[FEATURE]: Restore the previous 1M context window for opencode/deepseek-v4-flash-free

Feature hasn't been suggested before.

I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

First of all, thank you for maintaining OpenCode and providing access to these models.
opencode/deepseek-v4-flash-free quickly became one of my favorite coding models to use in the terminal.

I noticed that the context window was reduced from around 1M tokens to 200k. I understand there may be infrastructure or cost-related reasons behind the change, but I wanted to express how impactful the larger context window was in real-world usage.

With the larger context size, the model felt significantly more capable for long coding sessions, multi-file reasoning, large refactors, and maintaining consistency across extended conversations. It genuinely stood out compared to many alternatives because it could retain so much project context without losing coherence.

Since the reduction, the experience feels noticeably more constrained, especially on larger repositories and longer sessions. The previous context size made the model extremely practical and competitive for serious development workflows.

If possible, I’d really appreciate reconsidering the decision or offering:

a higher-context variant,
an opt-in “large context” mode,
or even a rate-limited version with the original 1M context.

The larger context window was honestly one of the strongest reasons to use this model through OpenCode.

Thanks again for all the work you’re doing.

This issue doesn't fully meet our contributing guidelines.

What needs to be fixed:

Feature request titles must start with [FEATURE]: (e.g., [FEATURE]: Restore the previous 1M context window for opencode/deepseek-v4-flash-free)

Please edit this issue to address the above within 2 hours, or it will be automatically closed.

This issue might be a duplicate of existing issues. Please check:

Qwen3.6 Plus Context Limit Decreased? #22595: Similar report of a model's context window being reduced unexpectedly

If you believe this was flagged incorrectly, please let a maintainer know.

Thanks for updating the issue! It now meets the contributing guidelines and the needs:compliance label has been removed. We appreciate you taking the time to provide clear context around the impact of the context window change.

Agree, the 1m context did worked very well, if it can be brought back, would be awesome, if it is abused and uses too many resources, maybe you guys could create a new tier account, like a donator account, that if an account donated for example 50$ it can use extra content not available to free tier, one time fee or something no subscription base, at least this can generate some revenue, that otherwise will be 0 because people will stuck to free models. Daily limits are ok, but the 1m context made a difference in quality.

Many are wiling to cintribute to what we believe is a good product and fair offer.

Agree, the 1m context did worked very well, if it can be brought back, would be awesome, if it is abused and uses too many resources, maybe you guys could create a new tier account, like a donator account, that if an account donated for example 50$ it can use extra content not available to free tier, one time fee or something no subscription base, at least this can generate some revenue, that otherwise will be 0 because people will stuck to free models. Daily limits are ok, but the 1m context made a difference in quality.

Many are wiling to cintribute to what we believe is a good product and fair offer.

you can solve this for now by adding this to .config/opencode/opencode.json :

  "provider": {
    "opencode": {
      "models": {
        "deepseek-v4-flash-free": {
          "limit": {
            "context": 1048576,
            "output": 384000
          }
        }
      }
    },
  }

Agree, the 1m context did worked very well, if it can be brought back, would be awesome, if it is abused and uses too many resources, maybe you guys could create a new tier account, like a donator account, that if an account donated for example 50$ it can use extra content not available to free tier, one time fee or something no subscription base, at least this can generate some revenue, that otherwise will be 0 because people will stuck to free models. Daily limits are ok, but the 1m context made a difference in quality.
Many are wiling to cintribute to what we believe is a good product and fair offer.

you can solve this for now by adding this to .config/opencode/opencode.json :
  "provider": {
    "opencode": {
      "models": {
        "deepseek-v4-flash-free": {
          "limit": {
            "context": 1048576,
            "output": 384000
          }
        }
      }
    },
  }

But would this actually work ? since opencode deepseek-v4-flash-free context window was degraded on thier end

Agree, the 1m context did worked very well, if it can be brought back, would be awesome, if it is abused and uses too many resources, maybe you guys could create a new tier account, like a donator account, that if an account donated for example 50$ it can use extra content not available to free tier, one time fee or something no subscription base, at least this can generate some revenue, that otherwise will be 0 because people will stuck to free models. Daily limits are ok, but the 1m context made a difference in quality.
Many are wiling to cintribute to what we believe is a good product and fair offer.

you can solve this for now by adding this to .config/opencode/opencode.json :
  "provider": {
    "opencode": {
      "models": {
        "deepseek-v4-flash-free": {
          "limit": {
            "context": 1048576,
            "output": 384000
          }
        }
      }
    },
  }
But would this actually work ? since opencode deepseek-v4-flash-free context window was degraded on thier end

Yeah it works, but in my opinion it is easier to just turn off compaction and then manually compact when needed.

