API models

1. Auto

   RouterFreeToolsVision
   auto

   Uses the server’s configured route and falls through to the next model on rate limits, errors or stalls.

   1M context$0 / M tokens
2. Speed Router

   RouterFreeTools
   speed-router

   Rates how hard each request is, then picks Qwen 3.8 27B or GPT 6 Luna and the reasoning effort to match.

   1M context$0 / M tokens
3. GPT-OSS 120B

   FreeTools
   gpt-oss-120b

   OpenAI's open-weight 120B model. Very fast on Groq, with Cloudflare and Ollama Cloud as fallbacks.

   Free131K context$0 / M tokens
4. GLM 5.3

   PaidUnavailable
   glm-5.3

   Z.ai GLM 5.3

   $0.07 in · $1.40 out / M tokens
5. Qwen 3.8 27B

   FreeTools
   qwen3.8-27b

   Alibaba's Qwen 3.8 27B.

   Free262K context$0 / M tokens
6. GPT 6 Luna

   FreeTools
   gpt-6-luna

   Paid via Routera. Cheapest GPT 6 model ($0.2 in / $1.2 out per M list price).

   $0.10 in ($0.50 cached) · $0.50 out / M tokens1M context$0 / M tokens
7. Nemotron 3 Ultra

   FreeTools
   nemotron-3-ultra
   Free1M context$0 / M tokens
8. Nemotron 3 Super

   Free
   nemotron-3-super
   Free$0 / M tokens
9. MiniMax M3.1 Flash

   Free
   minimax-m3.1-flash
   Free$0 / M tokens
10. Muse Glimmer 30B

    Free
    muse-glimmer-30b

    Muse Glimmer 30B is a multimodal reasoning model accepting text and images, with native tool-calling and separate reasoning output.

    Free$0 / M tokens
11. North Mini Code

    FreeTools
    north-mini-code

    North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized for code generation, agentic software engineering, and terminal tasks, and is trained to generalize across agent harnesses such as OpenCode and SWE-Agent. It offers a 256K-token context window with up to 64K tokens of output, supports interleaved reasoning and tool use via JSON schema, and is released open-weight under the Apache 2.0 license. Its small active-parameter footprint enables low-latency inference, including on local hardware.

    Free256K context$0 / M tokens
12. Gemma 4 31B

    FreeToolsVision
    gemma-4-31b

    Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

    Free262K context$0 / M tokens
13. Grok 4.7

    PaidToolsVision
    grok-4.7

    Grok 4.7 for reasoning, coding, and tool use.

    $0.10 in ($0.05 cached) · $0.50 out / M tokens256K context$3/M input · $15/M output
14. Claude Haiku 5.5

    PaidToolsVision
    claude-haiku-5.5

    Anthropic's small AI model for general tasks

    $0.10 in · $0.50 out / M tokens1M context$0.10/M input · $0.50/M output
15. Claude Haiku 5.5 (Batch)

    PaidToolsVision
    claude-haiku-5.5-batch
    Free1M context$0.05/M input · $0.25/M output
16. Mercury 3

    PaidUnavailable
    mercury-3
    $0.10 in · $0.35 out / M tokens
17. MiMo-V2.6-Flash

    PaidToolsVision
    mimo-v2.6-flash
    $0.14 in · $0.28 out / M tokens1M context$0.14/M input · $0.28/M output
18. GPT 6.1 Terra

    PaidToolsVision
    gpt-6.1-terra
    $1 in · $5 out / M tokens1M context$1/M input · $5/M output
19. Deepseek v4.1 Flash

    FreeToolsVision
    deepseek-v4.1-flash
    Free1M context$0 / M tokens
20. Agnes 3.0 Flash

    FreeToolsVision
    agnes-3.0-flash
    Free524K context$0 / M tokens
21. Agnes 2.5 Flash

    FreeToolsVision
    agnes-2.5-flash
    Free$0 / M tokens
22. DeepSeek v4.1 Flash

    FreeToolsVision
    deepseek
    $0.01 in · $0.05 out / M tokens1M context$0 / M tokens
23. Jev

    DecisionsFree
    jev

    TypeSafe’s decision model. Send text and typed questions (choice, score, yes/no) to /v1/jev/systemone and get structured answers with probabilities and confidence. Not a chat model.

    Free64K context$0 / M tokens

No models match these filters.