapshot of o3-mini delivering fast reasoning capabilities, function calling, and 200K token context limits for production services. | OpenAI | Not checked yet | — | — | $1.10 / $4.40 | — | — |
How we measure
Once an hour nRouter sends a real request to each checked model through the same Rust gateway that carries customer traffic, with up to three attempts two minutes apart. Success is the share of the last 24 hours of checks that returned a valid response, latency is the time to a complete response, and speed is output tokens per second. Price is the list price per 1M input and output tokens. A model without a check yet is marked not checked, and a figure that was not measured shows a dash. The page refreshes at most every five minutes.