Skip to main content

Text Models

Chat, reasoning, coding and agent models, priced per 1M tokens.

144 families · 148 model IDs · prices per 1M tokensUpdated Nov 21, 2026
  • Gemini 4 NeonNew$3.75 / $18.75 per 1M

    Gemini 4 Neon is Google’s low-latency model for coding, multi-step reasoning, and multimodal understanding in agentic workflows, with a unified 1M token context window and tunable thinking.

    Anonymized · 1M context · 64K max output · $0.1875/M cached input
  • GPT-6.2 AstraNew$8.00 / $40.00 per 1M

    GPT-6.2 Astra is the flagship model in OpenAI’s GPT-6.2 series, built for the hardest projects.

    Anonymized · 1.05M context · 128K max output · $0.40/M cached input
  • GPT-6.2 Astra ProNew$8.00 / $40.00 per 1M

    GPT-6.2 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra.

    Anonymized · 1.05M context · 128K max output · $0.40/M cached input
  • GPT-6.2 SolNew$2.00 / $10.00 per 1M

    GPT-6.2 Sol is an upgrade to GPT-6.1 Sol, positioned below GPT-6.2 Astra. It is an efficient, versatile model for everyday work, suited for multistep agentic workflows and clear, natural writing across technical and non-technical tasks.

    Anonymized · 1.05M context · 128K max output · $0.10/M cached input
  • GPT-6.2 Sol ProNew$2.00 / $10.00 per 1M

    GPT-6.2 Sol with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Sol.

    Anonymized · 1.05M context · 128K max output · $0.10/M cached input
  • Kimi K3.1 Pro E2EENew$2.50 / $12.50 per 1M

    Kimi K3.1 Pro is Moonshot AI’s flagship multimodal reasoning model and the post-trained successor to Kimi K3, with a 1M-token context window.

    1M context · 128K max output · $0.25/M cached input
  • Qwen 4 MaxNew$1.50 / $4.50 per 1M

    Qwen 4 Max is the flagship model of the Qwen 4 series. It accepts text, image, and video input, thinks by default with adjustable reasoning effort, and supports a 1M-token context window.

    Anonymized · 1M context · 384K max output · $0.075/M cached input
  • Gemini 4 HydrogenNew$1.88 / $9.38 per 1M

    Gemini 4 Hydrogen is Google’s fast, efficient model for coding and agentic work, with a unified 1M token context window and tunable thinking.

    Anonymized · 1M context · 64K max output · $0.0938/M cached input
  • GLM 5.3 Flash UncensoredNew$0.165 / $0.55 per 1M

    GLM 5.3 Flash Uncensored is an abliterated, uncensored variant of GLM-5.3 Flash, a reasoning model designed for coding, sustained agentic work, and production workloads, with a 1M-token context window.

    Private · 1M context · 128K max output · $0.033/M cached input
  • Gemini 4 CarbonNew$2.50 / $12.50 per 1M

    Gemini 4 Carbon is Google’s frontier model for long-horizon agentic work across software engineering, scientific reasoning, and cybersecurity defense, with a unified 1M token context window and deeper tunable thinking than Gemini 4 Argon.

    Anonymized · 1M context · 64K max output · $0.125/M cached input
  • Claude Fable 5.2New$8.00 / $40.00 per 1M

    Claude Fable 5.2 improves on Claude Fable 5.1 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end development, and finance and analysis tasks.

    Anonymized · 1M context · 128K max output · $0.20/M cached input
  • DeepSeek V4.1 Flash 1017 Abliterated running in a Trusted Execution Environment (TEE). A text-only reasoning and coding model with refusal behavior removed and a 1M-token context window.

    1M context · 128K max output · $0.0075/M cached input
  • DeepSeek V4.1 Flash 1017 Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash 1017, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

    Private · 1M context · 128K max output · $0.0083/M cached input
  • GPT-6.1 TerraNew$1.00 / $5.00 per 1M

    GPT-6.1 Terra is a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.

    Anonymized · 1.05M context · 128K max output · $0.05/M cached input
  • Abliterated Large FlashNew$1.25 / $2.50 per 1M

    Abliterated Large Flash is Abliteration AI’s unrestricted multimodal model, based on DeepSeek V4.1 Flash and further abliterated. It has 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

    Anonymized · 1M context · 128K max output · $0.125/M cached input
  • DeepSeek V4.1 Flash 1017 UltrafastNew$1.50 / $6.00 per 1M

    DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

    Private · 1M context · 128K max output · $0.03/M cached input
  • DeepSeek V4.1 Flash UncensoredNew$0.33 / $1.32 per 1M

    DeepSeek V4.1 Flash Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

    Private · 1M context · 128K max output · $0.0083/M cached input
  • Kimi K3.1 ProNew$2.00 / $10.00 per 1M

    Kimi K3.1 Pro is Moonshot AI’s flagship multimodal reasoning model and the post-trained successor to Kimi K3, with a 1M-token context window.