Agree, the 1m context did worked very well, if it can be brought back, would be awesome, if it is abused and uses too many resources, maybe you guys could create a new tier account, like a donator account, that if an account donated for example 50$ it can use extra content not available to free tier, one time fee or something no subscription base, at least this can generate some revenue, that otherwise will be 0 because people will stuck to free models. Daily limits are ok, but the 1m context made a difference in quality.
Many are wiling to cintribute to what we believe is a good product and fair offer.

you can solve this for now by adding this to .config/opencode/opencode.json :
  "provider": {
    "opencode": {
      "models": {
        "deepseek-v4-flash-free": {
          "limit": {
            "context": 1048576,
            "output": 384000
          }
        }
      }
    },
  }
But would this actually work ? since opencode deepseek-v4-flash-free context window was degraded on thier end
Yeah it works, but in my opinion it is easier to just turn off compaction and then manually compact when needed.

Yeah it worked for me, game changer ...

Agree, the 1m context did worked very well, if it can be brought back, would be awesome, if it is abused and uses too many resources, maybe you guys could create a new tier account, like a donator account, that if an account donated for example 50$ it can use extra content not available to free tier, one time fee or something no subscription base, at least this can generate some revenue, that otherwise will be 0 because people will stuck to free models. Daily limits are ok, but the 1m context made a difference in quality.
Many are wiling to cintribute to what we believe is a good product and fair offer.

you can solve this for now by adding this to .config/opencode/opencode.json :
  "provider": {
    "opencode": {
      "models": {
        "deepseek-v4-flash-free": {
          "limit": {
            "context": 1048576,
            "output": 384000
          }
        }
      }
    },
  }

Doesnt it just make you lose context? as I understand this if the context window of the model itself is 200k, increasing it in client side only will result in losing context? increasing it from client side just makes the app not comapact it at 200k or push more context but from server end it trims 800k context and recieves 200k. Please correct me if I am wrong, did any one tested it?

Agree, the 1m context did worked very well, if it can be brought back, would be awesome, if it is abused and uses too many resources, maybe you guys could create a new tier account, like a donator account, that if an account donated for example 50$ it can use extra content not available to free tier, one time fee or something no subscription base, at least this can generate some revenue, that otherwise will be 0 because people will stuck to free models. Daily limits are ok, but the 1m context made a difference in quality.
Many are wiling to cintribute to what we believe is a good product and fair offer.

you can solve this for now by adding this to .config/opencode/opencode.json :
  "provider": {
    "opencode": {
      "models": {
        "deepseek-v4-flash-free": {
          "limit": {
            "context": 1048576,
            "output": 384000
          }
        }
      }
    },
  }
Doesnt it just make you lose context? as I understand this if the context window of the model itself is 200k, increasing it in client side only will result in losing context? increasing it from client side just makes the app not comapact it at 200k or push more context but from server end it trims 800k context and recieves 200k. Please correct me if I am wrong, did any one tested it?

No try to send to the model more than 1M context it will literally tell u u cant an dit works over 200k so that means the server side accepts -1M tokens

Navigation Menu

Repository navigation

[FEATURE]: Restore the previous 1M context window for `opencode/deepseek-v4-flash-free` #27929

Feature hasn't been suggested before.

Describe the enhancement you want to request

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

[FEATURE]: Restore the previous 1M context window for opencode/deepseek-v4-flash-free #27929

Description

Feature hasn't been suggested before.

Describe the enhancement you want to request

Activity

github-actions commented on May 16, 2026

github-actions commented on May 16, 2026

Imnobot commented on May 18, 2026

djeddi-yacine commented on May 18, 2026

np4abdou1 commented on Jul 3, 2026

TopProjectsCreator commented on Jul 4, 2026

np4abdou1 commented on Jul 4, 2026

alfaisaldev commented on Jul 6, 2026

np4abdou1 commented on Jul 6, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions

[FEATURE]: Restore the previous 1M context window for `opencode/deepseek-v4-flash-free` #27929