    Private · 1M context · 128K max output · $0.20/M cached input
  • Kimi K3.1 Pro HighspeedNew$5.00 / $25.00 per 1M

    Kimi K3.1 Pro Highspeed is the faster variant of Kimi K3.1 Pro, Moonshot AI’s flagship multimodal reasoning model.

    Anonymized · 1M context · 128K max output · $0.375/M cached input
  • MiniMax M3.1 Flash$0.1875 / $0.75 per 1M

    MiniMax M3.1 Flash is a frontier model for coding, agentic workflows, and complex reasoning, with a 1M-token context window, text, image, and video input, and tunable thinking depth from low to max (max by default).

    Private · 1M context · 128K max output · $0.0187/M cached input
  • DeepSeek v4.1 Flash (1017)$0.30 / $1.20 per 1M

    DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

    Private · 1M context · 256K max output · $0.0075/M cached input
  • NVIDIA Nemotron 3.5 Super VL is an open multimodal vision-language model for specialized agents.

    Private · 256K context · 100K max output · $0.04/M cached input
  • Muse Spark Open$1.56 / $5.31 per 1M

    Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows.

    Private · 1M context · 128K max output · $0.1875/M cached input
  • ParetoBeta$1.00 / $4.00 per 1M

    Pareto is a blended model that runs several frontier models in parallel on every request and returns one answer. It accepts text and image inputs.

    Anonymized · 1M context · 32K max output · $0.0375/M cached input
  • Gemini 4 Argon$2.50 / $12.50 per 1M

    Gemini 4 Argon is Google’s frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable thinking.

    Anonymized · 1M context · 64K max output · $0.125/M cached input
  • Muse Wonder$5.00 / $25.00 per 1M

    Muse Wonder is a frontier reasoning model from Meta for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.

    Anonymized · 1M context · 128K max output · $0.25/M cached input
  • GPT-6.1 Sol Ultrafast$12.00 / $60.00 per 1M

    GPT-6.1 Sol Ultrafast is the same model served in OpenAI’s Ultrafast mode, up to 8x faster. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.

    Anonymized · 1.05M context · 128K max output · $0.60/M cached input
  • Claude Haiku 5.5$0.10 / $0.50 per 1M

    Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks.

    Anonymized · 1M context · 128K max output · $0.01/M cached input
  • Abliterated Large V2$3.00 / $5.00 per 1M

    Abliterated Large V2 is Abliteration AI’s unrestricted reasoning model, based on GLM-5.3 and further abliterated and fine-tuned. Text-only with 1M context, for harder reasoning and evaluation workloads.

    Anonymized · 1M context · 32K max output · $0.30/M cached input
  • GPT-6.1 Sol$2.00 / $10.00 per 1M

    GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work.

    Anonymized · 1.05M context · 128K max output · $0.10/M cached input
  • MiMo-V2.6-Flash$0.175 / $0.35 per 1M

    MiMo-V2.6-Flash is Xiaomi’s efficiency-balanced omnimodal model: a sparse Mixture-of-Experts with 309B total and 15B activated parameters, natively understanding text, image, video, and audio with a 1M-token context window.

    Private · 1M context · 128K max output · $0.0037/M cached input
  • Claude Opus 5.5$4.00 / $20.00 per 1M

    Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work.

    +1 variantAnonymized · 1M context · 128K max output · $0.20/M cached input
  • Claude Sonnet 5.5$2.00 / $10.00 per 1M

    Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets.

    Anonymized · 1M context · 128K max output · $0.10/M cached input
  • Aion 3.5$3.75 / $7.50 per 1M

    Aion 3.5, the successor to Aion 3.0, is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models, with a longer context window.

    Anonymized · 256K context · 32K max output · $0.9375/M cached input
  • Aion 3.5 Mini$0.875 / $1.75 per 1M

    Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.

    Anonymized · 256K context · 32K max output · $0.225/M cached input
  • GPT-6 Luna$0.10 / $0.50 per 1M

    GPT-6 Luna is OpenAI’s most efficient GPT-6 model for focused, high-volume tasks.

    Anonymized · 1.05M context · 128K max output · $0.01/M cached input
  • GPT-6 Sol$2.00 / $10.00 per 1M

    GPT-6 Sol is built for complex coding and agentic workflows.

    Anonymized · 1.05M context · 128K max output · $0.20/M cached input
  • Grok 4.7$2.27 / $6.80 per 1M

    Grok 4.7, the successor to Grok 4.6, is xAI’s multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.

    Private · 500K context · 200K max output · $0.57/M cached input
  • DeepSeek V4.1 Flash$0.30 / $1.20 per 1M

    DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

    Private · 1M context · 256K max output · $0.0075/M cached input
  • Qwen 3.8 Flash$0.14 / $0.49 per 1M

    Qwen 3.8 Flash is a multimodal model in the Qwen family, pairing strong reasoning and generation with remarkable speed.

    Anonymized · 1M context · 128K max output · $0.014/M cached input
  • Kimi K3 E2EE$3.75 / $18.75 per 1M

    Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows.

    1M context · 128K max output · $0.375/M cached input
  • GLM 5.3 E2EE$1.75 / $5.50 per 1M

    GLM 5.3 running in a Trusted Execution Environment (TEE). Z.ai’s flagship model with 1M context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.

    1M context · 32K max output · $0.325/M cached input
  • GLM 5.3 Flash E2EE$0.16 / $0.54 per 1M

    GLM 5.3 Flash running in a Trusted Execution Environment (TEE). A fast, low-cost multimodal model with 1M context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.

    1M context · 32K max output · $0.038/M cached input
  • Kimi K2.6 E2EE$0.87 / $4.12 per 1M

    Kimi K2.6 running in a Trusted Execution Environment (TEE). MoonshotAI’s multimodal model with 262K context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.

    256K context · 8K max output · $0.44/M cached input
  • Qwen 3.8 27B E2EE$0.47 / $3.53 per 1M

    Qwen 3.8 27B running in a Trusted Execution Environment (TEE). A multimodal model with 262K context supporting text and image input.

    256K context · 8K max output · $0.047/M cached input
  • GPT-6 Astra$10.00 / $50.00 per 1M

    GPT-6 Astra is OpenAI’s most capable model, built for the hardest end-to-end work.

    Anonymized · 1.05M context · 128K max output · $1.00/M cached input
  • GPT-6 Astra Pro$10.00 / $50.00 per 1M

    GPT-6 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra.

    Anonymized · 1.05M context · 128K max output · $1.00/M cached input
  • Gemini 3.8 Flash$0.9375 / $4.69 per 1M

    Gemini 3.8 Flash, the successor to Gemini 3.7 Flash, is built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.

    Anonymized · 1M context · 64K max output · $0.0938/M cached input
  • Claude Fable 5.1$10.00 / $50.00 per 1M

    Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end development, and finance and analysis tasks.

    Anonymized · 1M context · 128K max output · $0.25/M cached input
  • Hy4 Preview$1.04 / $3.13 per 1M

    Hy4 Preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy team, with 49B parameters active per token and a 1M-token context window.

    Private · 1M context · 64K max output · $0.0525/M cached input
  • GLM 5.3 Flash$0.15 / $0.50 per 1M

    GLM-5.3 Flash is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with visual context.

    Private · 1M context · 128K max output · $0.03/M cached input
  • GLM 5.3$1.75 / $5.50 per 1M

    GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.

    Private · 1M context · 128K max output · $0.325/M cached input
  • Qwen 3.8 27BBeta$0.45 / $3.20 per 1M

    Qwen 3.8 27B is a native vision-language dense model with 27B parameters. It improves coding, professional work, research, and long-horizon agentic tasks, with flexible thinking control and image and video understanding.

    Private · 256K context · 64K max output
  • DeepSeek V4 Pro 0813$1.65 / $4.95 per 1M

    DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window.

    Private · 1M context · 256K max output · $0.165/M cached input
  • Gemini 3.7 Flash$0.9375 / $4.69 per 1M

    Gemini 3.7 Flash, the successor to Gemini 3.6 Flash, is built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.

    Anonymized · 1M context · 64K max output · $0.0938/M cached input
  • Qwen 3.8 2.4T$2.50 / $7.50 per 1M

    Qwen 3.8 2.4T is Alibaba’s open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks.

    Private · 256K context · 64K max output · $0.3125/M cached input
  • Grok 4.6$2.27 / $6.80 per 1M

    Grok 4.6 is xAI’s multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.

    Private · 500K context · 200K max output · $0.57/M cached input
  • DeepSeek V4 Flash 0731$0.13 / $0.26 per 1M

    DeepSeek V4 Flash 0731 follows the 0423 release of DeepSeek V4 Flash, an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window.

    +1 variantPrivate · 1M context · 256K max output · $0.028/M cached input
  • Kimi K3$3.75 / $18.75 per 1M

    Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI.

    +1 variantPrivate · 1M context · 128K max output · $0.375/M cached input
  • Claude Opus 5$5.00 / $25.00 per 1M

    Claude Opus 5, the successor to Opus 4.8, delivers major gains in agentic coding, professional knowledge work, and long-horizon reasoning, with a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal…

    +1 variantAnonymized · 1M context · 128K max output · $0.50/M cached input

Capabilities

  • Function Calling: Let the model invoke tools and external APIs
  • Reasoning: Extended thinking for complex problem-solving
  • Vision: Analyze images alongside text prompts
  • Code: Optimized for code generation and understanding
See the Chat Completions API for usage examples.